Mathematical Modelling of Post Flowering Stalk Rot (PFSR)Spread and Intervention Strategies for Optimal Control in Maize Production

Abstract

Maize diseases such as Post Flowering Stalk Rot (PFSR) have a substantial influence on global food security and economic stability. Mathematical modelling can help determine effective disease-prevention methods. This work creates a compartmental model to mimic PFSR spread by including weather, soil moisture, and crop management. We assess the effectiveness of intervention techniques such as fungicide use, crop rotation, and resistant cultivar adoption. ML can help boost agricultural output through combating plant diseases and climate change. The traditional image processing techniques developed for disease detection suffer from low robustness and generalisability. Fine-grained maize plant disease classification is a challenging task due to the disease patterns' delicate and nuanced nature. We determine which of these four specialized machine learning frameworks has the highest validation accuracy, precision, and recall. It indicates the superiority and effectiveness of the proposed methodology.Our Article presents a fresh approach  for reliable classification  concerning any disease  occurring with a  maize plants.