Dawei Xu

Invasive aquatic plants such as water hyacinth (Eichhornia crassipes [Mart.] Solms) pose significant threats to freshwater ecosystems through obstruction of waterways, alteration of hydrodynamics, and impacts on biodiversity. Effective monitoring is critical for ecosystem protection and sustainable water management. However, learning-based approaches, such as machine learning and deep learning, require extensive annotated training data and substantial computational resources, limiting their suitability for large-scale operational monitoring. To address this, we developed a multitemporal image differencing (MID) approach that leverages the highly dynamic nature of water hyacinth in flowing waters. By analyzing a sequence of multitemporal satellite images, MID directly captures spatial and temporal changes, enabling timely and reliable detection of both established and newly forming patches. MID achieved an overall accuracy of 90.7%, comparable to the random forest classifier at 91.0%, while providing better discrimination of dynamic water hyacinth from stable nontarget vegetation, reflecting its ability to exploit temporal dynamics that single-date classifiers cannot capture. With high computational efficiency, simplicity, and scalability, MID is highly suitable for large-scale operational monitoring of invasive aquatic plants. These results demonstrate that MID is a robust and scalable framework for supporting ecological management and timely decision-making in dynamic freshwater systems.

Wind erosion poses a significant challenge to agricultural sustainability in Northern China’s arid regions. This study investigated the effectiveness of alfalfa grassland versus conventional cropland in controlling wind erosion across nine study sites in three agroecological regions. Using Sentinel-2 satellite imagery and the Revised Wind Erosion Equation (RWEQ) model, we analyzed vegetation cover duration and quantified soil wind erosion from 2018 to 2020. The results showed that alfalfa grassland extended vegetation cover by 80 days annually compared to cropland, with most extension occurring in spring. Alfalfa grassland demonstrated superior erosion control, reducing soil losses by 50% (24.02 versus 50.70 t/ha/yr) and increasing soil retention threefold (1.52 versus 0.59 t/ha/yr) compared to cropland. The northwest region experienced the highest erosion rates, while management practices significantly influenced alfalfa’s soil conservation effectiveness. Multiple regression analysis revealed vegetation cover and annual precipitation as primary factors affecting wind erosion. These findings suggest integrating alfalfa into crop rotations could effectively enhance soil conservation in Northern China’s wind erosion-prone regions.

Estimating forage yield and nutrient composition using hyperspectral remote sensing is a major challenge. However, there is still a lack of comprehensive research on the optimal wavelength for the analysis of various nutrients in pasture. In this research, conducted in Hailar District, Hulunber City, Inner Mongolia Autonomous Region, China, 126 sets of hyperspectral data were collected, covering a spectral range of 350 to 1800 nanometers. The primary objective was to identify key spectral bands for estimating forage dry matter yield (DMY), nitrogen content (NC), neutral detergent fiber (NDF), and acid detergent fiber (ADF) using principal component analysis (PCA), random forests (RF), and SHapley Additive exPlanations (SHAP) analysis methods, and then the RF and Extra-Trees algorithm (ERT) model was used to predict aboveground biomass (AGB) and nutrient parameters using the optimized spectral bands and vegetation indices. Our approach effectively minimizes redundancy in hyperspectral data by selectively employing crucial spectral bands, thus improving the accuracy of forage nutrient estimation. PCA identified the most variable bands at 400 nm, 520–550 nm, 670–720 nm, and 930–950 nm, reflecting their general spectral significance rather than a link to specific forage nutrients. Further analysis using RF feature importance pinpointed influential bands, predominantly within 930–940 nm and 700–730 nm. SHAP analysis confirmed critical bands for DMY (965 nm, 712 nm, and 1652 nm), NC (1390 nm and 713 nm), ADF (1390 nm and 715–725 nm), and NDF (400 nm, 983 nm, 1350 nm, and 1800 nm). The fitting accuracy for ADF estimated using RF was lower (R² = 0.58), while the fitting accuracy for other indicators was higher (R² ≥ 0.59). The performance and prediction accuracy of ERT (R² = 0.63) were noticeably superior to those of RF. In conclusion, our method effectively identifies influential bands, optimizing forage yield and quality estimation.

