A deep neural network-based decision support system for intelligent geospatial data analysis in intelligent agriculture system

A Deep Learning-Based Decision Support Tool for Plant-Parasitic Nematode Management

Plant-parasitic nematodes (PPN), especially sedentary endoparasitic nematodes like root-knot nematodes (RKN), pose a significant threat to major crops and vegetables. They are responsible for causing substantial yield losses, leading to economic consequences, and impacting the global food supply. The identification of PPNs and the assessment of their population is a tedious and time-consuming task. This study developed a state-of-the-art deep learning model-based decision support tool to detect and estimate the nematode population. The decision support tool is integrated with the fast inferencing YOLOv5 model and used pretrained nematode weight to detect plant-parasitic nematodes (juveniles) and eggs. The performance of the YOLOv5-640 model at detecting RKN eggs was as follows: precision = 0.992; recall = 0.959; F1-score = 0.975; and mAP = 0.979. YOLOv5-640 was able to detect RKN eggs with an inference time of 3.9 milliseconds, which is faster compared to other detection methods. The deep learning framework was integrated into a user-friendly web application system to build a fast and reliable prototype nematode decision support tool (NemDST). The NemDST facilitates farmers/growers to input image data, assess the nematode population, track the population growths, and recommend immediate actions necessary to control nematode infestation. This tool has the potential for rapid assessment of the nematode population to minimise crop yield losses and enhance financial outcomes.

Dynamic Linkages among Climate Change, Mechanization and Agricultural Carbon Emissions in Rural China

Climate change has become a major environmental issue facing all countries, having a significant effect on all aspects of agricultural production, such as the agricultural mechanization process and fertilizer use. Greenhouse gases produced by agricultural machinery and fertilizers during agricultural production are an important cause of climate change. On the basis of the above facts, researching the connection between agricultural mechanization, climate change, and agricultural carbon emissions is crucial for the development of low-carbon agriculture and for addressing climate change. We used a variety of econometric models and methods to analyze data from China's multiple provinces (cities) covering the years 2000 through 2019, in order to meet the research objectives. Furthermore, we utilized rainfall and sunlight as variables to assess climate change and adopted Granger tests to establish the link between rainfall, sunlight, agricultural mechanization, and carbon emissions in farming. The findings indicate a bidirectional causality relationship between rainfall, sunlight, agricultural mechanization, and carbon emissions in farming. Rainfall and sunlight are Granger causes of agricultural mechanization. Furthermore, agricultural mechanization has favorable effects on carbon emissions of agriculture, and climate change has long-term implications on agricultural mechanization and carbon emissions of agriculture. Finally, this paper investigated the green path suitable for the low-carbon development of Chinese agriculture, arguing that the government should formulate low-carbon agricultural policies by region and actively promote the upgrading of agricultural machinery.