Precise estimation of crop phenology is vital for optimizing farming practices and irrigation scheduling. Conventional methods often involve expensive equipment and high operational costs, making them less feasible for large-scale applications. To address this challenge, we applied a remote sensing-based approach to assess the spatial distribution of crop coefficients in the semi-arid region of Western Rajasthan, India. Leveraging the well-established Surface Energy Balance for Land (SEBAL) model, we integrated multispectral Landsat 8 imagery with the FAO Penman-Monteith (PM) method to generate crop coefficient distributions across farmlands. The entire process was executed on the cloud-based Google Earth Engine (GEE) platform, allowing for efficient and scalable analysis. Our results revealed a strong correlation between fluctuations in crop coefficients and changes in the Normalized Difference Vegetation Index (NDVI). Moreover, an inverse relationship was observed between NDVI and Land Surface Temperature (LST). Notably, the proposed approach yielded satisfactory results, filling the gap in practical and affordable tools for crop health monitoring and growth assessment. The SEBAL algorithm demonstrated high accuracy in predicting crop stress conditions, eliminating the need for soil and sub-soil characteristic information. Overall, our findings provide a cost-effective solution for farmers and administrators to monitor crop phenology at different spatial and temporal intervals, facilitating informed decision-making in agricultural management.