Search

Unregulated livestock breeding and grazing can degrade grasslands and damage the ecological environment. The combination of remote sensing and artificial intelligence techniques is a more convenient and powerful means to acquire livestock information in a large area than traditional manual ground investigation. As a mainstream remote sensing platform, unmanned aerial vehicles (UAVs) can obtain high-resolution optical images to detect grazing livestock in grassland. However, grazing livestock objects in UAV images usually occupy very few pixels and tend to gather together, which makes them difficult to detect and count automatically. This paper proposes the GLDM (grazing livestock detection model), a lightweight and high-accuracy deep-learning model, for detecting grazing livestock in UAV images. The enhanced CSPDarknet (ECSP) and weighted aggregate feature re-extraction pyramid modules (WAFR) are constructed to improve the performance based on the YOLOX-nano network scheme. The dataset of different grazing livestock (12,901 instances) for deep learning was made from UAV images in the Hadatu Pasture of Hulunbuir, Inner Mongolia, China. The results show that the proposed method achieves a higher comprehensive detection precision than mainstream object detection models and has an advantage in model size. The m A P of the proposed method is 86.47%, with the model parameter 5.7 M. The average recall and average precision can be above 85% at the same time. The counting accuracy of grazing livestock in the testing dataset, when converted to a unified sheep unit, reached 99%. The scale applicability of the model is also discussed, and the GLDM could perform well with the image resolution varying from 2.5 to 10 cm. The proposed method, the GLDM, was better for detecting grassland grazing livestock in UAV images, combining remote sensing, AI, and grassland ecological applications with broad application prospects. [ABSTRACT FROM AUTHOR]

Leaf area index (LAI) is a key indicator of vegetation structure and function, and its products have a wide range of applications in vegetation condition assessment and usually act as important input parameters for ecosystem modeling. Grassland plays an important role in regional climate change and the global carbon cycle and numerous studies have focused on the product-based analysis of grassland vegetation changes. However, the performance of various LAI products and their discrepancies across different grassland types in drylands remain unclear. Therefore, it is critical to assess these products prior to application. We evaluated the accuracy of four commonly used LAI products (GEOV2, GLASS, GLOBMAP, and MODIS) using LAI reference maps based on both bridging and cross-validation approaches. Under different grassland types, the GLASS LAI performed better in meadow steppe (R2 = 0.26, RMSE = 0.41 m2/m2) and typical steppe (R2 = 0.32, RMSE = 0.38 m2/m2); the GEOV2 LAI performed better in desert steppe (R2 = 0.39, RMSE = 0.30 m2/m2). When we assessed their spatial and temporal discrepancies during the period from 2010 to 2019, the four LAI products overall showed a high spatial and temporal consistency across the region. Compared with GLASS LAI, the most consistent to least consistent correlations can be ordered by GEOV2 LAI (R2 = 0.94), MODIS LAI (R2 = 0.92), and GLOBMAP LAI (R2 = 0.87). The largest differences in LAI throughout the year occurred in July for all grassland types. Limited by the location and number of sample plots, we mainly focused on spatial and temporal variations. The spatial heterogeneity of land surface is pervasive, especially in vast grassland areas with rich grassland types, and the results of this study can provide a basis for the application of the product in different grassland types. Furthermore, it is essential to develop highly accurate and reliable satellite-based LAI products focused on grassland from the regional to the global scale according to these popular approaches, which is the next step in our work plan. [ABSTRACT FROM AUTHOR]

Ecological protection and high-quality development of the Yellow River Basin (YRB), China, aroused remarkable concerns from China's Central Government, and has been a major national strategy. The Inner Mongolia reach of the Yellow River Basin (IM-YRB) is a typical dryland with pervasive vegetation restoration through the actions of the ecological projects that have been conducted in recent years. However, how climate changes and human activities, such as land use and land cover (LULC) changes, jointly impact vegetation variations in this region remains poorly understood. Here, using an explainable machine learning technique, we evaluated linkages between the kernel normalized difference vegetation index (kNDVI) and air temperature, precipitation, soil moisture, and LULC changes, and relevant marginal contributions of these four drivers to the observed vegetation changes. The grassland fraction on a pixel level was selected as the quantitative LULC variable due to its key role in regional LULC. We found that interannual kNDVI changes in most areas of this study region were negatively sensitive to temperature, but positively sensitive to precipitation and soil moisture, with area fractions of 71.74%, 96.93%, and 89.33%, respectively. The area fraction of negative kNDVI sensitivity to LULC was roughly equivalent to that of positive kNDVI sensitivity. The contributions of air temperature, precipitation, soil moisture, and LULC to overall kNDVI changes were 21.54%, 33.32%, 32.19%, and 12.95%, respectively. Moisture conditions also play a critical role in vegetation changes, which was reflected by the fluctuating growth of kNDVI as interannual changes in precipitation. Nonetheless, kNDVI changes are also affected by LULC, and LULC became the dominant factor behind the kNDVI anomalies over the grassland restoration regions from barren over the IM-YRB. This research provides theoretical support for dryland vegetation restoration under the influence of climate change. [ABSTRACT FROM AUTHOR]

