Search

Abstract Central Asia is an ecologically fragile arid zone and a typical mixed salt‒sand region. The socioeconomic and ecological problems attributed to the shrinking of the Aral Sea in Central Asia are notable concerns within the international community. In this study, the characteristics of salt dust aerosols from the Aral Sea were analysed to explore their interannual variation characteristics and analyse the spatial and temporal distributions of salt dust sources and transport and dispersion pathways. The results revealed that high concentrations of salt dust aerosols were concentrated around the Aral Sea and Lake Sarekamesh. The range and intensity of salt dust aerosols were less than those of dust aerosols. Salt dust events occurred frequently in spring and less frequently in autumn and winter. The occurrence frequency and impact range of salt dust aerosols from 2008 to 2012 were significantly lower than those during the previous period. From 2013 to 2018, the salt dust sources originated largely on the western side of the North Aral Sea. The spatial autocorrelation of salt dust aerosols was high and characterized by significant agglomeration, with significant changes in cold spot and hotspot regions. Salt dust in the Aral Sea region affects mainly the Kazakhstan region in spring, and it more notably affects Russia in winter. The results of this study increase the understanding of the spatial and temporal variability in salt dust aerosols within the arid zone of Central Asia and lay a foundation for the study of the impacts of salt dust aerosols on the climate system and ecological environment in arid zones. more...

Remote sensing technology provides an effective means for continuously assessing the chlorophyll content in plants on a broad scale. Given the challenges associated with satellite image quality and spatiotemporal resolution, spatiotemporal fusion algorithms for estimating vegetation chlorophyll content have garnered significant attention in recent years. In this study, we evaluated the performance of four fusion algorithms fusing Gaofen-1 WFV and MODIS data while also exploring their fusion accuracy. A random forest regression model was developed using the fused images and measured SPAD (Soil and Plant Analyzer Development) values, enabling large-scale, accurate, and dynamic monitoring of vegetation chlorophyll content. The results indicate that (1) all four fusion algorithms can effectively address the issue of missing images; (2) the constructed random forest regression model accurately estimates SPAD values; and (3) among the three vegetation indices that exhibit a strong correlation with SPAD values, the fusion strategy “Index-then-Blend” outperforms “Blend-then-Index.” This study provides comprehensive insights into dynamic and large-scale monitoring of vegetation chlorophyll content, particularly in scenarios in which satellite imagery is unavailable. more...

Study Region: Yellow River Basin, China, a region of critical ecological and economic significance. Study Focus: This research presents a novel integrated framework for regional drought-flood analysis and precipitation forecasting by evaluating CMADS-L and ERA5 reanalysis datasets against ground-based observations in the Yellow River Basin. We implement K-means clustering on Standardized Precipitation Evapotranspiration Index (SPEI) sequences to identify drought-flood regions and validate a CNN-LSTM hybrid model for regional precipitation forecasting, uniquely bridging traditional climate analysis with modern deep learning techniques for enhanced prediction accuracy. New Hydrological Insights for the Region: Our Analysis Reveals: (1) CMADS demonstrates superior performance over ERA5 in precipitation representation (r = 0.93 vs 0.92; MAE: 9.6 mm vs 17.5 mm; RMSE: 15.8 mm vs 25.9 mm), providing the first comprehensive evaluation of these datasets in complex terrain; (2) We identify three distinct hydroclimatic zones: Northeast (31.6 % area, ''wet-dry-wet'' sequences, quasi-4.5-year oscillations), Southeast (42.5 %, post-2000 drying trends, quasi-2.3-year cycles), and Western (25.9 %, post-2008 drying, quasi-12-year periodicities); (3) Our novel CNN-LSTM hybrid model achieves unprecedented prediction performance (R²: 0.70–0.85), with highest accuracy in the Western zone due to stable precipitation patterns. This integrated approach significantly advances regional hydroclimate understanding and provides a robust, transferable framework for water resource management under changing climate conditions, offering valuable methodological insights for similar river basins globally. more...

Understanding the threshold responses of vegetation to drought is essential for predicting and mitigating drought risk. Across Central Asia, extreme weather is expected to increase by the end of the 21st century. However, the threshold responses of different Central Asian vegetation types are not well understood. Here, we calculated drought indices for Central Asia based on meteorological data and remotely sensed vegetation indices from 2001 to 2020, used trend analysis to assess changes in drought and vegetation in Central Asia over the past 20 years, evaluated the threshold responses of five vegetation types to drought, and explored the drought causative factors of different vegetation types using coexistence analysis. All five Central Asian vegetation types responded to increasing drought in a nonlinear manner, and thus exhibited drought-responsive thresholds. Forests were the first responders to increasing drought, and wetlands were the least responsive overall. Grasslands, cultivated lands, shrublands, and forests crossed the drought threshold in different years between 2001 and 2020, with shrublands exhibiting the largest percentage of area crossing the threshold. Finally, the drought causative factor for grasslands, shrublands, and wetlands was soil moisture; for cultivated lands was precipitation; and for forests was saturated water vapor pressure difference. This study uncovers the characteristic responses of different Central Asian vegetation types to drought, and lays a theoretical foundation for drought assessment and ecological restoration in Central Asia. more...

The pine wilt disease (PWD) can cause destructive death to pine trees in a short period. Utilizing unmanned aerial vehicle (UAV) remote sensing technology to promptly identify PWD-infected trees has become an effective and feasible method for precise PWD monitoring. In this study, UAV multispectral imagery was used to analyze the sensitive spectral bands and different vegetation indices for PWD discriminability. A dataset of optimal spectral combinations from visible light and multispectral images was constructed, along with an improved YOLOv8 deep learning model for rapid and accurate identification of PWD-infected trees. The improved YOLOv8 model used omni-dimensional dynamic convolution (ODConv) to enhance the performance of convolutional networks, designed a dynamic head (DyHead) module to capture PWD features more accurately, and applied MPDioU to improve the regression accuracy and model runtime efficiency. Experimental results showed that the mAP@0.5 of the improved YOLOv8 model increased to 89.1 %, with a user accuracy of 90 % and a recall rate of 93.1 %. This achieved rapid and accurate detection of PWD-infected trees, providing effective technical support for automatic identification of PWD epidemic areas and control of PWD outbreaks based on UAV multispectral imagery. more...

ABSTRACTThe multi-angle method in the pixel dichotomy model (PDM) is used to produce fine spatial resolution (FSR) products of fractional vegetation cover (FVC), which involves numerous iterative computations. This phenomenon causes a low computational efficiency for global FVC. Here, we established the multi-angle equations, and simplified the two-stream approximation method to obtain multi-angle reflectance, which calculated the KDM parameters possible. Moreover, to accelerate the calculation of parameters in the multi-angle equations, land cover data were utilized as priority knowledge, which aims to decrease iterative computations to speed up the computational speed. Finally, we proposed an accelerated pixel dichotomy coupled linear kernel-driven model (PDKDM-A). By validating PDKDM-A using field measurements and FVC products, we found that the global FVC computed for various land covers exhibited strong agreement with the field measurements. The root mean square errors (RMSEs) were consistently below 0.150, except for grasslands, croplands, and cropland/natural vegetation mosaics. When comparing FVC products on the same scale, we discovered that the RMSE was less than 0.103, except for deciduous broadleaf forests. Our study demonstrates that PDKDM-A is an efficient algorithm, with the potential to quickly generate accurate global FVC products with fine spatial resolution. more...

Soil salinization represents a significant challenge to the ecological environment in arid areas, and digital mapping of soil salinization as well as exploration of its spatial heterogeneity with crop growth have important implications for national food security and salinization management. However, the machine learning models currently used are deficient in mining local information on salinity and do not explore the spatial heterogeneity of salinity impacts on crops. This study developed soil salinization inversion models using CNN (Convolutional Neural Network), LSTM (Long Short-Term Memory Network), and RF (Random Forest) models based on 97 field samples and feature variables extracted from Landsat-8 imagery. By evaluating the accuracy, the best-performing model was selected to map soil salinity at a 30m resolution for the years 2013 and 2022, and to explore the relationship between soil electrical conductivity (EC) values and the expansion of cotton fields as well as their spatial correlation. The results indicate that:(1) The CNN performs best in prediction, with an R2 of 0.84 for the training set and 0.73 for the test set, capable of capturing more local salinity information. (2) The expansion of cotton fields has reduced the level of soil salinization, with the area of severely salinized and saline soils in newly added cotton fields decreasing from 177.91 km2 and 381.46 km2 to 19.49 km2 and 1.12 km2, respectively. (3) Regions with long-term cotton cultivation and newly reclaimed cotton fields exhibit high sensitivity and vulnerability to soil salinity. This study explores the excellent performance of deep learning in salinity mapping and visualizes the spatial distribution of cotton fields that are highly sensitive to soil salinity, providing a scientific theoretical basis for accurate salinity management. more...

