Search

Global climate change and socio-economic development have led to a shortage of water and labour resources, which has had a significant impact on rice cultivation. In this study, the application of micro-ridge-furrow planting technology and degradable film mulching in dry direct-seeded rice was investigated to address the factors restricting the development of the rice industry and reduce the impact of rice production on the environment. The effects of a micro-ridge-furrow planting pattern and degradable film mulching on soil temperature, seedling growth, and yield of dry direct-seeded rice in a semiarid region of China were studied through three field experiments: micro-ridge-furrow mulching with traditional plastic film (T1); micro-ridge-furrow mulching with degradable film (T2); and traditional flat-cropping mulching with traditional plastic film (CK). The experimental results demonstrated that the micro-ridge-furrow mulching film planting pattern promoted the germination of rice seeds and improved the soil temperature, plant height, leaf area, dry mass, and grain yield. T2 had the highest average soil temperature (14.68–17.83 ℃ during the day; 14.4–15.74 ℃ at night), leaf area (41.85 cm2 plant−1), root dry mass (45.32 mg plant−1), shoot dry mass (58.46 mg plant−1), root–shoot ratio (0.821), and yield (8.112 t ha−1). In summary, the micro-ridge-furrow mulching with degradable film (T2) is recommended as an efficient planting and mulching pattern for sustainably solving environmental problems and improving grain yield in semiarid regions of China. [ABSTRACT FROM AUTHOR]

The brown rice planthopper (Nilaparvata lugens Stal) is one of the main pests of rice. The rapid and accurate detection of brown rice planthoppers (BRPH) can help treat rice in time. Due to the small size, large number and complex background of BRPHs, image detection of them is challenging. In this paper, a two-layer detection algorithm based on deep learning technology is proposed to detect them. The algorithm for both layers is the Faster RCNN (regions with CNN features). To effectively utilize the computing resources, different feature extraction networks have been selected for each layer. In addition, the second layer detection network was optimized to improve the final detection performance. The detection results of the two-layer detection algorithm were compared with the detection results of the single-layer detection algorithm. The detection results of the two-layer detection algorithm for detecting different populations and numbers of BRPHs were tested, and the test results were compared with YOLO v3, a deep learning target detection network. The test results show that the detection results of the two-layer detection algorithm were significantly better than those of the single-layer detection algorithm. In the tests for different numbers of BRPHs, the average recall rate of this algorithm was 81.92%, and the average accuracy was 94.64%; meanwhile, the average recall rate of YOLO v3 was 57.12%, and the average accuracy rate was 97.36%. In the experiment with different ages of BRPHs, the average recall rate of the algorithm was 87.67%, and the average accuracy rate was 92.92%. In comparison, for the YOLO v3, the average recall rate was 49.60%, and the average accuracy rate was 96.48%. [ABSTRACT FROM AUTHOR]