Artificial Neural Network for Monthly Rainfall Rate Prediction

[摘要] Rainfall rate forecasting plays an important role in various human activities. Rainfall forecasting is a challenging task due to the uncertainty of natural phenomena. In this paper, two neural network models are proposed for monthly rainfall rate forecasting. The performance of the proposed model is assesses based on monthly rainfall rate in Ampel, Boyolali, from 2001-2013. The experiment results show that the accuracy of the first model is much better than the accuracy of the second model. Its average accuracy is just above 98%, while the accuracy of the second model is approximately 75%. In additional, both models tend to perform better when the fluctuation of rainfall is low.

[发布机构] Department of Information Technology, Satya Wacana Christian University, Diponegoro St, 52-60, Salatiga, Central Java, Indonesia^1

[效力级别] 自然科学

[关键词] Human activities;Monthly rainfalls;Natural phenomena;Neural network model;Rainfall forecasting;Rainfall rates