Implementation of the K-Nearest Neighbors Algorithm in the AgroWeather System for Plant Recommendations Based on Weather Predictions

This study aims to develop an accurate weather prediction model that can be applied using the K-Nearest Neighbor (KNN) method to make it easier for the community, especially farmers, to know the weather in the future and to match plants that must be planted in certain seasons in Bandung Regency. Rising temperatures and climate change occurring in Bandung, West Java, have a significant impact on rice cultivation and agricultural production. With reliable weather predictions, farmers can avoid the risks associated with growing crops that are not suited to the weather conditions, such as pest attacks, plant diseases, and crop failure. The KNN method is a useful approach to predicting weather conditions based on historical data. The results of this research can help farmers or agricultural experts determine suitable plants to plant based on weather forecasts. The targeted output is a weather prediction model that can be integrated into an agricultural information system in Bandung Regency. This model has an accuracy rate of 90& in providing farmers with relevant information for the coming season and updates regarding weather conditions. In addition, this model also provides plant type recommendations with an accuracy rate of 85&. These recommendations are based on an analysis of historical data on crops that have done well in each previous season.