Agriculture plays a crucial role in Maharashtra’s economy, but climate change significantly affects crop productivity. Machine learning offers a powerful solution for predicting crop production and analysing the impact of climate on agriculture. This study utilises key environmental and agricultural parameters, including temperature, humidity, precipitation, wind speed, cultivated area, and production data, to develop predictive models. Using KNN, Linear Regression, Decision Trees, Random Forest, and Gradient Boosting algorithms, we aim to forecast crop production. The crops under study are Rice, Bajra, Cotton, Sugarcane and Wheat. District-wise data was collected and organised month-wise according to each crop’s growing season to ensure seasonally accurate prediction. This study supports flexible decision-making in agriculture by incorporating precision farming techniques. This lets farmers boost productivity and reduce risks. The results of this study will help develop sustainable farming practices, which provide better resource management and higher agricultural output.