To explore the effect of coal water slurry (CWS) gasification slag on the soil water physical characteristics of saline-alkali soil in the Yellow River Basin of Inner Mongolia, CWS gasification coarse slag (GCS) and gasification fine slag (GFS) were used as improvement materials and mixed with saline-alkali soil in different proportions. The influence mechanism of GCS and GFS on saline-alkali soil water holding capacity was investigated by measuring particle size composition, water holding capacity, and the change in the soil water characteristic curve after mixing. The results showed that adding gasification slag improved the particle size composition of saline-alkali soil, with sand content increased by -3.79%~217.31% and clay and silt content decreased by 5.77%~56.50% and -0.38%~41.53%, respectively. Soil bulk density decreased significantly ( ), with a decrease range of 15.17%~45.1%. The soil texture changed from silty loam to sandy loam, and the water retention performance improved, affecting the soil saturated water content, capillary water holding capacity, and field water holding capacity ( ), with increases ranging from 20.75%~86.15%, 7.84%~27.81%, and -1.89%~34.56%, respectively. After adding GCS and GFS, the VG model fit the soil water characteristic curve of saline-alkali soil well, indicating that the addition of gasification slag enhanced soil water retention significantly. In conclusion, CWS gasification slag effectively improved the water physical properties of saline-alkali soil and significantly enhanced the water retention and water holding capabilities.

The prediction of the daily crop leaf area index (LAI) plays a crucial role in forecasting crop growth trends and guiding field management decisions in the realm of scientific research. However, research on the daily prediction of LAI is scarce, and the challenges associated with acquiring sufficient training data pose limitations to the application of machine learning in this context. This study aimed to synergize the strengths of data assimilation and machine learning algorithms to forecast the daily LAI of maize. Initially, a data assimilation algorithm was employed to minimize the disparity between moderate-resolution imaging spectroradiometer-derived LAI and LAI generated through the CERES-Maize model. This effort resulted in a dataset comprising 289 LAI curves. Building upon this dataset, long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF) algorithms were formulated, incorporating N-day LAI input history (N = 5, 10, 15, 20, and 25) to predict LAI for days N + 1 to N + 15. The outcomes revealed that, in contrast to the LAI simulated by the crop model before assimilation, the assimilated LAI closely approximated the observed LAI, with an R² value of 0.90 and an RMSE of 0.44 m²/m². Furthermore, when compared to SVR and RF, the LSTM-based LAI prediction model exhibited superior accuracy at N = 15, achieving R² values of 0.99 and 0.99 for the training and testing datasets, respectively, along with RMSE values of 0.12 and 0.14 m²/m². It was evident that data assimilation supplied an ample number of samples for the training of machine learning algorithms. The integration of data assimilation technology with machine learning algorithms proved to be an effective methodology for forecasting daily crop LAI.

Water Requirement of Naked Oats under Subsurface Drip Irrigation in the North Foot of Yinshan Mountain Based on Single Crop Coefficient Approach: In order to accurately and rapidly calculate the water requirement of naked oats under drip irrigation in the north foot of Yinshan Mountain, the study adopted the and calculation method for potential evapotranspiration recommended in document FAO56 and applied SCCA to calculate the water requirement of crops based on the deficient irrigation experiments. The results indicated that the water requirements of naked oats without drought influence was 383.8 mm, and the maximum daily average water requirement intensity was heading flowering, which was the critical period of crop water requirement, and the mean value of in the whole growth period was 3.89 mm/d. After correction, of naked oats in the initial growth stage, crop development growth stage, mid-season growth stage, and late season growth stage was 0.34, 0.94, 1.05, and 0.36. The average of naked oats in the whole growth stage was 0.71. SCCA does not consider the influence of wetting depth in the initial growth period of crops and the correction of local irrigation in the mid-season and late season stage of crops. Therefore, when the irrigation quota of naked oats is 315 mm, the crop water requirement calculated by SCCA is 363.84 mm, which is about 10% different from the measured value. The results show that SCCA can be used to calculate the water requirement of naked oats under drip irrigation at the northern foot of Yinshan Mountain in Inner Mongolia, and the calculation error is within the allowable range. However, it is also necessary to consider the influence of different irrigation forms and plant height of crops on calculation value.