Meteorological Data and Pesticide Usage for Crop Yield Prediction Using Machine Learning

Global food security is seriously threatened by the agriculture sector's increased susceptibility to the negative effects of climate change and overuse of pesticides.Predicting crop yields accurately is crucial for reducing these risks and disseminating knowledge about sustainable farming methods.Using a year's worth of weather data, pesticide records, agricultural yield data, and machine learning algorithms, this study introduces a revolutionary crop yield forecast system.After using exacting techniques to collect, purify, and improve the data, we trained and assessed four machine learning models: XGBoost manages structured data, whereas LSTM records temporal weather trends.Spatial dependencies are analyzed using GNNs, whereas CatBoost handles categorical data.LSTM-XGBoost performs better than conventional models (Gradient Boosting, KNN) and is evaluated using cross-validation with an R2 score.The system achieves higher R2 score and lower RMSE for improved prediction accuracy.This research also examined the correlation between projected and actual crop yields and identified the ideal meteorological conditions.It paves the way for data-driven methods in sustainable agriculture and resource distribution, ultimately leading to a more secure future with respect to food availability and resilience to climate change.