IJISTECH (International Journal Of Information System & Technology)
Vol 3, No 1 (2019): November

Increasing Prediction Accuracy with the Backpropagation Algorithm (Case Study: Pematangsiantar City Rainfall)

Prayoga, Yogi (Unknown)
Hartama, Dedy (Unknown)
Jalaluddin, Jalaluddin (Unknown)
Sumarno, Sumarno (Unknown)
Nasution, Zulaini Masuro (Unknown)

Article Info

Publish Date
26 Nov 2019


The more advanced science and technology from various disciplines, currently rainfall can be predicted by carrying out various empirical approaches, one of which is by using Artificial Neural Networks (ANN). This study aims to apply ANN with backpropogation algorithm in predicting rainfall. The research data used is BPS data of the transfer city. The results of the study state that of the 6 models (4-5-1, 4-10-1, 4-25-1, 4-5-10-1, 4-5-25-1 and 4-5-50-1) architecture that was trained and tested using Matlab 6.1 application software, the results showed that the 4-5-25-1 architectural model was the best model for making predictions with 75% truth accuracy, Training MSE 0.001004582, Testing MSE 0.021882712 and Epoch 59,076 . It is expected that research can provide input to the government, especially BMKG Pematangsiantar city in predicting Rainfall based on computer science so as to improve the quality of services in the fields of Meteorology, Climatology, Air Quality and Geophysics in accordance with applicable laws and regulations.

Copyrights © 2019

Journal Info





Computer Science & IT


IJISTECH (International Journal Of Information System & Technology) is published with both online and print versions. The journal covers the frontier issues in the computer science and their applications in business, industry and other subjects. The computer science is a branch of engineering ...