Harsono, Radiatza Adhi and , Gurawan Djati Wibowo, ST., M.Eng (2021) Aplikasi Penggunaan Matlab Pada Jaringan Syaraf Tiruan Pada Pemodelan Hujan Aliran di Das Opak. Skripsi thesis, Universitas Muhammadiyah Surakarta.
PDF (Naskah Publikasi)
NASKAH PUBLIKASI.pdf Download (1MB) |
|
PDF (Halaman Depan)
HALAMAN DEPAN-4.pdf Download (391kB) |
|
PDF (Bab I)
BAB I.pdf Download (263kB) |
|
PDF (Bab II)
BAB II.pdf Restricted to Repository staff only Download (156kB) | Request a copy |
|
PDF (Bab III)
BAB III.pdf Restricted to Repository staff only Download (346kB) | Request a copy |
|
PDF (Bab IV)
Bab IV.pdf Restricted to Repository staff only Download (456kB) | Request a copy |
|
PDF (Bab V)
BAB V.pdf Restricted to Repository staff only Download (715kB) | Request a copy |
|
PDF (Bab VI)
BAB VI.pdf Restricted to Repository staff only Download (90kB) | Request a copy |
|
PDF (Daftar Pustaka)
DAFTAR PUSTAKA.pdf Download (60kB) |
|
PDF (Lampiran)
LAMPIRAN.pdf Restricted to Repository staff only Download (2MB) | Request a copy |
|
PDF (Surat Pernyataan Publikasi)
SURAT PERNYATAAN PUBLIKASI.pdf Restricted to Repository staff only Download (214kB) | Request a copy |
Abstract
Rain has a close relationship with discharge so there is a need for research to predict potential discharge based on semi-monthly regional rain data. So that water management and utilization can take place optimally and effectively. To analyze water availability ideally, long flow data is required (minimum 15 years), so that the results of the analysis can be said to be ideal. The limitation of flow data is one of the obstacles that are often found in the analysis of water availability. Flow data in Indonesia is often only in the range of 2-5 years. This happened in several areas in Indonesia. In this study, rainfall flow modeling for watersheds used an Artificial Neural Network model. Artificial Neural Network is one of the artificial representations of the human brain which always tries to simulate the learning process in the human brain. The human brain contains millions of neurons whose job is to process information. Each cell interacts with each other so that it supports the ability of the brain to work. Each neurons will have one cell nucleus which is responsible for processing information. Like the human brain, the neural network also consists of several neurons, which have connections between these neurons. The neurons will transform the information received through the outgoing connection to other neurons. The results showed that the use of backpropagation artificial neural network can be applied in modeling rainfall flow. Of the three variations of the training algorithm (gradient descent, adaptive learning rate, and lavender-marquadt), the lavender-marquadt training algorithm gives the most optimum results with a correlation value of 0,9970 or 99,70%, a RMSE value of 1,171x10-5, and volume error value of 0,0029 or 0,29%. Meanwhile, the gradient descent training algorithm gives a correlation value of 0,5216 or 52,16%, a RMSE value of 0,16161, and a volume error value of 0,0760 or 7,60%. The adaptive learning rate training algorithm gives a correlation value of 0,8886 or 88,86%, a RMSE value of 0,07569, and a volume error value of 0,0340 or 3,40%. From these results, it can be seen that the artificial neural network modeling is quite good for modeling data that is quite volatile and can also be applied in modeling rain runoff
Item Type: | Karya ilmiah (Skripsi) |
---|---|
Uncontrolled Keywords: | Rainflow modeling, artificial neural network, backpropagation, gradient descent, adaptive learning rate, lavenberg-marquadt |
Subjects: | T Technology > TA Engineering (General). Civil engineering (General) |
Divisions: | Fakultas Teknik > Teknik Sipil |
Depositing User: | RADIATZA ADHI HARSONO |
Date Deposited: | 11 Nov 2021 23:53 |
Last Modified: | 11 Nov 2021 23:53 |
URI: | http://eprints.ums.ac.id/id/eprint/95486 |
Actions (login required)
View Item |