This paper introduces WaterGPT, a language model designed for complex multimodal tasks in hydrology. WaterGPT is applied in three main areas: (1) processing and analyzing data such as images and text in water resources, (2) supporting intelligent decision-making for hydrological tasks, and (3) enabling interdisciplinary information integration and knowledge-based Q&A. The model has achieved promising results. One core aspect of WaterGPT involves the meticulous segmentation of training data for the supervised fine-tuning phase, sourced from real-world data and annotated with high quality using both manual methods and GPT-series model annotations. These data are carefully categorized into four types: knowledge-based, task-oriented, negative samples, and multi-turn dialogues. Additionally, another key component is the development of a multi-agent framework called Water_Agent, which enables WaterGPT to intelligently invoke various tools to solve complex tasks in the field of water resources. This framework handles multimodal data, including text and images, allowing for deep understanding and analysis of complex hydrological environments. Based on this framework, WaterGPT has achieved over a 90% success rate in tasks such as object detection and waterbody extraction. For the waterbody extraction task, using Dice and mIoU metrics, WaterGPT’s performance on high-resolution images from 2013 to 2022 has remained stable, with accuracy exceeding 90%. Moreover, we have constructed a high-quality water resources evaluation dataset, EvalWater, which covers 21 categories and approximately 10,000 questions. Using this dataset, WaterGPT achieved the highest accuracy to date in the field of water resources, reaching 83.09%, which is about 17.83 points higher than GPT-4.

Detecting pests and diseases on maize leaves is challenging. This is especially true under complex conditions, such as variable lighting and occlusion. Current methods suffer from low detection accuracy. They also lack sufficient real-time performance. Hence, this study introduces the lightweight detection method YOLOv11-RCDWD based on an improved YOLOv11 model. The proposed approach enhances the YOLOv11 model by incorporating the RepLKNet module as the backbone, which significantly enhances the model’s capacity to capture characteristics of maize leaf pests and diseases. Additionally, the CBAM is embedded within the neck feature extraction network to further refine the feature representation to augment the model’s capability to identify and select essential features by introducing attention mechanisms in both the channel and spatial dimensions, thereby improving the accuracy of feature expression. We have also improved the model by incorporating the DynamicHead module, WIoU loss function, and DynamicATSS label assignment strategy, which collectively enhance detection accuracy, efficiency, and robustness through optimized attention mechanisms, better handling of low-quality samples, and dynamic sample selection during training. The experimental findings indicate that the improved YOLOv11-RCDWD model effectively detected pests and diseases on maize leaves. The precision reached 92.6%, while the recall was 85.4%. The F1 score was 88.9%, and the mAP@0.5 and mAP@0.5~0.95 demonstrated an improvement of 4.9% and 9.0% over the baseline YOLOv11s. Notably, the YOLOv11-RCDWD model significantly outperformed other architectures such as Faster R-CNN, SSD, and various models within the YOLO series, demonstrating superior capabilities in terms of detection speed, parameter count, computational efficiency, and memory utilization. This model achieves an optimal balance between detection performance and resource efficiency. Overall, the improved YOLOv11-RCDWD model significantly reduces detection time and memory usage while maintaining high detection accuracy, supporting the automated detection of maize pests and diseases, and offering a robust solution for intelligent monitoring of agricultural pests.

Soil erosion is a global environmental problem. The rapid monitoring of the coverage changes in and spatial patterns of photosynthetic vegetation (PV) and non-photosynthetic vegetation (NPV) at regional scales can help improve the accuracy of soil erosion evaluations. Three deep learning semantic segmentation models, DeepLabV3+, PSPNet, and U-Net, are often used to extract features from unmanned aerial vehicle (UAV) images; however, their extraction processes are highly dependent on the assignment of massive data labels, which greatly limits their applicability. At the same time, numerous shadows are present in UAV images. It is not clear whether the shaded features can be further classified, nor how much accuracy can be achieved. This study took the Mu Us Desert in northern China as an example with which to explore the feasibility and efficiency of shadow-sensitive PV/NPV classification using the three models. Using the object-oriented classification technique alongside manual correction, 728 labels were produced for deep learning PV/NVP semantic segmentation. ResNet 50 was selected as the backbone network with which to train the sample data. Three models were used in the study; the overall accuracy (OA), the kappa coefficient, and the orthogonal statistic were applied to evaluate their accuracy and efficiency. The results showed that, for six characteristics, the three models achieved OAs of 88.3–91.9% and kappa coefficients of 0.81–0.87. The DeepLabV3+ model was superior, and its accuracy for PV and bare soil (BS) under light conditions exceeded 95%; for the three categories of PV/NPV/BS, it achieved an OA of 94.3% and a kappa coefficient of 0.90, performing slightly better (by ~2.6% (OA) and ~0.05 (kappa coefficient)) than the other two models. The DeepLabV3+ model and corresponding labels were tested in other sites for the same types of features: it achieved OAs of 93.9–95.9% and kappa coefficients of 0.88–0.92. Compared with traditional machine learning methods, such as random forest, the proposed method not only offers a marked improvement in classification accuracy but also realizes the semiautomatic extraction of PV/NPV areas. The results will be useful for land-use planning and land resource management in the areas.