Straw mulching is a widespread practice for reducing the soil carbon loss caused by erosion. However, the effects of straw mulching on dissolved organic matter (DOM) runoff loss from black soil are not well studied. How straw mulching affects the composition and loss of runoff DOM by changing soil aggregates remains largely unclear. Here, a straw mulching treatment was compared to a no mulching treatment (as a control) on sloping farmland with black soil erosion in Northeast China. We divided the soil into large macroaggregates (>2 mm), small macroaggregates (0.25–2 mm), and microaggregates ( more...

A comprehensive understanding of soil salinity characteristics and the vertical and spatial distribution of particle sizes in lakes and wetlands within arid zones, as well as elucidating their interrelationship, is crucial for effective wetland soil salinization management. In this study, the typical salinized wetland, the Ebinur Lake wetland, was selected as the research object. A total of 50 sampling points were established along the edge of Ebinur Lake, resulting in the collection of 200 soil samples from depths of 0–60 cm. The particle size distribution (PSD) of the soil samples was obtained by laser particle sizer, and the fractal dimension of the soil structure was deduced by applying fractal theory. The soluble salt content (TSS) and salt ions content were measured by laboratory physicochemical experiments. Finally, Pearson correlation and other methods were used to explore the relationship between soil salinity and soil particle size. The results showed the following: (1) Soil salinization in the study area was severe, and the accumulation of surface salts was obvious, with a mean value of 46,410 mg/kg. The spatial distribution of TSS was predominantly influenced by Cl−, SO42−, Na+ + K+, Mg2+, and Ca2+. (2) Across various soil depths, silt and sand were the primary constituents, with soil fractal dimensions (Dsoil) ranging from 1.91 to 2.76, averaging 2.54, and a poor soil textural structure. The spatial distribution of Dsoil closely mirrored that of TSS. (3) According to the correlation analysis results, as TSS increased, Dsoil continued to rise, with an increasing content of clay, while the sand content decreased. Simultaneously, as the soil particles became finer, TSS and Dsoil also increased, suggesting that sandy loam to silty soils in the study area were more prone to salt accumulation. more...

The water delivery capacity of Karez is gradually declining, and it is possible that such a traditional water supply systems might be completely replaced by modern water conservancy projects. To determine whether these ancient water conservancy projects have a future, we conducted a study in a typical research area of Xinjiang Province, China. Using remote sensing technology, in situ surveying, and the analytic hierarchy process, we evaluated Karez in terms of water delivery capacity, water intake convenience, and capability to maintaining the ecological stability of the surrounding area. The derived results are as follows. (1) During 2005–2020, the length of 14 Karez systems in the study area decreased; however, the calculated water access convenience degree (C) indicated that Karez are more convenient for water intake compared with modern transmission channels, i.e., Ckarez = 0.68 and Cchannel = 0.51. (2) The mean annual runoff of the Karez system was 69.38 × 106 m3, similar to that of the modern water transmission channels in the area (73.49 × 106 m3). (3) Change in ecological sensitivity occurred mostly in regions where Karez systems have disappeared, with increase of 70.69 % and 14.51 % in high and medium sensitivity areas, respectively, and decline of 21.53 % and 9.74 % in low-sensitivity and non-sensitivity areas. Our research shows that Karez have considerable water delivery capacity, and that their existence is beneficial to maintaining the stability of the surrounding ecology. The Karez system can be considered a template for harmonious coexistence between humans and nature. more...

Carbon use efficiency (CUE) and water use efficiency (WUE) are key metrics for quantifying the coupling between terrestrial ecosystem carbon and water cycles. The impacts of intensifying climate change and human activities on carbon and water fluxes in Central Asian vegetation remain unclear. In this study, the CUE and WUE in Central Asia from 2001 to 2022 were accurately estimated with the help of the Google Earth Engine (GEE) data platform; the Theil–Sen median slope estimation combined with the Manna–Kendall significance test and partial derivative analysis were used to investigate the CUE and WUE trends and their responses to climate change and human activities. CUE and WUE show overall declining trends with significant spatial variability. Among meteorological factors, vapor pressure deficit and temperature show the strongest correlation with CUE, while precipitation and temperature are most correlated with WUE. Compared to human activities, climate change has a greater impact on CUE and WUE, mainly exerting a negative influence. Human activities are the main drivers in regions with developed agriculture, such as oases, farmlands, and areas near rivers and lakes. This study provides scientific references for the optimization of water and soil resources and the integrated regional environmental management in Central Asia. more...

Xinjiang is a representative dry area in China characterized by oasis agriculture. In recent decades, the amount of farmland has increased considerably. For the regional objectives of “carbon peaking and carbon neutrality”, it is essential to investigate the carbon effects induced by large-scale changes in farmland. This research integrates the PLUS and InVEST models to calculate the carbon effects resulting from the spatiotemporal changes in farmland distribution in Xinjiang. It quantitatively assesses the changes in land-use patterns and carbon storage under four scenarios for 2035—natural development (ND), economic development (ED), ecological protection (EP), and farmland protection (FP)—and explores the spatial agglomeration degree of the carbon effect of cultivated land area change. The analysis reveals the following: (1) From 1990 to 2020, the farmland area in Xinjiang showed a trend of first decreasing and then increasing, resulting in a total increase of 33,328.53 km2 over the 30-year period. The newly added farmland primarily came from grassland and unused land. (2) The terrestrial ecosystem carbon storage in Xinjiang showed a trend of decreasing first and then increasing, with an increase of 57.49 Tg in 30 years. The centroid of carbon storage was located in the northwestern part of the Bayingolin Mongol Autonomous Prefecture, showing an overall southwestward shift. Changes in farmland area contributed to a regional carbon storage increase of 45.03 Tg. The contribution of farmland to carbon storage increased by 3.42%. (3) In 2035, the carbon storage value of different scenarios will increase compared with 2020, and the carbon sink of cultivated land will be the maximum under the cultivated land protection scenario. (4) There is a strong spatial positive correlation between the changes in carbon storage caused by the change in cultivated land area in Xinjiang, and there are more hot spots than cold spots. The carbon storage changes under farmland transformation have the characteristics of “high-high” clustering and “low-low” clustering. Future territorial spatial planning in Xinjiang should comprehensively coordinate ecological protection and farmland conservation measures, improve regional carbon sink capacity, and achieve green and sustainable development. more...

Research on the carrying capacity of land resources and their outputs to population size will be able to better serve the ecological governance of food security. This paper analyzes the population carrying capacity level of southern Xinjiang by using the population carrying capacity model of land resources, and ANOVA analyzes the significance difference between the newly added arable land and the original arable land. At the same time, the demand of cultivated land development is discussed. The results showed that the sown area of grain crops in all the prefectures showed an overall increase from 2009 to 2019. The population carrying scale is more optimistic under subsistence and well-off conditions. From 2009 to 2019, cropland in Aksu region increased the most, followed by Kashgar region, with both regions exceeding 300,000 ha. ANOVA results show that the new arable land is comprehensively lower than the original arable land in terms of quality grade and agricultural output, and salinization and desertification are more serious than on the original arable land. At the same time, the subsistence type requires the least amount of arable land development while the affluent type requires the most. Therefore, we should adapt to local conditions and develop modern agriculture scientifically and reasonably. more...

Soil moisture (SM) is a critical parameter in Earth’s water cycle, significantly impacting hydrological, agricultural, and meteorological research fields. The challenge of estimating surface soil moisture from synthetic aperture radar (SAR) data is compounded by the influence of vegetation coverage. This study focuses on the Weigan River and Kuche River Delta Oasis in Xinjiang, employing high-resolution Sentinel-1 and Sentinel-2 images in conjunction with a modified Water Cloud Model (WCM) and the grayscale co-occurrence matrix (GLCM) for feature parameter extraction. A soil moisture inversion method based on stacked ensemble learning is proposed, which integrates random forest, CatBoost, and LightGBM. The findings underscore the feasibility of using multi-source remote sensing data for oasis moisture inversion in arid regions. However, soil moisture content estimates tend to be overestimated above 10% and underestimated below 5%. The CatBoost model achieved the highest accuracy (R2 = 0.827, RMSE = 0.014 g/g) using the top 16 feature parameter groups. Additionally, the R2 values for Stacking1 and Stacking2 models saw increases of 0.008 and 0.016, respectively. Thus, integrating multi-source remote sensing data with Stacking models offers valuable support and reference for large-scale estimation of surface soil moisture content in arid oasis areas. more...

