Planting and mowing cover crops as livestock feed to synergistically optimize soil properties, economic profit, and environmental burden on pear orchards in the Yangtze River Basin.

BACKGROUND: Pears, as an important cash crop, are currently facing great issues due to unsustainable management practices. Cover cropping is a sustainable management strategy that can improve soil fertility and increase fruit yield, while it may also stimulate greenhouse gas emissions. Therefore, synergizing multiple indicators to achieve sustainable development is critical. This study introduces a new management system, namely the planting and mowing of ryegrass as a livestock feed system (PRSS), and analyzes its impact on soil quality, economic benefits, and environmental burdens. RESULTS: Our results indicated that PRSS could increase soil pH from 5.08 to 5.48 and decrease the content of soil alkali-hydrolyzable nitrogen, total phosphate, and available phosphate (26.96-59.89%) while also enhancing yield (+38.51%) compared with the traditional natural grass management system (TMS). The average soil methane fluxes in PRSS were 72.67 µg m-2 day-1 , higher than those of TMS (61.28 µg m-2 day-1 ). However, the gross primary production was lower than TMS (-37.24%), and no significant difference was observed in soil nitrous oxide fluxes. In different scenarios, the total profit of PRSS mode 1 (mowing ryegrass and selling to a livestock company) and PRSS mode 2 (mowing ryegrass and feeding own sheep) were 10 706.21 $ ha-1 and 26 592.87 $ ha-1 respectively. These values are respectively2.36 times and 5.85 times higher than that of TMS. The total global warming potential of TMS (18.19 t CO2 -eq ha-1 ) was 1.29 t CO2 -eq ha-1 higher and 2.89 t CO2 -eq ha-1 lower than that of PRSS mode 1 and mode 2 respectively. CONCLUSION: Compared with traditional natural grass, planting and mowing ryegrass in pear orchards can optimize soil properties, increase fruit yield, and reduce global warming potential. Different modes can greatly increase revenue but have varying impacts on environmental burdens. These findings can help rebuild the links between farmland and specialized livestock production, contributing to sustainable development in the pear industries. © 2023 Society of Chemical Industry.

Sustainable strategies related to soil fertility, economic benefit, and environmental impact on pear orchards at the farmer scale in the Yangtze River Basin, China.

Pears are an important income source in China, and unreasonable management practices have had a negative impact on the sustainability of pear orchards. However, multi-objective synergistic strategies are unclear on a farmer scale. In this study, we quantified indicators of soil fertility (soil organic matter (SOM)), environmental impact (global warming potentials (GWP)), and economic benefit (ratio of benefit and cost (BCR)) and analysed the synergetic strategies based on survey data from 230 smallholders in the Yangtze River Basin (Shanghai City, Chongqing City, Zhejiang province, and Jiangxi province). The average SOM, GWP, and BCR were 28.9 g kg-1, 17.3 t CO2-eq ha-1, and 3.63, respectively. Furthermore, optimised solutions using the Pareto multiple-objective optimisation model can reduce the GWP by 44.6% and improve the SOM and BCR by 34.4% and 43.9%, respectively, when fertiliser N rate and density are both decreased and the ratio of organic fertiliser application is increased compared to farmer management practices. The structural equation model indicated that planting density and fertiliser N rate can directly influence GWP and indirectly increase SOM and BCR; organic fertiliser application directly affects the GWP, SOM, and BCR. Our research provides a bottom-up approach based on the farmer scale, which can improve the sustainability of pear systems, and these findings can be used as guidelines for policymakers and pear orchard managers.

Automatic classification of heterogeneous slit-illumination images using an ensemble of cost-sensitive convolutional neural networks.

BACKGROUND: Lens opacity seriously affects the visual development of infants. Slit-illumination images play an irreplaceable role in lens opacity detection; however, these images exhibited varied phenotypes with severe heterogeneity and complexity, particularly among pediatric cataracts. Therefore, it is urgently needed to explore an effective computer-aided method to automatically diagnose heterogeneous lens opacity and to provide appropriate treatment recommendations in a timely manner. METHODS: We integrated three different deep learning networks and a cost-sensitive method into an ensemble learning architecture, and then proposed an effective model called CCNN-Ensemble [ensemble of cost-sensitive convolutional neural networks (CNNs)] for automatic lens opacity detection. A total of 470 slit-illumination images of pediatric cataracts were used for training and comparison between the CCNN-Ensemble model and conventional methods. Finally, we used two external datasets (132 independent test images and 79 Internet-based images) to further evaluate the model's generalizability and effectiveness. RESULTS: Experimental results and comparative analyses demonstrated that the proposed method was superior to conventional approaches and provided clinically meaningful performance in terms of three grading indices of lens opacity: area (specificity and sensitivity; 92.00% and 92.31%), density (93.85% and 91.43%) and opacity location (95.25% and 89.29%). Furthermore, the comparable performance on the independent testing dataset and the internet-based images verified the effectiveness and generalizability of the model. Finally, we developed and implemented a website-based automatic diagnosis software for pediatric cataract grading diagnosis in ophthalmology clinics. CONCLUSIONS: The CCNN-Ensemble method demonstrates higher specificity and sensitivity than conventional methods on multi-source datasets. This study provides a practical strategy for heterogeneous lens opacity diagnosis and has the potential to be applied to the analysis of other medical images.