A Comparative Investigation of Machine Learning Algorithms For Crop Yield Forecast And Agricultural Optimization

In this study, crop yield forecast is studied by machine-learning methods with respect to accuracy and reliability. Using algorithms like Decision Trees, Random Forests, Support Vector Machines (SVM), Neural Networks, XGBoost, and LightGBM the research scatters environmental elements, for instance rainfall, temperature, type of soil, and agriculture, for example fertilizer and irrigation utilization. With highest performance of key metrics like accurateness, exactness, recall and F1 score, Random Forest model made itself the best model capable of doing complex, nonlinear data relationship. The rainfall and irrigation frequency were found to be the two factors that affect the crop yield significantly using statistical tests such as ANOVA and Chi Square. This suggests that machine learning is a viable means towards improving the productivity of the agricultural resource. The inputs from the study can serve to guide farmers, agricultural policymakers and stakeholders in implementing data based sustainable farming strategies for better food security. © 2026 selection and editorial matter, Pushpa Choudhary, Sambit Satpathy, Arvind Dagur and Dhirendra Kumar Shukla; individual chapters, the contributors