Amidst the backdrop of global climate change, it is imperative to comprehend the intricate connections among surface water, vegetation, and climatic shifts within watersheds, especially in fragile, arid ecosystems. However, these relationships across various timescales remain unclear. We employed the Ensemble Empirical Mode Decomposition (EEMD) method to analyze the multifaceted dynamics of surface water and vegetation in the Bosten Lake Watershed across multiple temporal scales. This analysis has shed light on how these elements interact with climate change, revealing significant insights. From March to October, approximately 14.9–16.8% of the areas with permanent water were susceptible to receding and drying up. Both the annual and monthly values of Bosten Lake’s level and area exhibited a trend of initial decline followed by an increase, reaching their lowest point in 2013 (1,045.0 m and 906.6 km2, respectively). Approximately 7.7% of vegetated areas showed a significant increase in the Normalized Difference Vegetation Index (NDVI). NDVI volatility was observed in 23.4% of vegetated areas, primarily concentrated in the southern part of the study area and near Lake Bosten. Regarding the annual components (6 < T < 24 months), temperature, 3-month cumulative NDVI, and 3-month-leading precipitation exhibited the strongest correlation with changes in water level and surface area. For the interannual components (T≥ 24 months), NDVI, 3-month cumulative precipitation, and 3-month-leading temperature displayed the most robust correlation with alterations in water level and surface area. In both components, NDVI had a negative impact on Bosten Lake’s water level and surface area, while temperature and precipitation exerted positive effects. Through comparative analysis, this study reveals the importance of temporal periodicity in developing adaptive strategies for achieving Sustainable Development Goals in dryland watersheds. This study introduces a robust methodology for dissecting trends within scale components of lake level and surface area and links these trends to climate variations and NDVI changes across different temporal scales. The inherent correlations uncovered in this research can serve as valuable guidance for future investigations into surface water dynamics in arid regions. more...

Monitoring soil salinity with remote sensing is difficult, but knowing the link between saline soil surface spectra, soil water, and salt transport processes might help in modeling for soil salinity monitoring. In this study, we used an indoor soil column experiment, an unmanned aerial vehicle multispectral sensor camera, and a soil moisture sensor to study the water and salt transport process in the soil column under different water addition conditions and investigate the relationship between the soil water and salt transport process and the spectral reflectance of the image on the soil surface. The observation results of the soil column show that the soil water and salt transportation process conforms to the basic transportation law of “salt moves together with water, and when water evaporates, salt is retained in the soil weight”. The salt accumulation phenomenon increases the image spectral reflectance of the surface layer of the soil column, while soil temperature has no effect on the reflectance. As the water percolates down, water and salt accumulate at the bottom of the soil column. The salinity index decreases instantly after the addition of brine and then tends to increase slowly. The experimental results indicate that this work can capture the relationship between the water and salt transport process and remote sensing spectra, which can provide theoretical basis and reference for soil water salinity monitoring. more...

Soil salinization is a significant global threat to sustainable agricultural development, with soil salinity serving as a crucial indicator for evaluating soil salinization. Remote sensing technology enables large-scale inversion of soil salinity, facilitating the monitoring and assessment of soil salinization levels, thus supporting the prevention and management of soil salinization. This study employs multi-source remote sensing data, selecting 8 radar polarization combinations, 10 spectral indices, and 3 topographic factors to form a feature variable dataset. By applying a normalized weighted variable optimization method, highly important feature variables are identified. AdaBoost, LightGBM, and CatBoost machine learning methods are then used to develop soil salinity inversion models and evaluate their performance. The results indicate the following: (1) There is generally a strong correlation between radar polarization combinations and vegetation indices, and a very high correlation between various vegetation indices and the salinity index S3. (2) The top five feature variables, in order of importance, are Aspect, VH2, Normalized Difference Moisture Index (NDMI), VH, and Vegetation Moisture Index (VMI). (3) The method of normalized weighted importance scoring effectively screens important variables, reducing the number of input feature variables while enhancing the model’s inversion accuracy. (4) Among the three machine learning models, CatBoost performs best overall in soil salt content (SSC) prediction. Combined with the top five feature variables, CatBoost achieves the highest prediction accuracy (R2 = 0.831, RMSE = 2.653, MAE = 1.034) in the prediction phase. This study provides insights for the further development and application of methods for collaborative inversion of soil salinity using multi-source remote sensing data. more...

The validation of remotely sensed evapotranspiration (ET) products is important for the development of ET estimation models and the accuracy of the scientific application of the products. In this study, different ET products such as HiTLL, MOD16A2, ETMonitor, and SoGAE were compared using multi-source remote sensing data and ground-based data to evaluate their applicability in the Heihe River Basin (HRB) during 2010–2019. The results of the comparison with the site observations show that ETMonitor provides a more stable and reliable estimation of ET than the other three products. The ET exhibited significant variations over the decade, characterized by a general increase in rates across the HRB. These changes were markedly influenced by variations in land use and topographical features. Specifically, the analysis showed that farmland and forested areas had higher ET rates due to greater vegetation cover and moisture availability, while grasslands and water bodies demonstrated lower ET rates, reflecting their respective land cover characteristics. This study further explored the influence of various factors on ET, including land use changes, NDVI, temperature, and precipitation. It was found that changes in land use, such as increases in agricultural areas or reforestation efforts, directly influenced ET rates. Moreover, meteorological conditions such as temperature and precipitation patterns also played crucial roles, with warmer temperatures and higher precipitation correlating with increased ET. This study highlights the significant impact of land use and climatic factors on spatiotemporal variations in ET within the HRB, underscoring its importance for optimizing water resource management and land use planning in arid regions. more...

Salinization remains a major issue in soil degradation, for which biochar is a potential solution. In this meta-analysis, using 660 paired observations from 99 peer-reviewed articles, we evaluated biochar's effect on salt-affected soils and identified the initial soil properties, biochar properties and experimental factors influencing its efficacy. The results showed that the addition of biochar had a significant ameliorating effect on salt-affected soils. The soil electrical conductivity of saturated paste extract (ECe) was significantly reduced by 13.2%, and such effect was significant in severe salinization soil (rather than slight and moderate salinization). Meanwhile, the soil cation exchange capacity was significantly increased by 17.0%. However, the addition of biochar had no significant impact on soil pH. Model selection analyses further indicated that the level of initial salinity and the type of biochar feedstock were the most important factors regulating the response of soil ECe to biochar addition. In summary, while our study highlights the potential of biochar in ameliorating salt-affected soils, particularly in severely salinized soils, it also underscores the need for more comprehensive research in this field. Additional research is necessary to comprehensively address the significant heterogeneity of biochars, including their thorough characterization. In addition, more studies are required to explore the impact of biochar on both salt-tolerant and non-salt-tolerant plants in salt-affected soils. more...

Secondary salinization is a crucial constraint on agricultural progress in arid regions. The specific mulching irrigation technique not only exacerbates secondary salinization but also complicates field-scale soil salinity monitoring. UAV hyperspectral remote sensing offers a monitoring method that is high-precision, high-efficiency, and short-cycle. In this study, UAV hyperspectral images were used to derive one-dimensional, textural, and three-dimensional feature variables using Competitive adaptive reweighted sampling (CARS), Gray-Level Co-occurrence Matrix (GLCM), Boruta Feature Selection (Boruta), and Brightness-Color-Index (BCI) with Fractional-order differentiation (FOD) processing. Additionally, three modeling strategies were developed (Strategy 1 involves constructing the model solely with the 20 single-band variable inputs screened by the CARS algorithm. In Strategy 2, 25 texture features augment Strategy 1, resulting in 45 feature variables for model construction. Strategy 3, building upon Strategy 2, incorporates six triple-band indices, totaling 51 variables used in the model’s construction) and integrated with the Seagull Optimization Algorithm for Random Forest (SOA-RF) models to predict soil electrical conductivity (EC) and delineate spatial distribution. The results demonstrated that fractional order differentiation highlights spectral features in noisy spectra, and different orders of differentiation reveal different hidden information. The correlation between soil EC and spectra varies with the order. 1.9th order differentiation is proved to be the best order for constructing one-dimensional indices; although the addition of texture features slightly improves the accuracy of the model, the integration of the three-waveband indices significantly improves the accuracy of the estimation, with an R2 of 0.9476. In contrast to the conventional RF model, the SOA-RF algorithm optimizes its parameters thereby significantly improving the accuracy and model stability. The optimal soil salinity prediction model proposed in this study can accurately, non-invasively and rapidly identify excessive salt accumulation in drip irrigation under membrane. It is of great significance to improve the growing conditions of cotton, increase the cotton yield, and promote the sustainable development of Xinjiang’s agricultural economy, and also provides a reference for the prevention and control of regional soil salinization. more...

