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.

Biochar is an effective soil amendment for improving soil function; however, the effects of biochar produced at different pyrolysis temperatures on soil microbial community structure and enzyme activities remain insufficiently studied. A field experiment was conducted from 2023 to 2024 in the arid and semi-arid region of Northern China to investigate the effects of biochar produced at different pyrolysis temperatures (T1: 300 °C; T2: 500 °C; T3: 700 °C) and application rates (C1: 10 t ha⁻¹; C2: 20 t ha⁻¹; C3: 30 t ha⁻¹) on soil chemical properties, microbial community structure, enzyme activity, and potato nutrient use efficiency. The results indicated that the C2T2 treatment was most effective in enhancing soil fungal and actinomycete populations, increasing total microbial biomass, significantly improving soil enzyme activities, and ultimately promoting crop yield. Structural equation modeling indicated that biochar regulates soil nutrient supply, drives microbial community succession toward functional specialization, prolongs microbial regeneration cycles, and ultimately enhances potato nutrient use efficiency. The results of this research provide scientific evidence to support the sustainable development of potato farming in the North China region.

Introduction: The application of biochar is generally considered to enhance soil nutrient availability and improve soil fertility, particularly in saline environments. However, the mechanisms by which biochar pyrolysis temperature influences nitrogen (N) availability and transformation in soils with varying degrees of salinity remain unclear. Methods: In this study, a laboratory incubation experiment was conducted to investigate the effects of biochar produced at different pyrolysis temperatures under three salinity levels (0.78, 1.92, and 2.79 dS m ⁻¹ ). Five treatments were applied: control (CK), conventional nitrogen application (N1), and N1 combined with 1% (w w ⁻¹ ) biochar produced at 300 °C (N1C1), 500 °C (N1C2), and 700 °C (N1C3). Soil microbial biomass, enzyme activities, nitrogen-cycling functional genes, and nitrogen mineralization processes were measured. Results: (1) Under low and moderate salinity, the N1C2 treatment significantly increased soil microbial biomass as well as urease and acid protease activities, whereas under high salinity, N1C3 performed better. Biochar addition also elevated the relative abundance of nitrogen-cycling functional genes, indicating enhanced net nitrogen transformation capacity. (2) Increasing salinity significantly suppressed nitrogen mineralization, while biochar application alleviated this inhibitory effect. Under low and moderate salinity conditions, the N1C2 treatment exhibited higher net nitrification and nitrogen mineralization capacities, whereas under high salinity conditions, the N1C3 treatment showed the most pronounced effect. (3) Soil microbial biomass and the activities of urease and acid protease were key factors influencing nitrogen mineralization across different salinity levels. With increasing salinity, the nitrogen mineralization pathway shifted from one dominated by aerobic mineralization/nitrification to more complex mechanisms involving facultative or anaerobic processes. Discussion: These findings provide valuable insights into nitrogen management in saline soils and underscore the importance of tailoring biochar applications according to pyrolysis temperature and salinity conditions.