Optimizing agricultural water resource management is crucial for food production, as effective water management can significantly improve irrigation efficiency and crop yields. Currently, precise agricultural water demand forecasting and management have become key research focuses; however, existing methods often fail to capture complex spatial and temporal dependencies. To address this, we propose a novel deep learning framework that combines remote sensing technology with the UNet-ConvLSTM (UCL) model to effectively integrate spatial and temporal features from MODIS and GLDAS datasets. Our model leverages the high-resolution spatial data from UNet and the temporal dependencies captured by ConvLSTM to significantly improve prediction accuracy. Experimental results demonstrate that our UCL model achieves the best \(R^2\) compared to existing methods, reaching 0.927 on the MODIS dataset and 0.935 on the GLDAS dataset. This approach highlights the potential of AI and remote sensing technologies in addressing critical challenges in agricultural water management, contributing to more sustainable and efficient food production systems.

Water is a crucial resource for agricultural development in the Yellow River Basin. However, the effects of water shortages on the region’s agricultural development are becoming increasingly evident, creating a need to examine the relationship between agricultural water use (AWU) and the agricultural economy. This study uses panel vector autoregression to analyze the relationship between AWU and the agricultural economy in the Inner Mongolia section of the Yellow River Basin from 1998 to 2018. The results indicate the following: (1) AWU in the Inner Mongolia section of the Yellow River Basin significantly declined during the study period, showing clear differences in the AWU’s effectiveness among regions; (2) agriculture in the region stabilized after significant growth, and the share of primary-sector industries in the national economy also stabilized after significant decline; (3) in the long run, AWU and the agricultural economy become cointegrated with the AWU Granger-causing agricultural economy. By deepening our understanding of agricultural water demand in the Yellow River Basin, these findings provide theoretical justification for establishing water-conserving irrigation systems and making sustainable use of water resources.

To investigate the spatial and temporal changes in fractional vegetation coverage (FVC) and their driving forces in different regions of the Inner Mongolia section of the Yellow River Basin, this paper observed the spatial trends and stability of FVC in these regions based on the MOD13Q1 information regarding the 2000–2020 period as a data source. It used the dimidiate pixel model to invert FVC, and based on the centre of gravity migration model, the coefficient of variation and the Mann–Kendall and Sen’s slope estimator test, it studied the spatial variation trend and stability of FVC in the four relevant areas of the Inner Mongolia section; an attribution analysis using a geodetector was also conducted. The following results were found: (1) in terms of temporal FVC change in the relevant areas, from 2000 to 2020, the overall FVC showed an increasing trend, indicating an obvious hierarchy of change as per different seasonal scales (summer > growing season > fall > spring). There is a mutation point in FVC in different areas, and the FVC sequence is random. (2) Regarding spatial change, the overall FVC showed a trend of being high in the eastern regions and low in the western regions and low–high–low from the north to the south; the stability of the Hetao Irrigation District–Wuliangsuhai Area changed more significantly with the successive seasons, and the degraded areas of FVC were mainly distributed in the city centre of the Kundulun River–Daheihe River Area and in the Hetao Irrigation District in the summer. (3) In terms of driving factors, soil type had a relatively higher explanatory power regarding the Hetao Irrigation District–Wuliangsuhai Area, rainfall had a relatively higher explanatory power regarding the Morin River–Wuding River Area and the Kundulun River–Daheihe River Area, and land use had a relatively higher explanatory power regarding the Ten Kongtui–Heidaigou Area.

Soil wind erosion is one of the critical drivers of land degradation in the black soil region of northeastern China. In this study, 137Cs background value and soil wind erosion rate was studied by using 137Cs nuclide tracing technique in the black soil region of northeastern China, and wind erosion characteristics such as background value and soil erosion rate over the years were clarified, which has guiding significance for soil and water conservation and agricultural sustainable development in the black soil region of northeast China. The mean area activity of the Hilltop area was 1541 Bq·m-2, which was lower than the background value of 1879.7 Bq·m-2 in the study area. At the top of the hill, soil erosion occurred to some extent. The 137Cs profile has distributional characteristics that can be divided into three categories. Most of the 137Cs area activity in Hilltop area is evenly distributed in 0-15 cm, and the 137Cs area activity below 15 cm decreased gradually until it disappeared. The spatial difference of wind erosion rate is significant in the study area, mainly between 7.17-10.13 t·hm-2a-1. The average wind erosion rate of hilltops with different tillage quality depths has little difference. The average wind erosion rate is 8.60 t·hm-2a-1, which belongs to mild erosion. However, its erosion rate is higher than the tolerable soil loss of 2 t·hm-2a-1 in the black soil region of northeast China. As a result, soil erosion control in the black soil region of northeast China still requires attention.