Concrete cracks have always been the focus of research because of the serious damage they cause to structures. With the updating of hardware and algorithms, the detection of concrete structure surface cracks based on computer vision has received extensive attention. This paper proposes an improved algorithm based on the open-source model Deeplabv3+ and names it Deeplabv3+ BDF according to the optimization strategy used. Deeplabv3+ BDF first replaces the original backbone Xception with MobileNetv2 and further replaces all standard convolutions with depthwise separable convolutions (DSC) to achieve a light weight. The feature map of a shallow convolution layer is additionally fused to improve the detail segmentation effect. A new strategy is proposed, which is different from the two-stage training. The model training is carried out in the order of transfer learning, coarse-annotation training and fine-annotation training. The comparative test results show that Deeplabv3+ BDF showed good performance in the validation set and achieved the highest mIoU and detection efficiency, reaching real-time and accurate detection.

Changes in irrigation water-use efficiency are related closely to agricultural development. Clarifying the driving factors of irrigation water-use efficiency change at different agricultural development stages is beneficial for buffering the contradiction between the protection of water resources and massive agricultural water consumption. It also has theoretical and application value when it comes to elucidating the driving characteristics of spatial changes in irrigation water-use efficiency observed among the different provinces of China. This paper analyzes driving factors of irrigation water-use change based on a study of literature and a field survey. It selects 21 indices from five aspects of climatic change, resource endowment, economic situation, technological level, and management mode as the system of driving factors for irrigation water-use change. This article then uses statistical data on economic and social development in the 31 provinces of China in 2009, and applies the principal component analysis (PCA) method to extract the main driving factors affecting irrigation water-use efficiency change. After calculation of factor scores, clustering analysis is conducted on the 31 provinces to explore regional differences among the driving factors of irrigation water-use efficiency change. The results show that these can be attributed to the factors of agricultural economic development, water-saving irrigation technology, water resource endowment, and dissipation. The 31 provinces can be divided into five types: agricultural economy strong driving type; agricultural economy dominant type; industrial economy dominant type; agriculture strong development type; and coordinated driving type. In highly agricultural provinces, mature irrigation district management and water-saving measures influence the efficiency of irrigation water-use, making these strong positive driving factors. In highly industrial provinces, changes in irrigation water-use efficiency are mainly driven by economic development and structural adjustment, making these weak driving factors.

A simple formula is proposed to predict the vertical distribution of a suspended load concentration in a 2D steady turbulent flow. The proposed formula significantly improves the well-known Rouse...