Advanced Machine Learning Framework for Robust Crop Yield Prediction Under Extreme Climatic Conditions Using Historical and Weather Data

In many nations, agriculture is essential to both economic expansion and food security.Crop yield prediction is a crucial field of study that aids government agencies, researchers, and farmers in making better agricultural decisions.Manual estimation, historical assumptions, and simple statistical analysis are the main components of traditional crop output forecasting.Extreme weather circumstances like droughts, floods, erratic rainfall, and temperature swings frequently render these techniques useless.Agricultural productivity is becoming more unpredictable due to climate change, which causes crop losses and financial instability for farmers.Using historical agricultural and meteorological data, this study suggests a Robust Crop Yield Prediction Model based on an advanced machine learning architecture.In order to accurately estimate agricultural yield, the suggested method analyses crop production patterns and environmental variables using artificial intelligence and machine learning techniques.Rainfall, temperature, humidity, soil fertility, pesticide and fertiliser use, crop type, and seasonal data are just a few of the variables that the system gathers data on.Machine learning methods like Random Forest, Decision Tree, and Linear Regression models are used to pre-process and test these parameters.By finding hidden links and patterns in agricultural data, the suggested framework can make sensible predictions even in harsh weather.