The interrelation between grassland vegetation greenness and hydrothermal conditions on the Tibetan Plateau demonstrates a significant correlation. However, understanding the spatial patterns and the degree of this correlation, especially in relation to minimum and maximum air temperatures across various vertical gradient zones of the Plateau, necessitates further examination. Utilizing the normalized difference phenology index (NDPI) and considering four distinct hydrothermal conditions (minimum, maximum, mean temperature, and precipitation) during the growing season, an analysis was conducted on the correlation of NDPI with hydrothermal conditions across plateau elevations from 2000 to 2021. Results indicate that the correlation between vegetation greenness and hydrothermal conditions on the Tibetan Plateau grasslands is spatially varied. There is a pronounced negative correlation of greenness to maximum temperature and precipitation in the northeastern plateau, while areas exhibit stronger positive correlations to mean temperature. Additionally, as elevation increases, the positive correlation and sensitivity of alpine grassland vegetation greenness to minimum temperature significantly intensify, contrary to the effects observed with maximum temperature. The correlations between greenness and mean temperature in relation to elevational changes primarily exhibit a unimodal pattern across the Tibetan Plateau. These findings emphasize that the correlation and sensitivity of grassland vegetation greenness to hydrothermal conditions are both elevation-dependent and spatially distinct.

Alfalfa (Medicago sativa L.) is a widely planted perennial legume forage plant with excellent quality and high yield. In production, it is very important to determine alfalfa growth dynamics and forage yield in a timely and accurate manner. This study focused on inverse algorithms for predicting alfalfa forage yield in large-scale alfalfa production. We carried out forage yield and aboveground biomass (AGB) field surveys at different times in 2022. The correlations among the reflectance of different satellite remote sensing bands, vegetation indices, and alfalfa forage yield/AGB were analyzed, additionally the suitable bands and vegetation indices for alfalfa forage yield inversion algorithms were screened, and the performance of the statistical models and machine learning (ML) algorithms for alfalfa forage yield inversion were comparatively analyzed. The results showed that (1) regarding different harvest times, the alfalfa forage yield inversion model for first-harvest alfalfa had relatively large differences in growth, and the simulation accuracy of the alfalfa forage yield inversion model was higher than that for the other harvest times, with the growth of the second- and third-harvest alfalfa being more homogeneous and the simulation accuracy of the forage yield inversion model being relatively low. (2) In the alfalfa forage yield inversion model based on a single parameter, the moisture-related vegetation indices, such as the global vegetation moisture index (GVMI), normalized difference water index (NDWI) and normalized difference infrared index (NDII), had higher coefficients of correlation with alfalfa forage yield/AGB, and the coefficients of correlation R² values for the first-harvest alfalfa were greater than 0.50, with the NDWI correlation being the best with an R² value of 0.60. (3) For the alfalfa forage yield inversion model constructed with vegetation indices and band reflectance as multiparameter variables, the random forest (RF) and support vector machine (SVM) simulation accuracy was higher than that of the alfalfa forage yield inversion model based on a single parameter; the first-harvest alfalfa R² values based on the multiparameter RF and SVM models were both 0.65, the root mean square errors (RMSEs) were 329.74 g/m² and 332.32 g/m², and the biases were −0.47 g/m² and −2.24 g/m², respectively. The vegetation indices related to plant water content can be considered using a single parameter inversion model for alfalfa forage yield, the vegetation indices and band reflectance can be considered using a multiparameter inversion model for alfalfa forage yield, and ML algorithms are also an optimal choice. The findings in this study can provide technical support for the effective and strategic production management of large-scale alfalfa.

Understanding the grassland ecosystem is crucial for improving grassland ecosystem functions and services such as climate regulation, water and soil conservation, carbon sequestration, and biodiversity and gene pool maintenance. However, a systematic and comprehensive review of the relevant literature is still unclear and lacking. The VOSviewer software and cluster analysis were used to visually analyze and perform dimension reduction classification on the 27,778 studies related to grassland ecosystem research based on the Web of Science database. The number of publications targeting grassland ecosystem increased rapidly from 2006 to 2021. Ecology, agronomy, and environmental science were the most popular research categories, and the top journal sources were Remote Sensing, Journal of Ecology, and Ecology and Evolution. The leading publishing countries were the United States, China, and Germany. The top three institutions were the Chinese Academy of Sciences, the University of Chinese Academy of Sciences, and Colorado State University. Cooperation between different countries and institutions had increased. Keyword co-occurrence network analysis showed that Biodiversity, Vegetation and Conservation were the most popular study areas, grassland management, climate change, land use pattern, and ecosystem impact were the hot research topics. All studies could be divided into three categories by cluster analysis: grassland ecological characteristics including basic physicochemical properties, vegetation community characteristics, aboveground and belowground biomass, and soil structural quality of grassland; driving mechanisms that demonstrated effects of human activities and climate change on grassland ecosystem function; and grassland ecosystem services that focused the influences of different grassland management strategies on ecological services, animal welfare and human well-being. The three topic categories of reviewed studies were interrelated and consistent with each other, and the performances were progressive. This paper reviewed the trend evolution through keyword hotspots and analyzed the future research directions to provide an important reference for scientists to better respond to the balance of herbage and sustainable utilization of grassland and maintenance of ecological security.