Coal is an important energy resource in the world, especially in China. Extensive coal exploitation seriously damaged the grassland and its fragile ecosystem. However, temporal and spatial impact laws of open-pit coal exploitation on Landscape Ecological Health (LEH) of semi-arid grasslands are still not clear. Therefore, the main objective of this paper is to study impact of Large-scale Open-pit Coal Base (LOCB) on the LEH of semi-arid grasslands from the perspectives of temporal and spatial. Taking Shengli LOCB of Xilinguole grassland in Inner Mongolia as an example, we demonstrate a conceptual model of LOCB impact on LEH of semi-arid grasslands, and establish a research system called landscape Index-pattern Evolution-Driving force-Spatial statistics (IEDS). A complete process integrated from investigation, monitoring, and evaluation to the analysis of impact laws was developed. Result indicated that coal mining causes gradual increase of landscape patches, landscape fragmentation, gradual decline of landscape connectivity, complexity and irregularity of landscape shape, enhancement of landscape heterogeneity and complexity, gradual decline of landscape stability, gradual decrease of grassland landscape and annual increase of unhealthy grassland landscape. The LEH of grassland basically belongs to the state of slight deterioration. In the past 15 years, the spatial and temporal distribution characteristics of LEH in the study area are similar. This study provides scientific reference for ecological disturbance research, environmental protection, landscape planning, restoration and renovation of ecological environment in mining areas. At the same time, future research should integrate geological, hydrological, soil, vegetation, microorganisms, animals, climate, and other perspectives to study the impact of mining on landscape ecology deeply. [ABSTRACT FROM AUTHOR]

The main feature of grassland degradation is the change in the vegetation community structure. Hyperspectral-based grassland community identification is the basis and a prerequisite for large-area high-precision grassland degradation monitoring and management. To obtain the distribution pattern of grassland communities in Xilinhot, Inner Mongolia Autonomous Region, China, we propose a systematic classification method (SCM) for hyperspectral grassland community identification using China's ZiYuan 1-02D (ZY1-02D) satellite. First, the sample label data were selected from the field-collected samples, vegetation map data, and function zoning data for the Nature Reserve. Second, the spatial features of the images were extracted using extended morphological profiles (EMPs) based on the reduced dimensionality of principal component analysis (PCA). Then, they were input into the random forest (RF) classifier to obtain the preclassification results for grassland communities. Finally, to reduce the influence of salt-and-pepper noise, the label similarity probability filter (LSPF) method was used for postclassification processing, and the RF was again used to obtain the final classification results. The results showed that, compared with the other seven (e.g., SVM, RF, 3D-CNN) methods, the SCM obtained the optimal classification results with an overall classification accuracy (OCA) of 94.56%. In addition, the mapping results of the SCM showed its ability to accurately identify various ground objects in large-scale grassland community scenes. [ABSTRACT FROM AUTHOR]

The evolution of meandering rivers continues to attract considerable attention in research and for practical applications, given that it is closely associated with the safety of river systems and riparian zones. There has been much discussion regarding the various channel planform features exhibited by meandering rivers under different river systems and riparian conditions. The Yimin River is a good example and is located southeast of the Hulun Buir Grassland, which is characterised by a fragile ecosystem and little anthropological activity along with active flow during the non-frozen season from May to November each year and relatively low sediment discharge compared with the Yellow River and Mississippi River. Improved analysis of the evolution of the Yimin River from 1975 to 2019 can support increased local species diversity and more effective flood risk and river management. With the combined Google Earth Engine (GEE) platform and the Geographic Information Systems (GIS) technique, remote sensing images, including Landsat images and global surface water data, are used to analyse the channel planform features of the freely meandering river channel in the middle and lower Yimin River. The results show that the percentage of low sinuosity channel bends was higher than that of high-sinuosity bends. Although the bends with an amplitude greater than 0.48 km and sinuosity greater than 2.3 have an evident upstream-skewed trend, the main channel planform features were downstream skewed with 1499 such bends. The river system conditions in the Yimin River, including lower sediment discharge and vegetation cover, are conducive to the development of downstream-skewed bends. The high-sinuosity bends were found to have a relatively larger ratio during 1981–2000, a period with higher mean annual streamflow compared with other time periods. [ABSTRACT FROM AUTHOR]

