Knowledge of grassland classification in a timely and accurate manner is essential for grassland resource management and utilization. Although remote sensing imagery analysis technology is widely applied for land cover classification, few studies have systematically compared the performance of commonly used methods on semi-arid native grasslands in northern China. This renders the grassland classification work in this region devoid of applicable technical references. In this study, the central Xilingol (China) was selected as the study area, and the performances of four widely used machine learning algorithms for mapping semi-arid grassland under pixel-based and object-based classification methods were compared: random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and naive Bayes (NB). The features were composed of the Landsat OLI multispectral data, spectral indices, Sentinel SAR C bands, topographic, position (coordinates), geometric, and grey-level co-occurrence matrix (GLCM) texture variables. The findings demonstrated that (1) the object-based methods depicted a more realistic land cover distribution and had greater accuracy than the pixel-based methods; (2) in the pixel-based classification, RF performed the best, with OA and Kappa values of 96.32% and 0.95, respectively. In object-based classification, RF and SVM presented no statistically different predictions, with OA and Kappa exceeding 97.5% and 0.97, respectively, and both performed significantly better than other algorithms. (3) In pixel-based classification, multispectral bands, spectral indices, and geographic features significantly distinguished grassland, whereas, in object-based classification, multispectral bands, spectral indices, elevation, and position features were more prominent. Despite the fact that Sentinel 1 SAR variables were chosen as an effective variable in object-based classification, they made no significant contribution to the grassland distinction.

Agricultural flood disaster risk assessment plays a vital role in agricultural flood disaster risk management. Extreme precipitation events are the main causes of flood disasters in the Midwest Jilin province (MJP). Therefore, it is important to analyse the characteristics of extreme precipitation events and assess the flood risk. In this study, the Multifractal Detrended Fluctuation Analysis (MF-DFA) method was used to determine the threshold of extreme precipitation events. The total duration of extreme precipitation and the total extreme precipitation were selected as flood indicators. The copula functions were then used to determine the joint distribution to calculate the bivariate joint return period, which is the flood hazard. Historical data and flood indicators were used to build an agricultural flood disaster vulnerability surface model. Finally, the risk curve for agricultural flood disasters was established to assess the flood risk in the MJP. The results show that the proposed approaches precisely describe the joint distribution of the flood indicators. The results of the vulnerability surface model are in accordance with the spatiotemporal distribution pattern of the agricultural flood disaster loss in this area. The agricultural flood risk of the MJP gradually decreases from east to west. The results provide a firm scientific basis for flood control and drainage plans in the area.

Ecosystem succession and biodiversity change associated with grassland fires are crucial for the patterns and dynamics of ecosystem functioning and services. The reactions to fire by different grassland types vary diversely, and are determined by certain species assemblages and environments. However, there are still uncertainties concerning the role of fire in affecting grassland ecosystems and how the effects are sustained. By conducting a bibliometric analysis of related articles indexed in the Web of Science between 1984 and 2020, we firstly described the general trend of these articles over the recent decades (1984–2020). The major research progress in the effects of fire on grassland ecosystems was then systematically summarized based on three levels (individual level, community level, and ecosystem level) with eight topics. We concluded that strong persistence or resistance of adapted individuals facilitated community conversion to a novel environment, which temporally and spatially interacted with ecological factors. The novel habitats could maintain more frequent fires and change an ecosystem structure and functioning. Nonetheless, the transformation of ecosystem states will present more uncertainties on prospective succession trajectories, global carbon storage, and subsequent biodiversity conservation. This review is important to flourish biodiversity, as well as aid conservation policies and strategy making.

Grassland health assessment is the basis for formulating grassland protection policy. However, there are few assessment methods that consider the angle of natural succession for northern China’s regional native grassland with excessive human activities. The main purpose of this study is to build an assessment system for these areas from the perspective of natural succession. Besides, the minimal cumulative resistance (MCR) model was used to extract potential ecological information from the study area as a supplementary reference for the assessment results. The result for Bayinxile pasture, a typical semiarid steppe with excessive human activities located in northern China, showed that: (1) The ecological function of eastern hilly area was better than that of other regions and the western area was lowest as a whole. (2) The river was the most important ecological network in the whole grassland in that it was of vital significance in the prevention of retrogressive succession and in the linking of ecological communities. (3) The density of ecological network was closely related to the intensity of human activities, and farmland and roads had great negative influence on the connection of the grassland ecological network. We further proposed an ecological control zone and made suggestions for Bayinxile ecological management to prevent grassland degradation based on the above results. This study should provide a new perspective for grassland health assessment and sustainable development of regional grassland.

The desert steppe serves as a transitional zone between grasslands and deserts, and long-term monitoring of aboveground biomass (AGB) in the desert steppe is essential for understanding grassland changes. While AGB observation techniques based on multisource remote-sensing data and machine-learning algorithms have been widely applied, research on monitoring methods specifically for the desert steppe remains limited. In this study, we focused on the desert steppe of Inner Mongolia, China, as the study area and used field sampling data, MODIS data, MODIS-based vegetation indices (VI), and environmental factors (topography, climate, and soil) to compare the performance of four commonly used machine-learning algorithms: multiple linear regression (MLR), partial least-squares regression (PLS), random forest (RF), and support vector machine (SVM) in AGB estimation. Based on the optimal model, the spatial–temporal characteristics of AGB from 2000 to 2020 were calculated, and the driving forces of climate change and human activities on AGB changes were quantitatively analyzed using the random forest algorithm. The results are as follows: (1) RF demonstrated outstanding performance in terms of prediction accuracy and model robustness, making it suitable for AGB estimation in the desert steppe of Inner Mongolia; (2) VI contributed the most to the model, and no significant difference was found between soil-adjusted VIs and traditional VIs. Elevation, slope, precipitation, and temperature all had positive effects on the model; (3) from 2000 to 2020, the multiyear average AGB in the study area was 58.34 g/m², exhibiting a gradually increasing distribution pattern from the inner region to the outer region (from north to south); (4) from 2000 to 2020, the proportions of grassland with AGB slightly and significantly increasing trend in the study area were 87.08% and 5.13%, respectively, while the proportions of grassland with AGB slightly and significantly decreasing trend were 7.76% and 0.05%, respectively; and (5) over the past 20 years, climate change, particularly precipitation, has been the primary driving force behind AGB changes of the study area. This research holds reference value for improving desert steppe monitoring capabilities and the rational planning of grassland resources.