Sap flow is widely used to estimate the transpiration and water consumption of canopies and to manage water resources. In this paper, an improved time series prediction model was proposed by integrating three basic networks—CNN, GRU and BiLSTM—to assess sap flow with historical environment variables. A dataset with 17,569 records of each, including 9 environment variables and 1 sap flow, was applied from a public database of SAPFLUXNET. After normalization, the environment variables were analyzed and composed with the factor analysis method. After the CNN-GRU-BiLSTM structure was designed, N records of three main factors were computed from environment variables, which were measured at N previous moments, and the sap flow was measured at the current moment, and they were applied for each training, validation, and testing cycle. To improve and compare the CNN-GRU-BiLSTM-based model, nine other models, using the methods of multiple linear regression, support vector regression, random forest, LSTM, GRU, BiLSTM, CNN-GRU, CNN-BiLSTM, and CNN-GRU-LSTM, were constructed in this study, respectively. Results show that the performance of the CNN-GRU-BiLSTM-based model has more accuracy than the other nine models we built in this paper, with the mean absolute error, mean squared error, mean absolute percentage error, and coefficient of determination (R²) being 0.0410, 0.0029, 0.2708 and 0.9329, respectively. Furthermore, for a comparison of the descending dimension method of factor analysis, principal component analysis (PCA) and singular value decomposition (SVD) methods were applied and compared, respectively. Results show that the performance of the factor analysis-based model is better than the PCA- or SVD-based model, with the R² results of the factor analysis-based model being higher than the PCA- and SVD-based models by 5.06% and 10.63%, respectively. This study indicates that the CNN-GRU-BiLSTM-based sap flow prediction model established with a factor analysis of historical environmental variables has optimistic applications for analyzing the transpiration of trees and evaluating water consumption.

Accurate detection of grain pests is important for ensuring food security. The existing detection algorithms still face challenges such as low precision, high false positives, and missed detection when identifying storage pests due to the small size, complex backgrounds, and limited data availability. For this reason, this paper proposes a solution jointly driven by generative AI and analytical AI, named REGAN-BS-YOLOv8. Specifically, on the one hand, an image-generative AI method of Real_ESRGAN and the mosaic data augmentation method is introduced to improve the quality, resolution and number of grain pest images. On the other hand, a novel recognition algorithm is proposed by introducing Swin Transformer and BiFPN to YOLOv8n to obtain better perception ability, positioning accuracy, detail retention and edge clarity, improving the recognition accuracy, robustness, and generalization of stored-grain pest and the anti-interference capability in complex environments. In addition, a new dataset including 5818 images of nine types of grain pests at various scales and under diverse backgrounds was collected in this study. The experimental results show that the mAP@0.5, Precision and Recall are 97.7%, 96.2% and 95.4% respectively using the method proposed in this study, outperforming the other nine models. The performance of the model we proposed is excellent for different types of storage pests under different backgrounds, and the model identifies grain pests of different sizes in different environments with high precision and provides an important theoretical basis for the management of grain silos.