Development of effective model for non-destructive detection of defective kiwifruit based on graded lines.

The accurate detection of external defects in kiwifruit is an important part of postharvest quality assessment. Previous studies have not considered the problems posed by the actual grading environment. In this study, we designed a novel approach based on improved Yolov5 to achieve real-time and efficient non-destructive detection of multiple defect categories in kiwifruit. First, a kiwifruit image acquisition device based on grading lines was developed to enhance the image acquisition. Subsequently, a kiwifruit dataset was constructed based on the external defect characteristics and a new data enhancement method was proposed to augment the kiwifruit samples. Thereafter, the SPD-Conv and DW-Conv modules were combined to improve Yolov5s, with EIOU as the loss calculation function. The results demonstrated that the improved model training loss value was 0.013 lower, the convergence was accelerated, the number of parameters was reduced, and the computational effort was increased. The detection accuracies of the samples in the test set, which included healthy, leaf-rubbing damaged, healed cuts or scarred, and sunburned samples, were 98.8%, 98.7%, 97.6%, and 95.9%, respectively, with an overall detection accuracy of 97.7%. The detection time was 8.0 ms, thereby meeting real-time sorting demands. The average detection accuracy and model size of SSD, Yolov5s, Yolov7, and Yolov5-Ours were compared. When the confidence threshold was 0.5, the detection accuracy of Yolov5-Ours was 10% and 6.4% higher than that of SSD and Yolov5s, respectively. In terms of the model size, Yolov5-Ours was approximately 6.5- and 4-fold smaller than SSD and Yolov7, respectively. Thus, Yolov5-Ours achieved the highest accuracy, adaptability, and robustness for the detection of all kiwifruit categories as well as a small volume and portability. These results can provide technical support for the non-destructive detection and grading of agricultural products in the future.

Quantitative discrimination of algae multi-impacts on N2O emissions in eutrophic lakes: Implications for N2O budgets and mitigation.

It is generally accepted that eutrophic lakes significantly contribute to nitrous oxide (N2O) emissions. However, how these emissions are affected by the formation, disappearance, and mechanisms of algal blooms in these lakes has not been systematically investigated. This study examined and determined the relative contribution of spatiotemporal N2O production pathways in hypereutrophic Lake Taihu. Synchronously, the multi-impacts of algae on N2O production and release potential were measured in the field and in microcosms using isotope ratios of oxygen (δ18O) and bulk nitrogen (δ15N) to N2O and to intramolecular 15N site preference (SP). Results showed that N2O production in Lake Taihu was derived from microbial effects (nitrification and incomplete denitrification) and water air exchanges. N2O production was also affected by the N2O reduction process. The mean dissolved N2O concentrations in the water column during the pre-outbreak, outbreak, and decay stages of algae accumulation were almost the same (0.05 µmol·L-1), which was 2-10 times higher than in lake areas algae was not accumulating. However, except for the central lake area, all surveyed areas (with and without accumulated algae) displayed strong release potential and acted as the emission source because of dissolved N2O supersaturation in the water column. The mean N2O release fluxes during the pre-outbreak, outbreak, and decay stages of algae accumulation areas were 17.95, 26.36, and 79.32 µmol·m-2·d-1, respectively, which were 2.0-7.5 times higher than the values in the non-algae accumulation areas. In addition, the decay and decomposition of algae released large amounts of nutrients and changed the physiochemical properties of the water column. Additionally, the increased algae biomass promoted N2O release and improved the proportion of N2O produced via denitrification process to being 9.8-20.4% microbial-derived N2O. This proportion became higher when the N2O consumption during denitrification was considered as evidenced by isotopic data. However, when the algae biomass was excessive in hypereutrophic state, the algae decomposition also consumed a large amount of oxygen, thus limiting the N2O production due to complete denitrification as well as due to the limited substrate supply of nitrate by nitrification in hypoxic or anoxic conditions. Further, the excessive algae accumulation on the water surface reduced N2O release fluxes via hindering the migration of the dissolved N2O into the atmosphere. These findings provide a new perspective and understanding for accurately evaluating N2O release fluxes driven by algae processes in eutrophic lakes.

Pilot-scale composting of typical multiple agricultural wastes: Parameter optimization and mechanisms.

In this work, pilot-scale (100 kg of mixed wastes each time) composting of typical agricultural wastes, including chicken manure, vegetable leaves and rice husks with a mass ratio of 6:3:1, was studied. Effects of thermal phases and transformation time on performance, including moisture, nutrient, and carbon contents and C/N ratios of compost, were investigated. The optimal parameters were 75 ±â€¯5 °C and 18 h; the compost met the requirements of Chinese National Agricultural Organic Fertilizer Standard (NY525-2012). Mechanisms investigations demonstrated that, Bacillus and Sinibacillus played key roles in degrading high-molecular-weighted organic substances into small-molecular-weighted humic- and fulvic-acid-like matters, resulting in smaller particle size and loose structure of the product; rice husk particles acted as a conditioning agent and remained their originally morphology. The mechanism provided informative guidance for optimizing the process in practical application.