Search

Remote sensing precipitation data have the characteristics of wide coverage and revealing spatiotemporal information, but their spatial resolution is low. The accuracy of the data is obviously different in different study areas and hydrometeorological conditions. This study evaluated four precipitation products in the Yellow River basin from 2001 to 2019, constructed the optimal combined product, conducted downscaling with various machine algorithms, and performed corrections using meteorological station precipitation data to analyze the spatiotemporal trends of precipitation. The results showed that (1) GPM and MSWEP had the best four evaluation indicators, with R2 values of 0.93 and 0.90, respectively, and the smallest FSE and RMSE, with a BIAS close to 0. A high-precision mixed precipitation dataset, GPM-MSWEP, was constructed. (2) Among the three methods, the downscaling results of DFNN showed higher accuracy. (3) The results, after correction with GWR, could more effectively enhance the accuracy of the data. (4) Precipitation in the Yellow River Basin showed a decreasing trend in January, September, and December, while it exhibited an increasing trend in other months and seasons, with 2002 and 2016 being points of abrupt change. This study provides a reference for the production of high-precision satellite precipitation products in the Yellow River basin. [ABSTRACT FROM AUTHOR]

The optimal selection of characteristic bands and retrieval models for the hyperspectral retrieval of soil heavy metal concentrations poses a significant challenge. Additionally, satellite-based hyperspectral retrieval encounters several issues, including atmospheric effects, limitations in temporal and radiometric resolution, and data acquisition, among others. Given this, the retrieval performance of the soil arsenic (As) concentration in Pingtan Island, the largest island in Fujian Province and the fifth largest in China, is currently unclear. This study aimed to elucidate this issue by identifying optimal characteristic bands from the full spectrum from both statistical and physical perspectives. We tested three linear models, namely Multiple Linear Regression (MLR), Partial Least Squares Regression (PLSR) and Geographically Weighted Regression (GWR), as well as three nonlinear machine learning models, including Back Propagation Neural Network (BP), Support Vector Machine Regression (SVR) and Random Forest Regression (RFR). We then retrieved soil arsenic content using ground-based soil full spectrum data on Pingtan Island. Our results indicate that the RFR model consistently outperformed all others when using both original and optimal characteristic bands. This superior performance suggests a complex, nonlinear relationship between soil arsenic concentration and spectral variables, influenced by diverse landscape factors. The GWR model, which considers spatial non-stationarity and heterogeneity, outperformed traditional models such as BP and SVR. This finding underscores the potential of incorporating spatial characteristics to enhance traditional machine learning models in geospatial studies. When evaluating retrieval model accuracy based on optimal characteristic bands, the RFR model maintained its top performance, and linear models (MLR, PLSR and GWR) showed notable improvement. Specifically, the GWR model achieved the highest r value for the validation data, indicating that selecting optimal characteristic bands based on high Pearson's correlation coefficients (e.g., abs(Pearson's correlation coefficient) ≥0.45) and high sensitivity to soil active materials successfully mitigates uncertainties linked to characteristic band selection solely based on Pearson's correlation coefficients. Consequently, two effective retrieval models were generated: the best-performing RFR model and the improved GWR model. Our study on Pingtan Island provides theoretical and technical support for monitoring and evaluating soil arsenic concentrations using satellite-based spectroscopy in densely populated, relatively independent island towns in China and worldwide. [ABSTRACT FROM AUTHOR]

Modeling inland water quality by remote sensing has already demonstrated its capacity to make accurate predictions. However, limitations still exist for applicability in diverse regions, as well as to retrieve non-optically active parameters (nOAC). Models are usually trained only with water samples from individual or local groups of waterbodies, which limits their capacity and accuracy in predicting parameters across diverse regions. This study aims to increase data availability to understand the performance of models trained with heterogeneous databases from both remote sensing and field measurement sources to improve machine learning training. This paper seeks to build a dataset with worldwide lake characteristics using data from water monitoring programs around the world paired with harmonized data of Landsat-8 and Sentinel-2. Additional feature engineering is also examined. The dataset is then used for model training and prediction of water quality at the global scale, time series analysis and water quality maps for lakes in different continents. Additionally, the modeling performance of nOACs are also investigated. The results show that trained models achieve moderately high correlations for SDD, TURB and BOD (R2 = 0.68) but lower performances for TSM and NO3-N (R2 = 0.43). The extreme learning machine (ELM) and the random forest regression (RFR) demonstrate better performance. The results indicate that ML algorithms can process remote sensing data and additional features to model water quality at the global scale and contribute to address the limitations of transferring and retrieving nOAC. However, significant limitations need to be considered, such as calibrated harmonization of water data and atmospheric correction procedures. Moreover, further understanding of the mechanisms that facilitate nOAC prediction is necessary. We highlight the need for international contributions to global water quality datasets capable of providing extensive water data for the improvement of global water monitoring. [ABSTRACT FROM AUTHOR]

