Crop models are instrumental in simulating resource utilization in agriculture, yet their complexity necessitates extensive calibration, which can impact the accuracy of yield predictions. Machine learning shows promise for enhancing yield estimations but relies on vast amounts of training data. This study aims to improve the pakchoi yield prediction accuracy of simulation models. We developed a stacking ensemble learning model that integrates three base models—EU-Rotate_N, Random Forest Regression and Support Vector Regression—with a Multi-layer Perceptron as the meta-model for the pakchoi dry matter yield prediction. To enhance the training dataset and bolster machine learning performance, we employed the EU-Rotate_N model to simulate daily dry matter yields for unsampled data. The test results revealed that the stacking model outperformed each base model. The stacking model achieved an R² value of 0.834, which was approximately 0.1 higher than that of the EU-Rotate_N model. The RMSE and MAE were 0.283 t/ha and 0.196 t/ha, respectively, both approximately 0.6 t/ha lower than those of the EU-Rotate_N model. The performance of the stacking model, developed with the expanded dataset, showed a significant improvement over the model based on the original dataset.

To pursue high yields, the excessive application of nitrogen (N) fertilizer has been reported in high-residual soil nitrate levels, excessive nitrate leaching, and nitrate contamination of groundwater. In this study, tomato crops (Lycopersicon esculentum Mill.) were subjected to various nitrogen treatments, and the nitrate nitrogen content, soil water content at different soil layers, dry matter, and yield were measured. A mechanistic model, EU-Rotate_N, was used to simulate the aforementioned indexes in a region of Jiangsu province with a relatively higher water table. The predicted values of soil moisture and soil nitrate content at various soil depths agree well with the measured values during tomato growth. The statistical index of soil water content ranged from 0.367 to 0.749, 0.856 to 0.947, and the statistical index of soil nitrate nitrogen content ranged from 0.365 to 0.698, and 0.869 to 0.932, for Autumn-Winter (AW) and Spring-Summer (SS) crops, respectively. Moreover, the dry weight and yield simulation effects of the tomato are also in good agreement with the actual measured values. The results show that the EU-Rotate_N model is effective in simulating soil water content, nitrate nitrogen content, dry matter quality, and yield in Jiangsu province, with little underestimation in soil water content at a soil depth of 20–30 cm during SS, which might be improved further considering the high water table of the region.