Detecting pests and diseases on maize leaves under complex conditions, such as varying lighting and occlusion, is challenging, suffering from low detection accuracy and insufficient real-time performance. Hence, this study introduces the lightweight detection method YOLOv11-RepLKNet-CBAM-DynamicHead-WIoU-DynamicATSS (YOLOv11-RCDWD) based on an improved YOLOv11 model. The proposed method builds on the YOLOv11 model by introducing the RepLKNet module as the backbone network, which enhances the model's ability to express features of maize leaf pests and diseases while reducing the network parameters and computational complexity due to its efficient feature extraction capabilities. The Convolutional Block Attention Module (CBAM) is integrated into the neck feature extraction network to enhance the model's ability to select key features by introducing attention mechanisms in both the channel and spatial dimensions, thereby improving feature expression accuracy. Additionally, the DynamicHead detection head in the feature fusion structure dynamically adjusts the focus of attention through a unified attention mechanism for scale, space, and task awareness, improving detection accuracy and efficiency. Furthermore, the Weighted IoU (WIoU) loss function effectively handles the impact of low-quality samples on bounding box regression through a dynamic non-monotonic focusing mechanism. WIoU reduces the competitiveness of high-quality anchor boxes and the harmful gradients generated by low-quality samples, thereby enhancing the model's localization performance. Finally, the Dynamic Adaptive Training Sample Selection (DynamicATSS) label assignment strategy optimizes sample assignment based on statistical information during training by dynamically adjusting the selection mechanism for positive and negative samples, further enhancing the model's detection capabilities. Experimental results demonstrate that the improved YOLOv11-RCDWD model effectively detects pests and diseases on maize leaves. The precision, recall, and F1 score reach 92.6%, 85.4%, and 88.9%, respectively, an improvement of 4.9% and 9.0% over the baseline YOLOv11s. Notably, YOLOv11-RCDWD outperforms models such as Faster R-CNN, SSD, YOLOv5, YOLOv7, YOLOv8n, YOLOv9t, and YOLOv10n in detection speed (0.035 s), number of parameters (0.81 M), computational load (27.23 GFLOPs), and memory usage (6.46 MB), achieving the best balance between detection performance and resource efficiency. Overall, the improved YOLOv11-RCDWD model significantly reduces detection time and memory usage while maintaining high detection accuracy, supporting the automated detection of maize pests and diseases, and offering a robust solution for intelligent agricultural pest monitoring.

Natural solutions by which humans can overcome challenges have been severely hampered by biodiversity losses. It is essential to understand the key natural variables that influence changes in community diversity to maintain ecosystem function. The Ziwuling area has a natural recovery succession history of 150 years. Therefore, a survey was conducted to compare species composition characteristics across different vegetation recovery stages while also providing a phylogenetic and taxonomic response to the correlation between beta diversity and soil stoichiometry. The results showed that beta diversity and endemic plants had a similar single-peak temporal pattern. Soil organic carbon (SOC) accumulation was significantly positively correlated with total nitrogen (TN) and was also negatively correlated with total phosphorus (TP). Overall, soil TN, time since vegetation restoration (TVR in years), and W-SS (endemic woody plants at each stage) were able to explain 94.3% of the total variation in beta diversity. Temperate species such as Carex lanceolata, Lespedeza bicolor, and Sophora davidii are the basis for community construction. Community beta diversity patterns are the result of a mixture of ecological (e.g., climate patterns and soil nutrients) and evolutionary processes. This study combined plant resource needs with how they respond to natural recovery times in order to provide useful knowledge to protect biodiversity, the nutrient cycle, and the function of restoration ecology.

Coexistence between species within plant communities is a key issue in the practice of revegetation, forest management, and biodiversity conservation. Vegetation restoration is critical to control soil erosion and improve the ecological environment on the Loess Plateau. Here, we investigate the interspecific relationships of dominant plants during natural vegetation succession on the Loess Plateau. The results suggest that, under the ecological process of environmental filtering, species within communities can reduce interspecific competition and promote species coexistence via spatial heterogeneity and temporal asynchronous differences. The ecological niche overlap index (O_ik) significantly and positively correlated with the strength of interspecific associations. Most species pairs had weak competition and more stable interspecific relationships. The results of the χ² test showed that 317 species pairs were positively associated and 118 were negatively associated. The community is in a positive succession process, and the interaction relationship between species tends to be neutral. We should enhance the protection of positively associated species and pay attention to negatively associated species during forest management. Results revealed that Carex lanceolata Boott and Lespedeza bicolor Turcz coexisted easily with other species for mutual benefit, which could help build artificial forestland of native species to improve the ecological function.