<![CDATA[The production of coffee in Indonesia, particularly in Lampung, plays a crucial role in both the local and national coffee sectors. Weather plays a crucial role in the development of coffee trees. Nonetheless, the coffee production is frequently hindered by unpredictable weather conditions. This can be foreseen through the use of scientific forecasting. Blending agriculture and science can maximize coffee production and effective resource utilization. This study creates a predictive model for coffee production by combining machine learning methods with the NASA POWER dataset. Data from NASA POWER is used to acquire information on various weather factors that impact the growth of coffee trees, including solar radiation, temperature, humidity, pressure, soil wetness, and wind speed. Additionally, information on coffee production is sourced from BPS-Statistics Indonesia. The Random Forest algorithm is used to model the connection between variables. The study findings demonstrate that combining machine learning with remote sensing can offer an effective model. Assessment of the R2, RMSE, and MSE figures shows satisfactory results, though not flawless. This happens due to external factors beyond the weather that influence coffee cultivation. The combination of machine learning and remote sensing is incorporated into a website. This model has the potential to be transformed into an app that offers precise details on coffee cultivation in Lampung. This research highlights how remote sensing data can offer insights into predicting sustainable agriculture outcomes.]]>
