Weather Forecasting Rain Probability in Cebu Using ANFIS and Bayesian Network
Vince Xavier C. Del Rosario, Vhynce Joi Narca, Franz Timothy Jeanne Laconsay, Chris Jordan Alliac · 2021
The necessity of assessing the probability of rain and weather conditions of Cebu City is useful for providing its residents with valuable information for their daily activities. This paper describes the use of the Adaptive Neuro-Fuzzy Inference System (ANFIS) model to provide an estimation for the possibility of rainfall utilizing the following parameters: month (expressed in numerical form), date of the month, minimum temperature reading, maximum temperature reading, mean temperature reading, mean humidity percentage, average wind speed, and mean cloud percentage. The model has an 87.67% accuracy in weather forecasting, where the forecasted weather conditions are used to assess the probability of rain. The study recommends using the weather data set of the recent year, and that a survey on whether rain has occurred within a certain day be performed, as it would prove useful as output for teaching the ANFIS model, rather than relying on the Bayesian network.