This study appraised and compared the performance of process-based hydrological SWAT (soil and water assessment tool) with a machine learning-based multi-layer perceptron (MLP) models for simulating streamflow in the Upper Indus Basin. The study period ranges from 1998 to 2013, where SWAT and MLP models were calibrated/trained and validated/tested for multiple sites during 1998–2005 and 2006–2013, respectively. The performance of both models was evaluated using nash–sutcliffe efficiency (NSE), coefficient of determination (R2), Percent BIAS (PBIAS), and mean absolute percentage error (MAPE). Results illustrated the relatively poor performance of the SWAT model as compared with the MLP model. NSE, PBIAS, R2, and MAPE for SWAT (MLP) models during calibration ranged from the minimum of 0.81 (0.90), 3.49 (0.02), 0.80 (0.25) and 7.61 (0.01) to the maximum of 0.86 (0.99), 9.84 (0.12), 0.87 (0.99), and 15.71 (0.267), respectively. The poor performance of SWAT compared with MLP might be influenced by several factors, including the selection of sensitive parameters, selection of snow specific sensitive parameters that might not represent actual snow conditions, potential limitations of the SCS-CN method used to simulate streamflow, and lack of SWAT ability to capture the hydropeaking in Indus River sub-basins (at Shatial bridge and Bisham Qila). Based on the robust performance of the MLP model, the current study recommends to develop and assess machine learning models and merging the SWAT model with machine learning models. [ABSTRACT FROM AUTHOR]

The management and conservation of lakes should be conducted in the context of catchments because lakes collect water and materials from their upstream catchments. Thus, the datasets of catchment-level characteristics are essential for limnology studies. Lakes are widely spread on the Tibetan Plateau (TP), with a total lake area exceeding 50 000 km 2 , accounting for more than half of the total lake area in China. However, there has been no dataset of lake-catchment characteristics in this region to date. This study constructed the first dataset of lake-catchment characteristics for 1525 lakes with areas from 0.2 to 4503 km 2 on the TP. Considering that large lakes block the transport of materials from upstream to downstream, lake catchments are delineated in two ways: the full catchment, which refers to the full upstream-contributing area of each lake, and the inter-lake catchments, which are obtained by excluding the contributing areas of upstream lakes larger than 0.2 km 2 from the full catchment. There are six categories (i.e., lake body, topography, climate, land cover/use, soil and geology, and anthropogenic activity) and a total of 721 attributes in the dataset. Besides multi-year average attributes, the time series of 16 hydrological and meteorological variables are extracted, which can be used to drive or validate lumped hydrological models and machine learning models for hydrological simulation. The dataset contains fundamental information for analyzing the impact of catchment-level characteristics on lake properties, which on the one hand, can deepen our understanding of the drivers of lake environment change, and on the other hand can be used to predict the water and sediment properties in unsampled lakes based on limited samples. This provides exciting opportunities for lake studies in a spatially explicit context and promotes the development of landscape limnology on the TP. The dataset of lake-catchment characteristics for the Tibetan Plateau (LCC-TP v1.0) is accessible at the National Tibetan Plateau/Third Pole Environment Data Center (10.11888/Terre.tpdc.272026, Liu, 2022). [ABSTRACT FROM AUTHOR]

• First study to estimate Dissolved Organic Carbon in inland waters at a large scale. • The largest open source sample dataset AquaSat is used firstly for DOC estimation. • Satellite remote sensing and four different machine learning methods are used. • Including environmental data considerably improves the DOC estimation. • Gaussian Process Regression is the most promising method with its unique advantage. Dissolved Organic Carbon (DOC) in inland waters plays an essential role in the global carbon cycle and has significant public health effects. Machine learning (ML) together with remote sensing has emerged as a powerful and promising combination to quantify water quality parameters from space. However, inland water sample data for DOC is limited. Hence, little is known about the potential to quantify DOC content in inland waters, especially over large-scale areas. This study presents the first attempt to estimate DOC in inland waters over a large-scale area using satellite data and ML methods with the newly published open-source dataset AquaSat. Four ML approaches, namely Random Forest Regression (RFR), Support Vector Regression (SVR), Gaussian Process Regression (GPR), and a Multilayer Backpropagation Neural Network (MBPNN) were trained using more than 16 thousand samples across the continental United States matched with satellite data from Landsat 5, 7 and 8 missions. Satellite data from the Landsat missions were further extended with environmental data from the ERA5-Land product and used as input to train the ML algorithms. Our results show that including environmental data as inputs considerably improved the prediction of DOC for all ML algorithms, with GPR showing the most promising performance results with moderate estimation errors (RMSE: 4.08 mg/L). Permutation feature importance analysis showed that the wavelength range in the visible Green band (from Landsat) and the monthly average air temperature (from ERA5-Land) were the most important variables for the ML approaches. The results demonstrate the predictive strength of GPR and its useful feature to derive per pixel standard deviations for detailed analysis. Our results further highlight the important role of considering environmental processes to explain DOC variations over large scales. The application and performance of the GPR in mapping spatiotemporal variations of DOC in an entire water body were discussed by taking Lake Okeechobee (the 8th largest freshwater lake in the U.S.) as an illustrative example. While performance evaluation showed that DOC concentrations can be retrieved with adequate accuracy, algorithm development was challenged by the heterogenous nature of large-scale open source in situ data, issues related to atmospheric correction, and the low spatial and temporal resolution of the environmental predictors. This research demonstrates how open source, large-scale datasets like AquaSat in combination with ML and satellite remote sensing can make research toward large-scale estimation of inland water DOC more realistic while highlighting its remaining limitations and challenges. [Display omitted] [ABSTRACT FROM AUTHOR]

