<![CDATA[The Caringin Agricultural Extension Center (BPP) is an institution responsible for providing counseling and guidance to farmers in the Caringin region regarding effective agricultural methods, especially in the food sector. Amid unstable weather changes, farmers in BPP Caringin face uncertainty in weather forecasting that affects their agricultural production. The lack of information from BPP in mitigating the weather increases the risk of farmers because farmers often plant not according to the season.To solve this problem, it requires a system that is able to predict the weather more accurately. The authors in this study used the Adaptive Neuro Fuzzy Inference System (ANFIS) method as an effective solution. By integrating neural networks and fuzzy logic, ANFIS can improve weather forecasting accuracy. The use of PHP software with TensorFlow and Scikit-Fuzzy became a technical solution for efficient ANFIS model development. In addition, to store a data, then use MySQL. Through model training using historical weather data, we hope to provide more reliable weather predictions to support farmers in better decision making. It is hoped that this solution can reduce the risk of losses caused by weather uncertainty for farmers in BPP Caringin.It is hoped that with the implementation of the ANFIS method and the development of more accurate models, farmers in BPP Caringin will reduce the risk of losses due to weather uncertainty. More reliable weather predictions are expected to enable farmers to make informed decisions regarding planting time, crop maintenance, and harvesting. This solution is expected to not only benefit farmers in the region, but also become a foundation for the development of better and wider weather prediction systems, increasing overall agricultural productivity.]]>
