Pests and diseases are an inevitable problem in agricultural production, causing substantial economic losses yearly. The application of convolutional neural networks to the intelligent recognition of crop pest images has become increasingly popular due to advances in deep learning methods and the rise of large-scale datasets. However, the diversity and complexity of pest samples, the size of sample images, and the number of examples all directly affect the performance of convolutional neural networks. Therefore, we designed a new target-detection framework based on Cascade RCNN (Regions with CNN features), aiming to solve the problems of large image size, many pest types, and small and unbalanced numbers of samples in pest sample datasets. Specifically, this study performed data enhancement on the original samples to solve the problem of a small and unbalanced number of examples in the dataset and developed a sliding window cropping method, which could increase the perceptual field to learn sample features more accurately and in more detail without changing the original image size. Secondly, combining the attention mechanism with the FPN (Feature Pyramid Networks) layer enabled the model to learn sample features that were more important for the current task from both channel and space aspects. Compared with the current popular target-detection frameworks, the average precision value of our model (mAP@0.5) was 84.16%, the value of (mAP@0.5:0.95) was 65.23%, the precision was 67.79%, and the F1 score was 82.34%. The experiments showed that our model solved the problem of convolutional neural networks being challenging to use because of the wide variety of pest types, the large size of sample images, and the difficulty of identifying tiny pests.

In the context of black smelly rivers and urban pollution control, heavy metal pollution of river sediments has attracted widespread attention. Heavy metals can accumulate in the sediment through hydrolysis and complexation, and cause secondary pollution through diffusion and migration. River animals play an important role in river ecosystems, and their feeding, excretion and disturbance activities can have a significant impact on the transport and transformation of heavy metals in the sediment. This paper investigates the effects of river animals on the transport and transformation of Zn, typical heavy metals in the sediment, and evaluates the contamination and risk of the sediment and river animals before and after the experiment.

This study reports, for the first time, a stable and reproducible semi-continuous bioprocess for the sustained production of poly(3-hydroxybutyrate-co-3-hydroxyvalerate) (PHBV) over 98 days, corresponding to 7 consecutive operational repetitions. The process was operated under non-sterile conditions using a cyanobacteria-dominated microbiome and employed acetate and valerate supplementation. Throughout the operation, a consistent 3-hydroxyvalerate (3HV) molar fraction of 8-12.2 mol% was maintained, with a maximum polymer content of 17.9% of dry cell weight. Notably, reducing the valerate concentration from 100 to 50 mg·L-1 did not compromise PHBV production, indicating a robust metabolic adaptation of the microbial consortium and highlighting the potential for substrate optimization. Microbial community analysis revealed a strong dominance of Synechocystis sp. (>95%) over Synechococcus sp. (<5%), with the consortium exhibiting high resilience to cyclic hypoxic conditions. Transmission electron microscopy, in combination with Nile blue staining, confirmed the intracellular accumulation of PHBV granules within the microbial cells. Thermal characterization further demonstrated the formation of semi-crystalline PHBV, with characteristic melting transitions spanning 147.41-169.77 °C. Overall, this work demonstrates a robust, scalable biological platform for the continuous production of PHBV with controlled composition and stable thermal properties, thereby contributing to the development of sustainable biopolymer production processes.