Proper irrigation scheduling and agricultural water management require a precise estimation of crop water requirement. In practice, reference evapotranspiration (ETo) is firstly estimated, and used further to calculate the evapotranspiration of each crop. In this study, two new coupled models were developed for estimating daily ETo. Two optimization algorithms, the shuffled frog-leaping algorithm (SFLA) and invasive weed optimization (IWO), were coupled on an adaptive neuro-fuzzy inference system (ANFIS) to develop and implement the two novel hybrid models (ANFIS-SFLA and ANFIS-IWO). Additionally, four empirical models with varying complexities, including Hargreaves–Samani, Romanenko, Priestley–Taylor, and Valiantzas, were used and compared with the developed hybrid models. The performance of all investigated models was evaluated using the ETo estimates with the FAO-56 recommended method as a benchmark, as well as multiple statistical indicators including root-mean-square error (RMSE), relative RMSE (RRMSE), mean absolute error (MAE), coefficient of determination (R2), and Nash–Sutcliffe efficiency (NSE). All models were tested in Tabriz and Shiraz, Iran as the two studied sites. Evaluation results showed that the developed coupled models yielded better results than the classic ANFIS, with the ANFIS-SFLA outperforming the ANFIS-IWO. Among empirical models, generally the Valiantzas model in its original and calibrated versions presented the best performance. In terms of model complexity (the number of predictors), the model performance was obviously enhanced by an increasing number of predictors. The most accurate estimates of the daily ETo for the study sites were achieved via the hybrid ANFIS-SFLA models using full predictors, with RMSE within 0.15 mm day−1, RRMSE within 4%, MAE within 0.11 mm day−1, and both a high R2 and NSE of 0.99 in the test phase at the two studied sites. [ABSTRACT FROM AUTHOR]

Remote Sensing, as a driver for water management decisions, needs further integration with monitoring water quality programs, especially in developing countries. Moreover, usage of remote sensing approaches has not been broadly applied in monitoring routines. Therefore, it is necessary to assess the efficacy of available sensors to complement the often limited field measurements from such programs and build models that support monitoring tasks. Here, we integrate field measurements (2013–2019) from the Mexican national water quality monitoring system (RNMCA) with data from Landsat-8 OLI, Sentinel-3 OLCI, and Sentinel-2 MSI to train an extreme learning machine (ELM), a support vector regression (SVR) and a linear regression (LR) for estimating Chlorophyll-a (Chl-a), Turbidity, Total Suspended Matter (TSM) and Secchi Disk Depth (SDD). Additionally, OLCI Level-2 Products for Chl-a and TSM are compared against the RNMCA data. We observed that OLCI Level-2 Products are poorly correlated with the RNMCA data and it is not feasible to rely only on them to support monitoring operations. However, OLCI atmospherically corrected data is useful to develop accurate models using an ELM, particularly for Turbidity (R2 = 0.7). We conclude that remote sensing is useful to support monitoring systems tasks, and its progressive integration will improve the quality of water quality monitoring programs. [ABSTRACT FROM AUTHOR]

