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.

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.

Automated water body (WB) extraction is one of the hot research topics in the field of remote sensing image processing. To address the challenges of over-extraction and incomplete extraction in complex water scenes, we propose an encoder–decoder architecture semantic segmentation network for high-precision extraction of WBs called EDWNet. We integrate the Cross-layer Feature Fusion (CFF) module to solve difficulties in segmentation of WB edges, utilizing the Global Attention Mechanism (GAM) module to reduce information diffusion, and combining with the Deep Attention Module (DAM) module to enhance the model’s global perception ability and refine WB features. Additionally, an auxiliary head is incorporated to optimize the model’s learning process. In addition, we analyze the feature importance of bands 2 to 7 in Landsat 8 OLI images, constructing a band combination (RGB 763) suitable for algorithm’s WB extraction. When we compare EDWNet with various other semantic segmentation networks, the results on the test dataset show that EDWNet has the highest accuracy. EDWNet is applied to accurately extract WBs in the Weihe River basin from 2013 to 2021, and we quantitatively analyzed the area changes of the WBs during this period and their causes. The results show that EDWNet is suitable for WB extraction in complex scenes and demonstrates great potential in long time-series and large-scale WB extraction.