Background and aims: Grazing and mowing are widely adopted management practices for the semiarid steppe in China that profoundly affect the greenhouse gas (GHG) flux in grassland ecosystems. However, the general mechanisms for CH₄ and N₂O fluxes in response to grazing and mowing remain poorly understood. Thus, we conducted year-round flux measurements of CH₄ and N₂O fluxes to investigate the effect of grazing and mowing on CH₄ and N₂O fluxes. Methods: Using manual static chamber and gas chromatography, we measured the fluxes of CH₄ and N₂O from grazing-exclusion, grazing and mowing sites from June 2019 to June 2020 in the Hulunbuir Grassland, Inner Mongolia. Results: Grazing and mowing increased soil temperature and reduced soil water content and soil inorganic N content. Compared with grazing and mowing, lower mean CH₄ uptake (−67.58 ± 8.9 μg m⁻² h⁻¹) and higher mean N₂O emissions (29.17 ± 6.8 μg m⁻² h⁻¹) were found at the grazing-exclusion site. No pulse emissions of N₂O were found for all sites during the spring thaw period (STP), and only two small N₂O emission peaks due to soil thawing were captured on April 2nd and 5th. The contribution of the spring thaw to the total annual N₂O budget was small and accounted for only 10%, 13% and 12% of the annual fluxes at the grazing-exclusion, grazing and mowing sites, respectively. Conclusion: Our results indicate that grazing and mowing enhance CH₄ uptake and inhibit N₂O emissions, primarily due to the increased soil temperature and reduced soil water content and soil inorganic N content. No apparent pulse N₂O emissions were observed at any of the three sites during the STP in the Hulunbuir grassland.

Alfalfa (Medicago sativa L.) is one of the most widely planted forages due to its useful characteristics. Although alfalfa spatial distribution is an important source of basic data, manual surveys incur high survey costs, require large workloads and confront difficulties in collecting data over large areas; remote sensing compensates for these shortcomings. In this study, the time-series variation characteristics of different vegetation types were analyzed, and the extraction method of alfalfa mapping was established according to different spatial- and temporal-resolution remote sensing data. The results provided the following conclusions: (1) when using the wave peak and valley number of normalized difference vegetation index (NDVI) curves, in the study area, the number of wave peak needed to be greater than 2 and the number of wave valley needed to be greater than 1; (2) 91.6% of alfalfa sampling points were extracted by moderate resolution imaging spectroradiometer (MODIS) data using the wave peak and valley method, and 5.0% of oats sampling points were extracted as alfalfa, while no other vegetation types met these conditions; (3) 85.3% of alfalfa sampling points were identified from Sentinel-2 multispectral instrument (MSI) data using the wave peak and valley method; 6.0% of grassland vegetation and 8.7% of oats satisfied the conditions, while other vegetation types did not satisfy this rule; and (4) the temporal phase selection was very important for alfalfa extraction using single-time phase remote sensing images; alfalfa was easily separated from other vegetation at the pre−wintering stage and was more difficult to separate at the spring regreening stage due to the variability in the alfalfa overwintering rate; the overall classification accuracy was 92.9% with the supervised classification method using support vector machine (SVM) at the pre-wintering stage. These findings provide a promising approach to alfalfa mapping using different remote sensing data.

Leaf area index (LAI) is one of the key biophysical indicators for characterizing the growth and status of vegetation and is also used in modeling earth system processes. Machine learning algorithms (MLAs) such as random forest regression (RFR), artificial neural network regression (ANNR) and support vector regression (SVR) based on satellite data have been widely used for the estimation of LAI. However, the selection of input variables has a great impact on the estimation performance of MLAs. In this study, we aimed to improve the LAI inversion model of Inner Mongolia grassland based on MLAs incorporating empirical knowledge. Firstly, we used the ANNR, SVR and RFR approaches, respectively, to rank the input variables including vegetation indices, climate factors, soil factors and topography factors and found that Normalized Difference Phenology Index (NDPI) contributed the most to LAI estimation. Secondly, we selected four sets of input variables, namely, all variables—A, model selected variables—B, overlapping variables—C and self-defined variables—D, respectively. Subsequently, we built twelve LAI estimation models (RFR-A, RFR-B, RFR-C, etc.) based on three MLAs and four sets of input variables. The evaluation of them showed the RFR produced higher prediction accuracy, followed by ANNR and SVR. Furthermore, the RFR-D presented the highest accuracy in predicting LAI (R² = 0.55, RMSE = 0.37 m²/m², MAE = 0.29 m²/m²). Finally, we compared our results with MODIS LAI and GEOV2 LAI products and found that all of them showed a similar spatial distribution of grassland LAI in the four sub-regions covering all grassland types, but our model exhibited larger LAI values in the desert steppe and smaller LAI values in the others. These findings demonstrated that MLAs incorporating empirical knowledge could improve the accuracy of modelling LAI and further study is necessary to reduce the uncertainty in LAI mapping in grassland.