Prediksi curah hujan bulanan berdasrkan parameter cuaca menggunakan jaringan saraf tiruan Levenberg Marquardt

Setiyaris, Setiyaris, Hariyadi, M. Amin ORCID: and Crysdian, Cahyo (2023) Prediksi curah hujan bulanan berdasrkan parameter cuaca menggunakan jaringan saraf tiruan Levenberg Marquardt. Jurnal Media Informatika Budidarma, 7 (3). pp. 1125-1133. ISSN 2548-8368

16320.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview


Accurate prediction of rainfall is very important for warning services for hydrometeorological disasters or disasters caused by rain, so high accuracy is required in making predictions of rainfall. Artificial Neural Networks are becoming a trend in the field of computers because they provide the best accuracy in making predictions. Artificial neural networks are very powerful in recognizing data patterns to model and predict rainfall. The purpose of this research is to predict rainfall using the Levenberg Marquardt algorithm artificial neural network method. The data used for analysis are 120 data consisting of temperature, humidity, pressure, wind speed and solar radiation. To get accurate predictions, calculations are carried out by varying the amount of input and output data as well as varying the number of neurons in the hidden layer. The best performance of a model is measured from the value of MSE or Mean Square Error. The result shows that the network with a data composition of 90% input data, 10% output data and 25 neurons in the hidden layer is the best architecture with an MSE value of 0.029

Item Type: Journal Article
Keywords: predictions; weather; rainfall; artificial neural networks; Levenberg Marquardt
Subjects: 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing
Divisions: Faculty of Technology > Department of Informatics Engineering
Depositing User: Mokhamad Amin Hariyadi
Date Deposited: 14 Nov 2023 10:59


Downloads per month over past year

Origin of downloads

Actions (login required)

View Item View Item