To break the black box feature of XGBoost model and enhance its persuasiveness, an interpretable flight delay prediction model based on SHAP was proposed. Firstly, based on the fusion of flight history data and weather data, outliers were processed and features were selected by recursive feature elimination method. Secondly, a flight delay duration prediction model was constructed, and genetic algorithm was used for parameter optimization, then it was compared with commonly used models at present. Finally, based on the prediction of flight delay duration and the SHAP model, the importance of features was analyzed from two perspectives: overall features and the interrelationships between the features. The experimental results show that the XGBoost model optimized by genetic algorithm has higher prediction, with a decrease of 8.94% in MAE, 19.85% in RMSE, and 6.15% in MAPE, with higher accuracy compared to other models. The SHAP model can break the black box characteristics of the XGBoost model and enhance its interpretability, which provides some support for reducing flight delay duration. more...

Abstract Ammonia-oxidizing archaea and bacteria (AOA and AOB, respectively) are important intermediate links in the nitrogen cycle. Apart from the AOA and AOB communities in soil, we further investigated co-occurrence patterns and microbial assembly processes subjected to inorganic and organic fertilizer treatments for over 35 years. The amoA copy numbers and AOA and AOB communities were found to be similar for the CK and organic fertilizer treatments. Inorganic fertilizers decreased the AOA gene copy numbers by 0.75–0.93-fold and increased the AOB gene copy numbers by 1.89–3.32-fold compared to those of the CK treatment. The inorganic fertilizer increased Nitrososphaera and Nitrosospira. The predominant bacteria in organic fertilizer was Nitrosomonadales. Furthermore, the inorganic fertilizer increased the complexity of the co-occurrence pattern of AOA and decreased the complexity pattern of AOB comparing with organic fertilizer. Different fertilizer had an insignificant effect on the microbial assembly process of AOA. However, great difference exists in the AOB community assembly process: deterministic process dominated in organic fertilizer treatment and stochastic processes dominated in inorganic fertilizer treatment, respectively. Redundancy analysis indicated that the soil pH, NO3 −N, and available phosphorus contents were the main factors affecting the changes in the AOA and AOB communities. Overall, this findings expanded our knowledge concerning AOA and AOB, and ammonia‐oxidizing microorganisms were more disturbed by inorganic fertilizers than organic fertilizers. more...

As a typical geographic landscape unit in the arid zone of northwest China, the distribution of the thermal environment in the substratum of the desert-oasis is of great significance to the monitoring of the ecological environment and the quality of human habitat in the region. The purpose of this research is to reveal the spatial–temporal evolution pattern of the thermal environment of the desert–oasis in the Turpan–Hami region from 2005 to 2020 and its trend changes, and to investigate the relationship between natural and human factors and the thermal environment and to conduct a long time series analysis. Firstly, the accuracy of MODIS land surface temperature (LST) data combined with site data was verified. Secondly, the mean-standard deviation method is used to identify desert heat island and oasis cold island zones. Again, the spatial–temporal distribution and change trends of thermal environment are explored by using standard deviation ellipse and spatial autocorrelation combined with land use/land cover (LULC) types. Finally, based on the multi-source remote sensing data, the natural factors and human factors are selected to explore their correlation with the thermal environment using Pearson correlation analysis. The results show that (1) the desert heat island zones are distributed in the desert areas on the periphery of urban built-up areas in Gaochang District, Shanshan County and Yizhou District of Hami Region. The oasis cold island zones are concentrated in the urban built-up areas of Gaochang District and Yizhou District, mainly because the vegetation coverage of urban built-up areas is higher than that of the peripheral desert areas. (2) The spatial development characteristics of the extremely high temperature (EHT) zone and the high temperature (HT)zone from 2005 to 2020 are “southeast-northeast-northwest” and “southeast-northwest” respectively, and the area of construction land 16a increased by 0.31%. This indicates that the spatial evolution of the thermal environment is closely related to the LULC and the degree of urbanization development. (3) From a four–period image with P 2.58, the thermal environment displays a high positive spatial correlation with Moran's I values of 0.45, 0.54, 0.47, and 0.45. (4) Temperature (Tem), downward longwave radiation (LWdown), and nighttime light intensity (NPP) all exhibited positive correlations with the LST and are significant in the desert region (p more...

Accurate estimation of surface evapotranspiration (ET) in the Heihe River Basin using remote sensing data is crucial for understanding water dynamics in arid regions. In this paper, by coupling physical constraints and machine learning for hybrid modeling, we develop a hybrid model based on surface conductance optimization. A hybrid modeling algorithm, two physical process-based ET algorithms (Penman–Monteith-based and Priestley–Taylor-based ET algorithms), and three pure machine learning algorithms (Random Forest, Extreme Gradient Boosting, and K Nearest Neighbors) are comparatively analyzed for estimating the ET. The results showed that, in general, the machine learning model optimized by parameters was able to better predict the surface conductance of the hybrid model. Driver analyses showed that radiation, normalized difference vegetation index (NDVI), and air temperature had high correlations with ET. The hybrid model had a better prediction performance for ET than the other five models, and it improved the R2 of the two physical process-based algorithms to 0.9, reduced the root mean square error (RMSE) to 0.5 mm/day, reduced the BIAS to 0.2 mm/day, and improved the Kling–Gupta efficiency (KGE) to 0.9. The hybrid model outperformed the others across different time scales, displaying lower BIAS, RMSE, and higher KGE. Spatially, its ET patterns aligned with regional vegetation changes, with superior accuracy in annual ET estimation compared to the other models. Comparison with other ET products shows that the estimation results based on the hybrid model have better performance. This approach not only improves the accuracy of ET estimation but also improves the understanding of the physical mechanism of ET estimation by pure machine learning models. This study can provide important support for understanding ET and hydrological processes under different climatic and biotic vegetation in other arid and semi-arid regions. more...

Soil moisture content is an important measure of soil health, and high-precision soil moisture trend analysis is essential for understanding regional ecological quality in the context of climate change, flood monitoring, and water cycle processes. However, in the arid regions of Central Asia, where data are severely lacking, obtaining high-spatial-resolution, continuous soil moisture data is difficult due to the scarcity of stations. Moreover, because soil moisture is easily affected by evaporation time, surface morphology, and anthropogenic factors, mature theoretical models or empirical or semiempirical models to measure soil moisture are also lacking. To investigate the distribution and trend of soil moisture in the Ebinur Lake water, in this study, microwave remote sensing and visible remote sensing data were selected as inputs, and the Global Land Data Assimilation System (GLDAS-2.2) data products were downscaled using the GTWR model, which increased the spatial scale from 27,830 m × 27,830 m to 30 m × 30 m. The phenomena involved in the soil moisture change cycle, spatial distribution, temporal variation, and internal randomness distance were analyzed in the study area through wavelet analysis, Theil–Sen trend analysis, the Mann–Kendall (MK) test, and a variogram. This study obtained high-resolution continuous soil moisture data in the arid and data-scarce region in Central Asia, thus broadening the field of multisource remote sensing analysis and providing a theoretical basis for the construction of precision agriculture in northwest China. more...

Accurate and reliable precipitation data are important for analyzing regional precipitation distribution, water resource management, and ecological environment construction. Due to the scarcity of meteorological stations in the Turpan–Hami region, precipitation observation conditions are limited, and it is difficult to obtain precipitation data. Firstly, the applicability of TRMM 3B43v7, GPM_3IMERGM 06, and CMORPH CDR satellite precipitation data for the Turpan–Hami Region was evaluated, and the products with better applicability were selected. Next, the Extreme Gradient Boosting Algorithm (XGBoost) and the Shapley Additive Explanations for Machine Learning (SHAP) model were combined to carry out a feature importance analysis on the climate factors affecting precipitation (mean temperature, actual evapotranspiration, wind speed, cloud cover), from which climate factors with a greater influence on precipitation were selected. Combined with climate factors, normalized difference vegetation index (NDVI), slope, aspect, and elevation as explanatory variables, a Multi-Scale Geographically Weighted Regression (MGWR) model was constructed to obtain the monthly precipitation data of 1 km spatial resolution in the Turpan–Hami area from 2001 to 2020. Finally, the spatiotemporal distribution characteristics and changing trend of precipitation in the Turpan–Hami region from 2001 to 2020 were analyzed. The results show that (1) GPM_3IMERGM 06 satellite precipitation data exhibits good applicability in the Turpan–Hami region. (2) The precision verification of the downscaling results from a monthly scale and an annual scale shows that the accuracy and spatial resolution of the data are improved after downscaling. (3) From 2001 to 2020, the precipitation in the Turpan–Hami region showed an insignificantly increasing trend. more...

