Optimizing Crop Yield Predictions Using K-Nearest Neighbors Regression: An Analysis of Temperature, Rainfall and Soil pH Influences

This study focuses on developing a predictive model for crop production using the K-nearest neighbors (KNN) regression algorithm. Key variables like temperature, rainfall, and soil pH are analyzed, with the dataset including features such as rainfall, temperature, pH levels, and crop production specific to a region. The KNN regression model was trained and tested on this dataset, and its performance was assessed using metrics like the R² score, mean absolute error (MAE), and median absolute error (MedAE). Results indicate that the KNN regression model demonstrates significant potential for predicting crop production, achieving a high R² score and low MAE and MedAE values. This suggests its utility in agricultural applications, such as assisting farmers and policymakers in estimating crop yields based on environmental conditions. However, further investigation is required to assess the model's generalizability and explore additional ways it can enhance decision-making in the agricultural sector.