The Development of a Real-Time Disease Prediction Model through Big Data-based Analysis of Crop-Pathogen-Environment Interactions

This paper presents a method for developing a real-time disease prediction model for major economic crops using big data analytics. By integrating genomic and phenomics data with climate change variables, we analyzed the interactions between crops, pathogens, and environmental factors. A comprehensive disease prediction system was established based on this analysis. Various machine learning algorithms were employed to ensure effective feature selection and analysis, considering both temporal and spatial factors. This research not only focuses on developing the predictive model but also emphasizes its practical applications and challenges in real-world agricultural settings. With climate change posing increasing threats to food security, the relevance of such predictive systems is becoming ever more crucial.