Land degradation due to soil erosion is a major problem in mountainous areas. It is crucially important to understand the law of soil erosion under different land-use patterns with rainfall variability. We studied Qingshuihe Watershed in the Chongli district of the Zhangjiakou area. Four runoff plots, including caragana, corn, apricot trees, and barren grassland, were designed on the typical slopes of Xigou and Donggou locations. The 270 natural rainfall events observed from 2014 to 2016 were used to form a rainfall gradient. The relationship between runoff and sediment yield was analyzed. Results showed that the monthly rainfall of the slope runoff plot in the Chongli mountain area presented the trend of concentrated rainfall in summer, mainly from June to September, accounting for 82.4% of the total rainfall in 2014–2016, which was far higher than that in other months. Starting from April to May every year, the rainfall increased with time, then from July to September, the rainfall decreased gradually, but it was still at the high level of the whole year. Among the four ecosystems, the caragana-field has the best effect on reducing the kinetic energy of rainfall and runoff, which can effectively reduce the runoff and sediment yield of the slope and reduce the intensity of soil erosion. In terms of the total amount of runoff and sediment, the runoff and sediment yield of the caragana-field reduced by 74%–87% and 64%–86% compared with that of the grassland. Comparing different land-use types, the caragana plantation would be conducive to conserving soil and water resources. more...

Climate change has caused inland wetlands shrinkage and exacerbated problems, such as sustainable development and ecological security, for years. These issues are mainly pronounced in the inland arid area. The ecological environment’s deterioration is especially severe in the drylands of the interior. However, dryland wetland changes and their response to climate are poorly understood. This study uses the K-means algorithm in Google Earth Engine (GEE) to classify two typical dryland wetlands (Ebinur and Bosten Lakes) for rapidly and accurately detecting dryland wetland changes. Moreover, it explores the long-term spatial–temporal variation in wetland distribution. In addition, it investigates the response of various lakes to climate change in northern and southern Xinjiang using wavelet analysis. The study’s results showed that K-means clustering in the GEE platform has a high classification accuracy (Kappa > 0.8) in wetland classification, making it a feasible approach. The terminal lake wetland types, represented by the Ebinur Lake, changed significantly between 2001 and 2021. In contrast, the inflow-outflow lake wetland types, represented by the Bosten Lake, perform more consistently. Significant spatial–temporal variation is observed at Ebinur Lake, with the lake gradually shrinking and transforming into a marsh, where the largest marsh proportion degrades into non-wetland during the year. Bosten Lake experienced frequent conversions between marsh and non-wetland throughout the year. Furthermore, the responses of various dryland lakes to climate change are consistent, and a low precedes precipitation and follows evapotranspiration. However, their sensitivity to climate response varies, with the terminal lake being most affected by climate change. Mastering the dynamic changes and climate response of dryland wetlands achieves the sustainable development goals of drylands, including carbon neutrality and peak carbon dioxide emissions. more...

With the development of human society, the balance between the minimum ecological instream flow requirement (MEIFR), which is an essential part of the ecological water demand in arid areas, and anthropogenic water depletion has received increasing attention. However, due to the lack of hydrological station data and river information on arid basins, previous researchers usually considered only the individual ecological water demand of rivers, lakes, or oases. To address this issue, a new method that combines river hydraulic parameters and the wet circumference obtained by an unmanned aerial vehicle (UAV) and remote sensing hydrological station (RSHS) technologies was applied to obtain the MEIFR and, then, systematically and quantitatively explore the balance from the perspective of the entire basin of Aiding Lake from 1990 to 2022, which is the lowest point of Chinese terrestrial territory. The results showed the following: (1) since 1990, the discharge of the seven rivers in the study area increased by 1–6%, and the MEIFR of these rivers increased by 15–100%; both quantities decreased by 3–5% from the upper to the lower reaches of the basin; (2) the surface area and water level of Aiding Lake decreased by 5% and 14%, respectively, but the MEIFR first decreased by 25% from 1990 to 2013 and, then, increased by 66.7% from 2013 to 2022; and (3) from 2011 to 2022, the MEIFR and anthropogenic water depletion exhibited a balance. Against the background of climate change, this research revealed that the MEIFR of the rivers in the Aiding Lake Basin have shown an upward trend over the past 30 years and quantitatively determined the above balance relationship and the period of its occurrence. This study supplied a method that could provide guidance for water resource management by decision-makers at a global level, thus helping achieve the sustainable development goals (SDGs). more...

Ecosystem water use efficiency (WUE) and ecosystem photosynthetic efficiency (EPE) are key indicators in studies of the carbon–water cycle in terrestrial ecosystems. Analyses of WUE and EPE can enhance our understanding of the relationship between ecosystem light use efficiency and WUE. Although several studies of individual indexes (i.e., either WUE or EPE) have been conducted, analyses of variation in both WUE and EPE, as well as their relationships, have rarely been conducted. Here, we analyzed spatial and temporal variation in WUE and EPE in Central Asia. Specifically, time trend analysis was conducted to characterize temporal and spatial changes in WUE and EPE in Central Asia from 2001 to 2020 at different altitudes and latitudes. Pearson correlation analysis was used to characterize the effects of precipitation and temperature on WUE and EPE. WUE decreased and EPE increased in Central Asia over the 20-year study period; this might have been due to interannual variations in precipitation and temperature. WUE was highest in August, and EPE was highest in June and July. Substantial spatial heterogeneity in WUE and EPE was observed; WUE was highly variable in Central Asia as well as in western and southern Central Asia. Major changes in EPE were observed in northern, eastern, and southern Central Asia. We also found that both WUE and EPE decreased with the increase in altitude. WUE was positively correlated with temperature and negatively correlated with precipitation, whereas EPE was positively correlated with both temperature and precipitation. The increase in photosynthetic efficiency might be one of the main factors contributing to increases in ecosystem productivity in arid environments. The temporal and spatial variation in WUE and EPE observed in our study will aid ecosystem research, providing a reliable theoretical basis for ecosystem research in areas with scarce large-scale data, integrated water resources management, and ecosystem restoration efforts. Our findings also enhance our understanding of the terrestrial carbon–water cycle and have implications for predicting ecosystem responses to climate change. The results of this study provide insights that will aid studies of the terrestrial carbon–water cycle under the background of climate change. It is of great significance to further study the carbon water cycle in the future. more...

Abstract Extreme precipitation events exhibit an increasing trend for both the frequency and magnitude on global and regional scales and it has already proven the impact of man-made global warming on the extreme precipitation amplification. Based on the observed datasets and global climate model (GCM) output, this study has evaluated the impact from anthropogenic forcing on the trend and temporal non-uniformity (i.e. increase in unevenness or disparity) of the precipitation amounts (PRCPTOT), extremes (R95p and RX5day) and intensity (SDII) in Central Asia (CA) from 1961 to 2005. Results indicate that radiative forcing changes, mainly driven by human activities, have significantly augmented the extreme precipitation indices in CA. The median trend with the influence of anthropogenic activities for the PRCPTOT, SDII, R95p and RX5day amounted to 2.19 mm/decade, 0.019 mm/decade, 1.39 mm/decade and 0.21 mm/decade during the study period, respectively. A statistically insignificant decrease in non-uniformity was noticed for the PRCPTOT, SDII and RX5day in Central CA (CCA) and Western CA (WCA), while Eastern CA (ECA) was the only region with a statistically significant increase in non-uniformity of the PRCPTOT, SDII, R95p and RX5day by 4.22%, 3.98%, 3.73% and 3.97%, respectively from 1961 to 2005 due to anthropogenic forcing. These results reflect the difference in various regions regarding the impact of anthropogenic forcing on the non-uniformity of extreme precipitation events in CA, which might help to fully understand the role of anthropogenic forcing in the changes of the precipitation extremes in CA and contribute to the development of water resource management strategies. more...

Surface water quality is an important factor affecting the ecological environment and human living environment. The monitoring of surface water quality by remote sensing monitoring technology can provide important research significance for water resources protection and water quality evaluation. Finding the optimal spectral index sensitive to water quality for remote sensing monitoring of water quality is extremely important for surface water quality analysis and treatment in the Ebinur Lake Basin in arid areas. This study used Sentinel-2MSI data at 10 m resolution to quickly monitor the water quality of the watershed. Through laboratory experiments and measurement data from the Ebinur Lake Basin, 22 water quality parameters (WQPs) were obtained. Through Z-score and redundancy analysis, 9 WQPs with significant contributions were extracted. Based on the remote sensing spectral band, four water indexes (NDWI, NWI, EWI, AWEI-nsh) and 2D modeling spectral index (DI, RI, NDI), the correlation analysis between WQPs and two kinds of spectral band indexes is carried out, and it is concluded that the overall correlation between WQP and 2D spectral modeling is more relevant. This paper calculates the evaluation and models the 2D spectrum of the Water Quality Index (WQI). The WQI is predicted and modeled through four machine learning algorithms (RF, SVM, PLSR, PLSR-SVM).The results show that the inversion effect of the two-dimensional spectral modeling index on water quality parameters (WQPs) is superior to that of the water index, and the correlation coefficient of the DI (R12-R1) SWIR-2 and BLUE band interpolation index reaches 0.787. On this basis, three kinds of two-dimensional spectral modeling indexes are used to inversely synthesize the WQI, and the correlation coefficient of the ratio index of the RI (R11/R8) SWIR-1 and near-infrared (NIR) bands is preferably 0.69. In the WQI prediction, the partial least squares regression support vector machine (PLSR-SVM) model in machine learning algorithms has good modeling and prediction effects (R2c = 0.873, R2v = 0.87), which can provide a good basis. The research results provide references for remote monitoring of surface water in arid areas, and provide a basis for water quality prediction and safety evaluation. HIGHLIGHTS Inversion of water quality in the Ebinur Lake Basin by Sentinel-2 MSI data.; Analysis of the contribution rate of different water quality parameters in water by Z-score and PCA.; Comparison of classical water quality index, correlation between spectral modeling and water quality parameters.; Modeling and predicting water quality index (WQI) using machine learning and linear correlation methods.; more...