The rapid expansion of oil palm is a major driver of deforestation and other associated damage to the climate and ecosystem in tropical regions, especially Southeast Asia. It is therefore necessary to precisely detect and monitor oil palm plantations to safeguard the ecosystem services and biodiversity of tropical forests. Compared with optical data, which are vulnerable to cloud cover, the Sentinel-1 dual-polarization C-band synthetic aperture radar (SAR) acquires global observations under all weather conditions and times of day and shows good performance for oil palm detection in the humid tropics. However, because accurately distinguishing mature and young oil palm trees by using optical and SAR data is difficult and considering the strong dependence on the input parameter values when detecting oil palm plantations by employing existing classification algorithms, we propose an innovative method to improve the accuracy of classifying the oil palm type (mature or young) and detecting the oil palm planting area in Sumatra by fusing Landsat-8 and Sentinel-1 images. We extract multitemporal spectral characteristics, SAR backscattering values, vegetation indices, and texture features to establish different feature combinations. Then, we use the random forest algorithm based on improved grid search optimization (IGSO-RF) and select optimal feature subsets to establish a classification model and detect oil palm plantations. Based on the IGSO-RF classifier and optimal features, our method improved the oil palm detection accuracy and obtained the best model performance (OA = 96.08% and kappa = 0.9462). Moreover, the contributions of different features to oil palm detection are different; nevertheless, the optimal feature subset performed the best and demonstrated good potential for the detection of oil palm plantations. [ABSTRACT FROM AUTHOR]

Remote-sensing-based machine learning approaches for water quality parameters estimation, Secchi Disk Depth (SDD) and Turbidity, were developed for the Valle de Bravo reservoir in central Mexico. This waterbody is a multipurpose reservoir, which provides drinking water to the metropolitan area of Mexico City. To reveal the water quality status of inland waters in the last decade, evaluation of MERIS imagery is a substantial approach. This study incorporated in-situ collected measurements across the reservoir and remote sensing reflectance data from the Medium Resolution Imaging Spectrometer (MERIS). Machine learning approaches with varying complexities were tested, and the optimal model for SDD and Turbidity was determined. Cross-validation demonstrated that the satellite-based estimates are consistent with the in-situ measurements for both SDD and Turbidity, with R2 values of 0.81 to 0.86 and RMSE of 0.15 m and 0.95 nephelometric turbidity units (NTU). The best model was applied to time series of MERIS images to analyze the spatial and temporal variations of the reservoir's water quality from 2002 to 2012. Derived analysis revealed yearly patterns caused by dry and rainy seasons and several disruptions were identified. The reservoir varied from trophic to intermittent hypertrophic status, while SDD ranged from 0–1.93 m and Turbidity up to 23.70 NTU. Results suggest the effects of drought events in the years 2006 and 2009 on water quality were correlated with water quality detriment. The water quality displayed slow recovery through 2011–2012. This study demonstrates the usefulness of satellite observations for supporting inland water quality monitoring and water management in this region. [ABSTRACT FROM AUTHOR]

[Display omitted] • EVI × PAR shows great potential for tracking the GPP variations in coastal wetlands based on the simple linear regression. • NDVI × PAR overtakes EVI × PAR for the GPP estimation in the salt marshes with little tidal influence and plant litter. • Random forest regression improves the performance in upscaling the GPP measurements to large spatial scales. • High spatial resolution, a good combination of VIs, and advanced algorithms are vital for estimating GPP in coastal wetlands. Accurate monitoring of the spatiotemporal variations in the gross primary productivity (GPP) in coastal wetlands is essential for blue carbon quantification. However, the currently available moderate-spatial-resolution GPP algorithms and products may contain large uncertainties and may rarely meet the demands of tidal wetland research. In this paper, we examine two statistical methods, namely, simple linear regression and random forest regression, to capture the high spatial resolution GPP variations in the salt marshes in the Yangtze Estuary by integrating multi-source data, including eddy covariance, Landsat, and Moderate-resolution Imaging Spectroradiometer (MODIS) satellite data. The satellite-derived photosynthetically active radiation (PAR), enhanced vegetation index (EVI), normalized difference vegetation index (NDVI), and normalized difference water index (NDWI) are used individually and in different combinations to drive the two statistical methods and investigate their performances in estimating the GPP. The results show that together with the PAR, the EVI generally has the greatest potential for GPP estimation (R2 > 0.75, RMSE < 6.80 μmol m−2 s−1) based on simple linear regression. However, the NDVI outperforms the EVI in wetlands with little tidal flooding and plant litter. The random forest method improves the performance in terms of upscaling the GPP measurements to large regions, and the combination of the EVI, NDVI, NDWI, and PAR performs the best, indicating that the use of the more advanced algorithm and the incorporation of a remotely sensed index that reflects the tidal influence are beneficial to GPP estimation in coastal salt marshes. Moreover, using Landsat data with a high spatial resolution (30 m) yields a much more accurate GPP estimation than using MODIS data with a 500 m resolution. Our results demonstrate that the use of high spatial resolution data, the proper use of remotely sensed indices, and the incorporation of a good combination of these indices through an advanced algorithm such as a machine learning algorithm are vital for capturing the nearly instantaneous GPP variations in coastal wetlands at large spatial scales. [ABSTRACT FROM AUTHOR]