Weather Forcast Optimization Using Learning Vector Quantization Methods with Genetic Algorithms

Abstract

Weather forecasting is one of the important factors in daily life, as it can affect the activities carried out by the community. The study was conducted to optimize weather forecasts using artificial neural network methods. The artificial neural network used is a learning vector quantization (LVQ) methods and genetics algorithms (GA). BMKG weather data was originally modeled using the LVQ method, then also created the LVQ Method Optimization weather forecast model using GA. Data attributes consist of numeric and categoric. Numeric attributes as input parameters are: temperature, evaporation, sunlight, humidity and rainvol. While the categorical attributes are ourput from weather forecasts include: Cloudly (C), Partly Cloudly (PC), Sunny (S), Rain (R) and Cloudly rain (CR). Sample data used is 1096 data. Both models were tested so that they obtained 72% accuracy results for weather forecast models using the LVQ method and 73% of the weather forecast accuracy results that were optimized using GA. The results have not achieved the most optimal results because it turns out that citeko region weather data is not suitable for use in both methods. Because the data has an imbalance in the amount of data per class.