Soil salinization is one of the most important causes of land degradation and desertification, especially in arid and semi-arid areas. The dynamic monitoring of soil salinization is of great significance to land management, agricultural activities, water quality, and sustainable development. The remote sensing images taken by the synthetic aperture radar (SAR) Sentinel-1 and the multispectral satellite Sentinel-2 with high resolution and short revisit period have the potential to monitor the spatial distribution of soil attribute information on a large area; however, there are limited studies on the combination of Sentinel-1 and Sentinel-2 for digital mapping of soil salinization. Therefore, in this study, we used topography indices derived from digital elevation model (DEM), SAR indices generated by Sentinel-1, and vegetation indices generated by Sentinel-2 to map soil salinization in the Ogan-Kuqa River Oasis located in the central and northern Tarim Basin in Xinjiang of China, and evaluated the potential of multi-source sensors to predict soil salinity. Using the soil electrical conductivity (EC) values of 70 ground sampling sites as the target variable and the optimal environmental factors as the predictive variable, we constructed three soil salinity inversion models based on classification and regression tree (CART), random forest (RF), and extreme gradient boosting (XGBoost). Then, we evaluated the prediction ability of different models through the five-fold cross validation. The prediction accuracy of XGBoost model is better than those of CART and RF, and soil salinity predicted by the three models has similar spatial distribution characteristics. Compared with the combination of topography indices and vegetation indices, the addition of SAR indices effectively improves the prediction accuracy of the model. In general, the method of soil salinity prediction based on multi-source sensor combination is better than that based on a single sensor. In addition, SAR indices, vegetation indices, and topography indices are all effective variables for soil salinity prediction. Weighted Difference Vegetation Index (WDVI) is designated as the most important variable in these variables, followed by DEM. The results showed that the high-resolution radar Sentinel-1 and multispectral Sentinel-2 have the potential to develop soil salinity prediction model. more...

Water scarcity has emerged as a major impediment to the long-term development of inland arid region basins. Increased human activity has produced land degradation in arid areas and water stress in recent years. The objective of this research was to expose patterns in land cover changes in inland arid basin and the mechanisms driving them, as well as to optimize the socioeconomic and ecological water consumption structure of water resources. Therefore, this research used Google Earth Engine to map land cover year by year from 2000 to 2020, simulated future land cover changes and driving force analysis using a Patch-generating land use simulation model, and finally established the relationship between water consumption of different systems and different land cover types using linear equations, and scenario simulation method were used to estimates the ecological and agricultural water consumption in 2035. The results showed (1) Over the previous 20 years, there has been an increase in the amount of saline, agricultural land, and natural vegetation (grassland, scrub, and forest), as well as a considerable drop around permanent glaciers and snow. (2) Under the Markov-2035 scenario, saline land decreases to 32.92 km2, natural vegetation decreases to 381.89 km2, arable land shrinks to 135.69 km2, and the permanent glacier shrinks to 30.03 km2. Ecological water consumption would be 0.127 × 108 m3, while agricultural water consumption would be 0.394 × 108 m3. (3) Elevation influenced the variety of all land cover types. Saline land was more sensitive to temperature, railroad proximity, and pH; agricultural land was more sensitive to population density and gross regional product; and natural vegetation was more sensitive to soil organic matter, railroad proximity, and temperature. more...

Soil salinization has hampered the achievement of sustainable development goals (SDGs) in many countries worldwide. Several countries have recently launched hyperspectral remote sensing satellites, opening new avenues for accurate soil-salinity monitoring. Among them, Gaofen-5 (GF-5) from China has a high comprehensive performance, including a spectral resolution of 5 nm, 330 bands, and signal-to-noise ratio of 700. However, the potential of GF-5 for estimating soil salinity is not well understood. In this study, we proposed a strategy that includes bootstrap methods, fractional order derivative (FOD) techniques and decision-level fusion models to exploit the soil salinity diagnostic information and reduce estimation uncertainty in the Ebinur Lake oasis in northwestern China. The results showed that the GF-5 data were suitable for assessing soil salinity. The FOD technique enhanced the correlation between soil salinity and spectra, identified more diagnostic bands, improved the accuracy of soil salinity estimation, and reduced model uncertainty. The low-order FOD outperformed the high-order FOD. The spectra processed by the 0.9 order derivative were the most correlated with soil salinity (r = −0.76). The model driven by the 0.8 order derivative produced the optimal estimated model (R2 = 0.95, root mean square error (RMSE) = 3.20 dS m−1 and a ratio of performance to interquartile distance (RPIQ) = 5.96). The model driven by the 0.8 order derivative had less uncertainty than the models based on the original and integer-order derivative (first- and second- derivatives) spectra. This study provides a reference for estimating soil salinity from GF-5 data using the proposed framework with low uncertainty and high accuracy. GF-5 data have great potential for assessing environmental problems and facilitating further SDGs. more...

Accurate assessment of the spatial distribution and severity of soil salinization has long plagued local governments and researchers in the arid parts of Xinjiang Uygur Autonomous Region (XJUAR). The emergence of machine learning has brought hope to this research field, such as Random Forest (RF) and Stochastic Gradient Treeboost (SGT),however, which are few applications to the quantitative assessment of soil salinization. Therefore, in order to evaluate the accuracy level of the two algorithms for predicting soil salinity, twenty-seven environmental subsets were designed. Each data set is calculated using both RF and SGT to produce an optimal set of variables. The simulation results from 70.37% (19/27) of the subsets showed that the predicted value of soil salinity from SGT is closer to the observed value than is that from RF. The statistics of all datasets showed that the average values of R2 value for RF and SGT were 0.38 and 0.40, the average Root Mean Squared Error (RMSE) value were 28.59 and 27.46, and the Ratio of Prediction to Deviation (RPD) averages were 1.20 and 1.24, respectively. The important dominant factor were topographic variables with coarse resolution, temperature and vegetation indices, land use and landform. more...

Abstract The open and shared nature of the Automatic Dependent Surveillance Broadcast (ADS-B) protocol makes its messages extremely vulnerable to various security threats, such as jamming, modification, and injection. This paper proposes a long short-term memory (LSTM)-based ADS-B spoofing attack detection method from the perspective of data. First, the message sequence is preprocessed in the form of a sliding window, and then, an LSTM network is used to perform prediction training on the windows. Finally, the residual set of predicted values and true values is calculated to set a threshold. As a result, we can detect a spoofing attack and further identify which feature was attacked. Experiments show that this method can effectively detect 10 different kinds of simulated manipulated ADS-B messages without further increasing the complexity of airborne applications. Therefore, the method can respond well to the security threats suffered by the ADS-B system. more...

Exploring the future trends of land use/land cover (LULC) changes is significant for the sustainable development of a region. The simulation and prediction of LULC in a large-scale basin in an arid zone can help the future land management planning and rational allocation of resources in this ecologically fragile region. Using the whole Ili-Balkhash Basin as the study area, the patch-generating land use simulation (PLUS) model and a combination of PLUS and Markov predictions (PLUS–Markov) were used to simulate and predict land use in 2020 based on the assessment of the accuracy of LULC classification in the global dataset. The accuracy of simulations and predictions using the model were measured for LULC data covering different time periods. Model settings with better simulation results were selected for simulating and predicting possible future land use conditions in the basin. The future predictions for 2025 and 2030, which are based on historical land change characteristics, indicate that the overall future spatial pattern of LULC in the basin remains relatively stable in general without the influence of other external factors. Over the time scale of the future five years, the expansion of croplands and barren areas in the basin primarily stems from the loss of grasslands. Approximately 48% of the converted grassland areas are transformed into croplands, while around 40% are converted into barren areas. In the longer time scale of the future decade, the conversion of grasslands to croplands in the basin is also evident. However, the expansion phenomenon of urban and built-up lands at the expense of croplands is more significant, with approximately 774.2 km2 of croplands developing into urban and built-up lands. This work provides an effective new approach for simulating and predicting LULC in data-deficient basins at a large scale in arid regions, thereby establishing a foundation for future research on the impact of human activities on basin hydrology and related studies. more...

