The aim of the study, The difficulties of climate change, rapid population growth, and dwindling resources make sustaining, and finding new farming methods, imperative. Using precision agriculture, they designed an integrated PA model which employs weather (rain and temperature), farm (sowing and irrigation), and agricultural remote sensing data (soil moisture) to anticipate crop yields and optimize resource use. Through agro-meteorological, remote sensing, and farm-level data integrations and model optimizations, weather factors and farming techniques are accurately predicted. Compliance of spatiotemporal data analysis and machine learning and deep learning methods (including regression, random forest, gradient boosting, and neural networks) resulted to optimal performance. An integrated model yields RMSE of 0.55, MAE of 0.42, and R2 of 0.89, which is significantly better than single source methods. An analysis of feature importance identified integrated rainfall, and NDVI predictors, with soil moisture, temperature, and fertilizers as supporting predictors. Independent of the framework, agricultural stakeholders, policymakers, and farmers can utilize these results to strengthen food security and enhance agricultural resiliency, as evidenced by the marginally deviated predicted and observed yields.