The You Only Look Once (YOLO) series algorithms have been widely adopted in concrete crack detection, with attention mechanisms frequently being incorporated to enhance recognition accuracy and efficiency. However, existing research is confronted by two primary challenges: the suboptimal performance of attention mechanism modules and the lack of explanation regarding how these mechanisms influence the model’s decision-making process to improve accuracy. To address these issues, a novel Dynamic Efficient Channel Attention (DECA) module is proposed in this study, which is designed to enhance the performance of the YOLOv10 model in concrete crack detection, and the effectiveness of this module is visually demonstrated through the application of interpretable analysis algorithms. In this paper, a concrete dataset with a complex background is used. Experimental results indicate that the DECA module significantly improves the model’s accuracy in crack localization and the detection of discontinuous cracks, outperforming the existing Efficient Channel Attention (ECA). When compared to the similarly sized YOLOv10n model, the proposed YOLOv10-DECA model demonstrates improvements of 4.40%, 3.06%, 4.48%, and 5.56% in precision, recall, mAP50, and mAP50-95 metrics, respectively. Moreover, even when compared with the larger YOLOv10s model, these performance indicators are increased by 2.00%, 0.04%, 2.27%, and 1.12%, respectively. In terms of speed evaluation, owing to the lightweight design of the DECA module, the YOLOv10-DECA model achieves an inference speed of 78 frames per second, which is 2.5 times faster than YOLOv10s, thereby fully meeting the requirements for real-time detection. These results demonstrate that an optimized balance between accuracy and speed in concrete crack detection tasks has been achieved by the YOLOv10-DECA model. Consequently, this study provides valuable insights for future research and applications in this field.

The Huaihe River Basin (HRB) is an important water system in eastern China, and its water quality has received widespread attention. This study explored the latest spatial variation patterns of surface water quality in the HRB to cope with the increasingly severe challenges of water resource management. By integrating multidimensional water quality data from surface water monitoring stations, including dissolved oxygen (DO), chemical oxygen demand (COD_Mn and COD), biochemical oxygen demand (BOD₅), ammonia nitrogen (NH₃–N), total phosphorus (TP), and total nitrogen (TN), this study utilized a cluster analysis technique to categorize the water quality data and reveal changes in the geographic variability of water quality. Among the 382 monitoring stations in the HRB, 258 stations had TN content lower than Class V, which was the highest among all monitoring indicators. The entropy weight method used to assess the comprehensive water quality showed that there were 157 and 163 monitoring stations belonging to Class III and IV, respectively, and stations with poor water quality were distributed downstream in the river network and estuary area. Correlation and cluster analyses indicated that agricultural and organic matter pollution were the two main factors affecting water quality in the HRB, particularly in the downstream area, and the high loading of nutrient salts such as TP and NH₃–N reflected the significant influence of agricultural activities. In addition, the study examined the potential driving role of factors such as topography, geomorphology, and human activities on water quality changes and visualized the relationship between water quality class and cluster categories through spatial distribution maps and Sankey diagrams to clarify the regional patterns of water quality problems.