Climate change forecasts indicate that the frequency and intensity of extreme climate events will increase in the future; these changes will have important effects on ecosystem stability and function. An important arid region of the world, Central Asia has ecosystems that are extremely vulnerable to extreme weather events. However, few studies have investigated the resistance and resilience of this region’s ecosystems to extreme weather events. In this study, first, the extreme drought/wet threshold was calculated based on the 113-year (1901–2013) standardized precipitation–evapotranspiration index (SPEI); second, moderate resolution imaging spectroradiometer (MODIS) remote sensing data were applied to calculate ecosystem water use efficiency (WUE) and quantify ecosystem resistance and resilience after different extreme climate events; and finally, differences in the changes of various ecosystem types before and after climate events were assessed. The results showed the following: (1) The average SPEI was 0.073, and the thresholds of extreme wetness and drought were 0.91 and −0.67, respectively. Central Asia experienced extreme wet periods in 2002 and 2003 and a drought period in 2008. (2) Suitable wetness levels can increase the resistance of an ecosystem; however, continuous wetness reduces ecosystem resistance, as does drought. Wet areas had strong resilience after wet events, and arid areas had strong resilience after drought events. (3) During both wet and drought years, the transition between shrubland and grassland caused changes in ecosystem resistance and resilience. These findings are important for understanding the impact of future climate change on ecosystem stability. more...

At present, forest and fruit resource surveys are mainly based on ground surveys, and the information technology of the characteristic forest and fruit industries is evidently lagging. The automatic extraction of fruit tree information from massive remote sensing data is critical for the healthy development of the forest and fruit industries. However, the complex spatial information and weak spectral information contained in high-resolution images make it difficult to classify fruit trees. In recent years, fully convolutional neural networks (FCNs) have been shown to perform well in the semantic segmentation of remote sensing images because of their end-to-end network structures. In this paper, an end-to-end network model, Multi-Unet, was constructed. As an improved version of the U-Net network structure, this structure adopted multiscale convolution kernels to learn spatial semantic information under different receptive fields. In addition, the “spatial-channel” attention guidance module was introduced to fuse low-level and high-level features to reduce unnecessary semantic features and refine the classification results. The proposed model was tested in a characteristic high-resolution pear tree dataset constructed through field annotation work. The results show that Multi-Unet was the best performer among all models, with classification accuracy, recall, F1, and kappa coefficient of 88.95%, 89.57%, 89.26%, and 88.74%, respectively. This study provides important practical significance for the sustainable development of the characteristic forest fruit industry. more...

Ecological challenges resulting from soil salinization in the Tarim River Basin (TRB), exacerbated by climate change and human activities, have emphasized the need for a quick and accurate assessment of regional ecological environmental quality (EEQ) and driving mechanisms. To address this issue, this study has developed a remote-sensing ecological index with salinity adaptability (RSEISI) for EEQ assessment in the Tarim River Basin by integrating the comprehensive salinity index (CSI) into the remote-sensing ecological index (RSEI). The RSEISI enhances the sensitivity of soil salinity and characterizes the surface features of arid regions, thus expanding the applicability. Then, we used time-series analysis methods and a geodetector to quantify the spatial temporal trends and driving factors of EEQ in the TRB from 2000 to 2022. The results show that the RSEISI with salinity adaptation effectively monitors the EEQ of the TRB. The EEQ of the TRB displayed the situation of oasis expansion, desert deterioration, and glacier melting, and the multiyear average EEQ grades were dominated by medium and poor grades in desert and saline areas, while medium, good, and excellent grades were concentrated in oasis and mountainous areas. Looking at the trend of change in conjunction with land-use types, the EEQ of the TRB showed a mild degradation trend mainly in unused land, followed by a mild improvement trend in cropland and grassland. The Hurst index indicated that the EEQ of most areas of the TRB will improve in the future. Soil type, land use, precipitation, and temperature were considered to be key factors affecting the EEQ across the TRB, and changes in the EEQ were found to be the interaction of multiple factors. This study may provide innovative concepts and methodologies, scientific and technological support for ecological management, and green development models in the northwest arid zone. more...

Detecting changes in urban areas presents many challenges, including complex features, fast-changing rates, and human-induced interference. At present, most of the research on change detection has focused on traditional binary change detection (BCD), which becomes increasingly unsuitable for the diverse urban change detection tasks as cities grow. Previous change detection networks often rely on convolutional operations, which struggle to capture global contextual information and underutilize category semantic information. In this paper, we propose SIGNet, a Siamese graph convolutional network, to solve the above problems and improve the accuracy of urban multi-class change detection (MCD) tasks. After maximizing the fusion of change differences at different scales using joint pyramidal upsampling (JPU), SIGNet uses a graph convolution-based graph reasoning (GR) method to construct static connections of urban features in space and a graph cross-attention method to couple the dynamic connections of different types of features during the change process. Experimental results show that SIGNet achieves state-of-the-art accuracy on different MCD datasets when capturing contextual relationships between different regions and semantic correlations between different categories. There are currently few pixel-level datasets in the MCD domain. We introduce a new well-labeled dataset, CNAM-CD, which is a large MCD dataset containing 2508 pairs of high-resolution images. more...

Surface flow (SF) and subsurface flow (SSF) are important hydrological processes occurring on slopes, and are driven by two main factors: rainfall intensity and slope gradient. To explore nitrogen (N) migration and loss from sloping farmland in the Miyun Reservoir, the characteristics of total nitrogen (TN) migration and loss via SF and SSF under different rainfall intensities (30, 40, 50, 60, 70, and 80 mm/h) and slope gradients (5°, 10°, and 15°) were studied using indoor stimulated rainfall tests and mathematical models. Nitrogen loss via SF and SSF was found to increase exponentially and linearly with time, respectively, with SSF showing 14–78 times higher loss than SF. Under different rainfall intensities, SSF generally had larger TN loss loading than SF, thereby indicating that SSF was the main route for TN loss. However, the TN loss loading proportion via SF increasing from 14.03% to 35.82% with increasing rainfall intensity is noteworthy. Furthermore, compared with the measurement data, the precision evaluation index Nash-Suttcliffe efficient (NSE) and the determination coefficient (R2) of the effective mixing depth model in the numerical simulation of TN loss through SF in the sloping farmland in the Miyun Reservoir were 0.74 and 0.831, respectively, whereas those of the convection-dispersion equation for SSF were 0.81 and 0.811, respectively, thus indicating good simulation results. Therefore, this paper provides a reference for studying the mechanism of N migration and loss in sloping farmland in the Miyun Reservoir. more...

The accurate inversion of actual evapotranspiration (ETa) at a regional scale is crucial for understanding water circulation, climate change, and drought monitoring. In this study, we produced a 1 km monthly ETa dataset for Turpan and Hami, two typical arid cities in northwest China, using multi-source remote sensing data, reanalysis information, and the ETMonitor model from 1980 to 2021. We analyzed the spatiotemporal variation of ETa using various statistical approaches and discussed the impact of climate and land use and cover changes (LUCC) on ETa. The results show the following: (1) the estimation results correlate well with ETa products on monthly scales (coefficient of determination (R2) > 0.85, root mean square error (RMSE) < 15 mm/month) with high reliability. (2) The ETa values were spatially distributed similarly to precipitation and LUCC, with the multi-year (1980–2021) average of 66.31 mm and a slightly fluctuating downward trend (−0.19 mm/a). (3) During the 42-year period, 63.16% of the study area exhibited an insignificant decrease in ETa, while 86.85% experienced pronounced fluctuations (coefficient of variation (CV) > 0.20), and 78.83% will show an upward trend in the future. (4) ETa was significantly positively correlated with precipitation (94.17%) and insignificantly positively correlated with temperature (55.81%). The impact of human activities showed an insignificant decreasing trend (85.41%). Additionally, the intensity of ETa varied considerably among land types, with the largest for cropland (424.12 mm/a). The results of the study have implications for promoting the rational allocation of regional water resources and improving water use efficiency in arid zones. more...

PM2.5, which refers to fine particles with an equivalent aerodynamic diameter of less than or equal to 2.5 µm, can not only affect air quality but also endanger public health. Nevertheless, the spatial distribution of PM2.5 is not well understood in data-poor regions where monitoring stations are scarce. Therefore, we constructed a random forest (RF) model and a bagging algorithm model based on ground-monitored PM2.5 data, aerosol optical depth (AOD) and meteorological data, and auxiliary geographical variables to accurately estimate the spatial distribution of PM2.5 concentrations in Xinjiang during 2015–2020 at a resolution of 1 km. Through 10-fold cross-validation (CV), the RF model and bagging algorithm model were verified and compared. The results showed the following: (1) The RF model achieved better model performance and thus can be used to estimate the PM2.5 concentration at a relatively high resolution. (2) The PM2.5 concentrations were high in southern Xinjiang and low in northern Xinjiang. The high values were concentrated mainly in the Tarim Basin, while most areas of northern Xinjiang maintained low PM2.5 levels year-round. (3) The PM2.5 values in Xinjiang showed significant seasonality, with the seasonally averaged concentrations decreasing as follows: winter (71.95 µg m−3) > spring (64.76 µg m−3) > autumn (46.01 µg m−3) > summer (43.40 µg m−3). Our model provides a way to monitor air quality in data-scarce places, thereby advancing efforts to achieve sustainable development in the future. more...

