Tomato leaf disease detection based on attention mechanism and multi-scale feature fusion.

When detecting tomato leaf diseases in natural environments, factors such as changes in lighting, occlusion, and the small size of leaf lesions pose challenges to detection accuracy. Therefore, this study proposes a tomato leaf disease detection method based on attention mechanisms and multi-scale feature fusion. Firstly, the Convolutional Block Attention Module (CBAM) is introduced into the backbone feature extraction network to enhance the ability to extract lesion features and suppress the effects of environmental interference. Secondly, shallow feature maps are introduced into the re-parameterized generalized feature pyramid network (RepGFPN), constructing a new multi-scale re-parameterized generalized feature fusion module (BiRepGFPN) to enhance feature fusion expression and improve the localization ability for small lesion features. Finally, the BiRepGFPN replaces the Path Aggregation Feature Pyramid Network (PAFPN) in the YOLOv6 model to achieve effective fusion of deep semantic and shallow spatial information. Experimental results indicate that, when evaluated on the publicly available PlantDoc dataset, the model's mean average precision (mAP) showed improvements of 7.7%, 11.8%, 3.4%, 5.7%, 4.3%, and 2.6% compared to YOLOX, YOLOv5, YOLOv6, YOLOv6-s, YOLOv7, and YOLOv8, respectively. When evaluated on the tomato leaf disease dataset, the model demonstrated a precision of 92.9%, a recall rate of 95.2%, an F1 score of 94.0%, and a mean average precision (mAP) of 93.8%, showing improvements of 2.3%, 4.0%, 3.1%, and 2.7% respectively compared to the baseline model. These results indicate that the proposed detection method possesses significant detection performance and generalization capabilities.

An evolution perspective on the urban land carrying capacity in the urbanization era of China.

The past few decades witness a typical urbanization era in large developing countries such as China. In line with the urbanization process, land resources have inevitably presented a series of changes. The evolution of urban land carrying capacity (ULCC) is appreciated as a yardstick for guiding towards sustainable urban development. This paper therefore proposes an alternative method from carrier-load perspective for investigating the evolution of ULCC performance in China during the rapid urbanization era of 2012-2017. The data employed for analysis is collected from 290 Chinese prefectural-level cities. Results indicate that ULCC performance in the urbanizing China has been evolving towards a better state, for which 94% of the surveyed cities have made progress. However, significant disparity exists between cities on ULCC evolution performance, in particular, mega cities tend to have better ULCC evolution performance. Some cities may have better evolution performance although they have a poor average ULCC value. Contrarily, some cities may present poor evolution performance but they carry a better average ULCC value. The research findings provide valuable references not only for policy-makers to better understand the state of ULCC across the country, and appreciate inspiring experiences and lessons for implementing effective tailor-made measures to improve the ULCC performance, but also for enriching the literature in land resource management.