Estimating the Start of Growing Season (SOS) of grassland on the global scale is an important scientific issue since it can reflect the response of the terrestrial ecosystem to environmental changes and determine the start time of grazing. However, most remote sensing data has coarse- temporal and spatial resolution, resulting in low accuracy of SOS retrieval based on remote sensing methods. In recent years, much research has focused on multi-source data fusion technology to improve the spatio-temporal resolution of remote sensing information, and to provide a feasible path for high-accuracy remote sensing inversion of SOS. Nevertheless, there is still a lack of quantitative evaluation for the accuracy of these data fusion methods in SOS estimation. Therefore, in this study, the SOS estimation accuracy is quantitatively evaluated based on the spatio-temporal fusion daily datasets through the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) and other models in Xilinhot City, Inner Mongolia, China. The results show that: (1) the accuracy of SOS estimation based on spatio-temporal fusion daily datasets has been slightly improved, the average Root Mean Square Error (RMSE) of SOS based on 8d composite datasets is 11.1d, and the best is 9.7d ( f s t a r f m 8 ); (2) the estimation accuracy based on 8d composite datasets ( R M S E ¯ = 11.1d) is better than daily fusion datasets ( R M S E ¯ = 18.2d); (3) the lack of the Landsat data during the SOS would decrease the quality of the fusion datasets, which ultimately reduces the accuracy of the SOS estimation. The R M S E ¯ of SOS based on all three models increases by 11.1d, and the STARFM is least affected, just increases 2.7d. The results highlight the potential of the spatio-temporal data fusion method in high-accuracy grassland SOS estimation. It also shows that the dataset fused by the STARFM algorithm and composed for 8 days is better for SOS estimation. [ABSTRACT FROM AUTHOR]

Grassland classification is crucial for grassland management. One commonly used method utilizes remote sensing vegetation indices (VIs) to map grassland classes at various scales. However, most grassland classifications were conducted as case studies in a small area due to lack of field data sources. At a small scale, classification is reliable; however, great uncertainty emerges when extended to other areas. In this study, large amounts of field observations (more than 30,000 aerial photos) were obtained using unmanned aerial vehicle photography in Inner Mongolia, China, during the peak period of grassland growth in 2018 and 2019. Then, four machine learning classification algorithms were constructed based on characteristic indices of MODIS NDVI in the growing season to map grassland classes of Inner Mongolia. Finally, the spatial distribution and temporal variation of temperate grassland classes were analyzed. Results showed that: (1) Among all characteristic indices, the maximum, average, and sum of MODIS NDVI from July to September during 2015 to 2019 greatly affected grassland classification. (2) The random forest method exhibited the best performance with overall accuracy and kappa coefficient being 72.17% and 0.62, respectively. (3) Compared with the grassland class mapped in the 1980s, 30.98% of grassland classes have been transformed. Our study provides a technological basis for effective and accurate classification of the temperate steppe class and a theoretical foundation for sustainable development and restoration of the temperate steppe ecosystem. [ABSTRACT FROM AUTHOR]

Plant phenology, especially the timing of the start and the end of the vegetation growing season (SOS and EOS), plays a major role in grassland ecosystem carbon cycles. As the second-largest grassland country in the world, China's grasslands are mainly distributed in the northern cold temperate climate zone. The accuracies and relations of plant phenology estimations from multialgorithms and data resources are poorly understood. Here, we investigated vegetation phenology in two typical cold temperate grasslands, Haibei (HB) and Inner Mongolia (NM) grasslands, in China from 2001 to 2017. Compared to ground vegetation phenology observations, we analyzed the performance of the moderate resolution imaging spectroradiometer MODIS phenology products (MCD12Q2) and two remote sensing-based vegetation phenology algorithms from the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) time series (five satellite-based phenology algorithms). The optimal algorithm was used to compare with eddy covariance (EC)-based carbon phenology, and to calculate the thresholds of carbon phenology periods (SOSt and EOSt) in each site. Results showed that satellite-based phenology estimations (all five algorithms in this study) were strongly coupled with the temporal variation of the observed phenological period but significantly overestimated the SOS, predicting it to be over 21 days later than the field data. The carbon phenology thresholds of HB grassland (HB_SOSt and HB_EOSt) had a significant upward trend, with the multiyear average values being 0.14 and 0.29, respectively. In contrast, the thresholds of NM grasslands (NM_SOSt and NM_EOSt) also showed a certain upward trend, but it was not significant (p > 0.05), with the multiyear average values being 0.17 and 0.2, respectively. Our study suggested the thresholds of carbon phenology periods (SOSt and EOSt, %) could be simply and effectively estimated based on their significant relationship with the EC-based maximum of gross primary productivity observations (GPPmax) at a specific site and time. Therefore, this study suggested the thresholds of carbon phenology were not fixed even in a specific ecosystem, which also provided simple bridges between satellite-based vegetation phenology and EC-based carbon phenology in similar grasslands. [ABSTRACT FROM AUTHOR]