Detecting and assessing changes in the hydrologic cycle and its response to a changing environment is essential for maintaining regional ecological security and restoring degraded ecosystems. There is no clear scientific evidence on the effects of human activities and climate variability on runoff and its components in typical arid areas. Therefore, in this study, a heuristic segmentation algorithm, a variable infiltration capacity model (VIC), and remote sensing data to quantify the effects of human activities and climate variability on runoff in the catchment of Lake Ebinur, Xinjiang, China. The results found: (1) The heuristic segmentation algorithm divided the study period into reference period (1964-1985) and two impact periods: I (1986-2000) and II (2001-2017). (2) Cropland and forest land showed an increasing trend, with grassland and barren land accounting for most of the increase. At the same time, the leaf area index (LAI) increased by 0.002 per year during the growing season. (3) Compared with the reference period, runoff depth decreased by 108.80 mm in impact period I due to human activities, but increased by 110.5 mm due to climate variability, resulting in an overall increase in runoff depth of 1.72 mm. Runoff depth increased by 11.10 mm in the impact period II compared to the reference period, with climate variability resulting in an increase of 154.40 mm, but human activities resulted in a decrease of 143.30 mm. Our results shed light on decision-making related to water stress in changing circumstances in arid regions. more...

Automatic road extraction from remote sensing images has an important impact on road maintenance and land management. While significant deep-learning-based approaches have been developed in recent years, achieving a suitable trade-off between extraction accuracy, inference speed and model size remains a fundamental and challenging issue for real-time road extraction applications, especially for rural roads. For this purpose, we developed a lightweight dynamic addition network (LDANet) to exploit rural road extraction. Specifically, considering the narrow, complex and diverse nature of rural roads, we introduce an improved Asymmetric Convolution Block (ACB)-based Inception structure to extend the low-level features in the feature extraction layer. In the deep feature association module, the depth-wise separable convolution (DSC) is introduced to reduce the computational complexity of the model, and an adaptation-weighted overlay is designed to capture the salient features. Moreover, we utilize a dynamic weighted combined loss, which can better solve the sample imbalance and boosts segmentation accuracy. In addition, we constructed a typical remote sensing dataset of rural roads based on the Deep Globe Land Cover Classification Challenge dataset. Our experiments demonstrate that LDANet performs well in road extraction with fewer model parameters ( more...

At present, extracting water-soluble organic matter (WSOM) from agricultural organic waste is primarily used to evaluate soil organic matter content in farmland. However, only a few studies have focused on its vertical behavior in the soil profile. This study aims to clarify the three-dimensional fluorescence spectrum characteristics of the WSOM samples in 0–60 cm black soil profile before and after different chemical fertilizer treatments after six years of fertilization. Fluorescence spectroscopy combined with fluorescence and ultraviolet-visible (UV-Vis) spectroscopies are used to divide four different fertilization types: no fertilization (T0), nitrogen phosphorus potassium (NPK) (T1), biochar (T2), biochar + NPK (T3), and biochar + N (T4) in a typical black soil area. The vertical characteristics of WSOC are also analyzed. The results showed that after six years of nitrogen application, T2 had a significant effect on the fluorescence intensity of Zone II (decreasing by 9.6% in the 0–20 cm soil layer) and Zone V (increasing by 8.5% in the 0–20 cm soil layer). The fluorescent components identified in each treatment group include ultraviolet radiation A humic acid-like substances (C1), ultraviolet radiation C humic acid-like substances (C2), and tryptophan-like substance (C3). As compared with the land with T1, the content of C2 in the 20–60 cm soil layer with T2 was lower, while that of C2 in the surface and subsoil with T3 was higher. In addiiton, there were no significant differences in the contents of C1, C2, and C3 by comparing the soils applied with T3 and T4, respectively. The composition of soil WSOM was found to be significantly influenced by the addition of a mixture of biochar and chemical fertilizers. The addition of biochar alone exerted a positive effect on the humification process in the surface soil (0–10 cm). NPK treatment could stimulate biological activity by increasing biological index values in deeper soil layers (40–50 cm). Nitrogen is the sovereign factor that improves the synergism effect of chemical fertilizer and biochar during the humification process. According to the UV-Vis spectrum and optical index, soil WSOM originates from land and microorganisms. This study reveals the dynamics of WSOC in the 0–60 cm soil layer and the biogeochemical effect of BC fertilizer treatment on the agricultural soil ecosystem. more...

One reason for soil degradation is salinization in inland dryland, which poses a substantial threat to arable land productivity. Remote-sensing technology provides a rapid and accurate assessment for soil salinity monitoring, but there is a lack of high-resolution remote-sensing spatial salinity estimations. The PlanetScope satellite array provides high-precision mapping for land surface monitoring through its 3-m spatial resolution and near-daily revisiting frequency. This study’s use of the PlanetScope satellite array is a new attempt to estimate soil salinity in inland drylands. We hypothesized that field observations, PlanetScope data, and spectral indices derived from the PlanetScope data using the partial least-squares regression (PLSR) method would produce reasonably accurate regional salinity maps based on 84 ground-truth soil salinity data and various spectral parameters, like satellite band reflectance, and published satellite salinity indices. The results showed that using the newly constructed red-edge salinity and yellow band salinity indices, we were able to develop several inversion models to produce regional salinity maps. Different algorithms, including Boruta feature preference, Random Forest algorithm (RF), and Extreme Gradient Boosting algorithm (XGBoost), were applied for variable selection. The newly constructed yellow salinity indices (YRNDSI and YRNDVI) had the best Pearson correlations of 0.78 and −0.78. We also found that the proportions of the newly constructed yellow and red-edge bands accounted for a large proportion of the essential strategies of the three algorithms, with Boruta feature preference at 80%, RF at 80%, and XGBoost at 60%, indicating that these two band indices contributed more to the soil salinity estimation results. The best PLSR model estimation for different strategies is the XGBoost-PLSR model with coefficient of determination (R2), root mean square error (RMSE), and ratio of performance to deviation (RPD) values of 0.832, 12.050, and 2.442, respectively. These results suggest that PlanetScope data has the potential to significantly advance the field of soil salinity research by providing a wealth of fine-scale salinity information. more...

Environmental loss is primarily caused by soil, water, and nutrient loss, and runoff is associated with nutrient transport and sediment loss. Most existing studies have focused on one influencing factor, namely slope gradient or rainfall intensity, for slope erosion and nutrient loss, but the joint effects of the two factors have rarely been researched. In this context, the impact of slope gradients (0°, 5°, 10°, and 15°) and rainfall intensities (30, 40, 50, 60, 70, and 80 mm/h) on soil erosion and nutrient loss on the sloping fields of Miyun Reservoir were explored using the indoor artificial rainfall simulation testing system. Based on the results of the study, the variation of runoff coefficient with slope gradient was not noticeable for rainfall intensities 40 mm/h, the increased range of runoff coefficient doubled, and the increase was the fastest under 0° among the four slope gradients. The slope surface runoff depth and runoff rate showed positive correlations with the rainfall intensity (r = 0.875, p < 0.01) and a negative correlation with the slope gradient. In addition, the cumulative sediment yield was positively related to the slope gradient and rainfall intensity (r > 0.464, p < 0.05). Moreover, the slope surface runoff-associated and sediment-associated loss rates of total nitrogen (TN) rose as the rainfall intensity or slope gradient increased, and significant linear positive correlations were found between the runoff-associated TN loss rate (NLr) and the runoff intensity and between the sediment-associated NLr and the erosion intensity. In addition, there were positive linear correlations between slope runoff-associated or sediment-associated TN loss volumes and rainfall intensity, surface runoff, and sediment loss volumes, which were highly remarkable. The slope gradient had a significant positive correlation with the slope surface runoff-associated TN loss at 0.05 (r = 0.452) and a significant positive correlation with the sediment-associated TN loss at the level of 0.01 (r = 0.591). The rainfall intensity exhibited extremely positive correlations with the slope surface runoff-associated and sediment-associated TN loss at 0.01 (r = 0.717 and 0.629) Slope gradients have less effect on nitrogen loss on sloped fields than rainfall intensity, mainly because rainfall intensity affects runoff depth. Based on the findings of this study, Miyun Reservoir may be able to improve nitrogen loss prevention and control. more...