Rainfall-runoff forecasting utilizing genetic programming technique
This paper reports how the rainfall-runoff is forecasted utilizing Genetic Programming (GP) technique. It is a program that was inspired by biological processes such as mutation, crossover, and inversion in order to create a new generation. It is a program that will learn and improve with each analy...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Published: |
IAEME Publication
2023
|
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uniten.dspace-25035 |
---|---|
record_format |
dspace |
spelling |
my.uniten.dspace-250352023-05-29T15:30:46Z Rainfall-runoff forecasting utilizing genetic programming technique Ahmed A.N. Hayder G. Rahman R.A.B.A. Borhana A.A. 57214837520 56239664100 57205651379 55212152300 This paper reports how the rainfall-runoff is forecasted utilizing Genetic Programming (GP) technique. It is a program that was inspired by biological processes such as mutation, crossover, and inversion in order to create a new generation. It is a program that will learn and improve with each analysis done. It uses a trial an error method in order to forecast rainfall-runoff. GP uses Root Mean Squared Error (RMSE) as an indication of how accurate the results of the forecast. The lower and closer the RMSE to zero, the more accurate the rainfall-runoff forecasted. The study consists of running the data on the software until the lowest RMSE is obtained. This research contains three models which use a different number of input variables to see whether it will give an impact on the rainfall-runoff forecasting. The results are compared and a bar chart is plotted. � IAEME Publication. Final 2023-05-29T07:30:46Z 2023-05-29T07:30:46Z 2019 Article 2-s2.0-85060928940 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85060928940&partnerID=40&md5=fc57e4d103c43b26a882d93d5d621a62 https://irepository.uniten.edu.my/handle/123456789/25035 10 1 1523 1534 IAEME Publication Scopus |
institution |
Universiti Tenaga Nasional |
building |
UNITEN Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tenaga Nasional |
content_source |
UNITEN Institutional Repository |
url_provider |
http://dspace.uniten.edu.my/ |
description |
This paper reports how the rainfall-runoff is forecasted utilizing Genetic Programming (GP) technique. It is a program that was inspired by biological processes such as mutation, crossover, and inversion in order to create a new generation. It is a program that will learn and improve with each analysis done. It uses a trial an error method in order to forecast rainfall-runoff. GP uses Root Mean Squared Error (RMSE) as an indication of how accurate the results of the forecast. The lower and closer the RMSE to zero, the more accurate the rainfall-runoff forecasted. The study consists of running the data on the software until the lowest RMSE is obtained. This research contains three models which use a different number of input variables to see whether it will give an impact on the rainfall-runoff forecasting. The results are compared and a bar chart is plotted. � IAEME Publication. |
author2 |
57214837520 |
author_facet |
57214837520 Ahmed A.N. Hayder G. Rahman R.A.B.A. Borhana A.A. |
format |
Article |
author |
Ahmed A.N. Hayder G. Rahman R.A.B.A. Borhana A.A. |
spellingShingle |
Ahmed A.N. Hayder G. Rahman R.A.B.A. Borhana A.A. Rainfall-runoff forecasting utilizing genetic programming technique |
author_sort |
Ahmed A.N. |
title |
Rainfall-runoff forecasting utilizing genetic programming technique |
title_short |
Rainfall-runoff forecasting utilizing genetic programming technique |
title_full |
Rainfall-runoff forecasting utilizing genetic programming technique |
title_fullStr |
Rainfall-runoff forecasting utilizing genetic programming technique |
title_full_unstemmed |
Rainfall-runoff forecasting utilizing genetic programming technique |
title_sort |
rainfall-runoff forecasting utilizing genetic programming technique |
publisher |
IAEME Publication |
publishDate |
2023 |
_version_ |
1806428501541126144 |
score |
13.214268 |