The Effect of Number of Factors and Data on Monthly Weather Classification Performance Using Artificial Neural Networks

Abstract

Current weather-related research only focuses on weather prediction based on raw data and the factors used are generally 4 factors: average temperature, solar radiation, air pressure, and wind. In this research, monthly weather prediction is done using 5 factors where the additional factor used is rainfall in the previous time. In contrast to previous prediction research, the prediction process carried out in this study emphasizes the modeling of training data according to the desired prediction model.. These two things distinguish this research from previous studies. The prediction model used in this study is a classification-based prediction model that is the Artificial Neural Network (ANN) method combined with the backpropagation algorithm for calculating the weight of the ANN network. The data used are meteorological data from 2010 to 2018 in the Bogor area, where data from 2010 to 2016 are used as training data, and data from 2017 to 2018 are used as test data. The results of this study indicate that the design of the model with the use of data for 6 years with feature data of 5 factors has an accuracy rate of 83.33%.

Performance Analysis of Hybrid Machine Learning Methods on Imbalanced Data (Rainfall Classification)

“…The results of the accuracy of the ANN method in research [10] using breast cancer data obtained is equal to 86.95% by applying 10 neurons to the input layer, sigmoid function, and 1 hidden layer. Research [10] compares the performance results of the ANN method based on the number of factors and the amount of data used. In this study, the ANN method is combined with backpropagation to calculate the weight of the ANN network and uses 11 hidden layers.…”

“…In studies [8], [9], and [10] still discuss the analysis of model performance on classification, but with different cases. In [8], applied the XGBoost algorithm to the classification of forest fires using feature importance.…”

“…Research [11] apply the ANN algorithm in the medical field, especially in cancer research. While research [10] on the prediction of monthly weather classification. The results of the accuracy of the ANN method in research [10] using breast cancer data obtained is equal to 86.95% by applying 10 neurons to the input layer, sigmoid function, and 1 hidden layer.…”

“…While research [10] on the prediction of monthly weather classification. The results of the accuracy of the ANN method in research [10] using breast cancer data obtained is equal to 86.95% by applying 10 neurons to the input layer, sigmoid function, and 1 hidden layer. Research [10] compares the performance results of the ANN method based on the number of factors and the amount of data used.…”

“…In research [9], the hybrid method has not been applied to increase the accuracy value obtained. While in research [10], the number of factors used in building a predictive model is still too few.…”