Search

Under complex field conditions, robust and efficient boll detection at maturity is an important tool for pre-harvest strategy and yield prediction. To achieve automatic detection and counting of long-staple cotton in a natural environment, this paper proposes an improved algorithm incorporating deformable convolution and attention mechanism, called YOLO-C, based on YOLOv7: (1) To capture more detailed and localized features in the image, part of the 3 × 3 convolution in the ELAN layer of the backbone is replaced by deformable convolution to improve the expressiveness and accuracy of the model. (2) To suppress irrelevant information, three SENet modules are introduced after the backbone to improve the ability of feature maps to express information, and CBAM and CA are introduced for comparison experiments. (3) A WIoU loss function based on a dynamic non-monotonic focusing mechanism is established to reduce the harmful gradients generated by low-quality examples on the original loss function and improve the model performance. During the model evaluation, the model is compared with other YOLO series and mainstream detection algorithms, and the model mAP@0.5 achieves 97.19%, which is 1.6% better than the YOLOv7 algorithm. In the model testing session, the root mean square error and coefficient of determination (R2) of YOLO-C are 1.88 and 0.96, respectively, indicating that YOLO-C has higher robustness and reliability for boll target detection in complex environments and can provide an effective method for yield prediction of long-staple cotton at maturity.

The aim of this study was to microencapsulate probiotic bacteria (Lactobacillus acidophilus 11073) using whey-protein-isolate (WPI)–octenyl-succinic-anhydride-starch (OSA-starch)-complex coacervates and to investigate the effects on probiotic bacterial viability during spray drying, simulated gastrointestinal digestion, thermal treatment and long-term storage. The optimum mixing ratio and pH for the preparation of WPI-OSA-starch-complex coacervates were determined to be 2:1 and 4.0, respectively. The combination of WPI and OSA starch under these conditions produced microcapsules with smoother surfaces and more compact structures than WPI-OSA starch alone, due to the electrostatic attraction between WPI and OSA starch. As a result, WPI-OSA-starch microcapsules showed significantly (p < 0.05) higher viability (95.94 ± 1.64%) after spray drying and significantly (p < 0.05) better protection during simulated gastrointestinal digestion, heating (65 °C/30 min and 75 °C/10 min) and storage (4/25 °C for 12 weeks) than WPI-OSA-starch microcapsules. These results demonstrated that WPI-OSA-starch-complex coacervates have excellent potential as a novel wall material for probiotic microencapsulation.

The Haihe River basin of North China is characterized by extremely low per capita water resources and a consistently long-term decreasing trend of precipitation and runoff over the last few decades. This study analyzes the climatological features of rainy season (May−September) precipitation in the Haihe River basin and its branch systems based on a high-density hourly observational dataset during 2007−2017. We show that there are two high-rainfall zones in the basin, with one along the south of the Yanshan Mountains to Taihang Mountains and another along the Tuma River in the south. Rainstorm centers exist amidst the two zones. July generally sees the highest precipitation, followed by August, and May has the lowest precipitation. The major flood season is reached between the third pentad of July and the fourth pentad of August. The precipitation is high at night but low in the daytime. In the pre-flood season before early July, rainfalls mostly arrive at 16:00−21:00 h. After entering the major flood season, the diurnal precipitation has two peaks, one at 17:00−22:00 h and the other at 0:00−7:00 h. In the post-flood season after mid-August, the most rain occurs at night, with the peak appearing at 0:00−8:00 h. The short-duration precipitation is mainly distributed in the mountainous areas, and the long-duration precipitation that contributes most to seasonal rainfalls appears in the plain areas, and the continuous precipitation mostly occurs in the windward slopes of the Taihang Mountains and the Yanshan Mountains. In addition, urbanization process around large city stations may have affected the rainy season precipitation to a certain extent in the Haihe River basin, with large and medium city stations experiencing around 10% higher precipitation than small city stations. However, this issue needs to be investigated exclusively.