Predicting groundwater level using traditional and deep machine learning algorithms
This research aims to evaluate various traditional or deep machine learning algorithms for the prediction of groundwater level (GWL) using three key input variables specific to Izeh City in the Khuzestan province of Iran: groundwater extraction rate (E), rainfall rate (R), and river flow rate (P) (w...
Published in: | Frontiers in Environmental Science |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Frontiers Media SA
2024
|
Subjects: | |
Online Access: | http://dx.doi.org/10.3389/fenvs.2024.1291327 https://www.frontiersin.org/articles/10.3389/fenvs.2024.1291327/full |
id |
crfrontiers:10.3389/fenvs.2024.1291327 |
---|---|
record_format |
openpolar |
spelling |
crfrontiers:10.3389/fenvs.2024.1291327 2024-09-15T18:03:53+00:00 Predicting groundwater level using traditional and deep machine learning algorithms Feng, Fan Ghorbani, Hamzeh Radwan, Ahmed E. 2024 http://dx.doi.org/10.3389/fenvs.2024.1291327 https://www.frontiersin.org/articles/10.3389/fenvs.2024.1291327/full unknown Frontiers Media SA https://creativecommons.org/licenses/by/4.0/ Frontiers in Environmental Science volume 12 ISSN 2296-665X journal-article 2024 crfrontiers https://doi.org/10.3389/fenvs.2024.1291327 2024-08-13T04:05:34Z This research aims to evaluate various traditional or deep machine learning algorithms for the prediction of groundwater level (GWL) using three key input variables specific to Izeh City in the Khuzestan province of Iran: groundwater extraction rate (E), rainfall rate (R), and river flow rate (P) (with 3 km distance). Various traditional and deep machine learning (DML) algorithms, including convolutional neural network (CNN), recurrent neural network (RNN), support vector machine (SVM), decision tree (DT), random forest (RF), and generative adversarial network (GAN), were evaluated. The convolutional neural network (CNN) algorithm demonstrated superior performance among all the algorithms evaluated in this study. The CNN model exhibited robustness against noise and variability, scalability for handling large datasets with multiple input variables, and parallelization capabilities for fast processing. Moreover, it autonomously learned and identified data patterns, resulting in fewer outlier predictions. The CNN model achieved the highest accuracy in GWL prediction, with an RMSE of 0.0558 and an R 2 of 0.9948. It also showed no outlier data predictions, indicating its reliability. Spearman and Pearson correlation analyses revealed that P and E were the dataset’s most influential variables on GWL. This research has significant implications for water resource management in Izeh City and the Khuzestan province of Iran, aiding in conservation efforts and increasing local crop productivity. The approach can also be applied to predicting GWL in various global regions facing water scarcity due to population growth. Future researchers are encouraged to consider these factors for more accurate GWL predictions. Additionally, the CNN algorithm’s performance can be further enhanced by incorporating additional input variables. Article in Journal/Newspaper DML Frontiers (Publisher) Frontiers in Environmental Science 12 |
institution |
Open Polar |
collection |
Frontiers (Publisher) |
op_collection_id |
crfrontiers |
language |
unknown |
description |
This research aims to evaluate various traditional or deep machine learning algorithms for the prediction of groundwater level (GWL) using three key input variables specific to Izeh City in the Khuzestan province of Iran: groundwater extraction rate (E), rainfall rate (R), and river flow rate (P) (with 3 km distance). Various traditional and deep machine learning (DML) algorithms, including convolutional neural network (CNN), recurrent neural network (RNN), support vector machine (SVM), decision tree (DT), random forest (RF), and generative adversarial network (GAN), were evaluated. The convolutional neural network (CNN) algorithm demonstrated superior performance among all the algorithms evaluated in this study. The CNN model exhibited robustness against noise and variability, scalability for handling large datasets with multiple input variables, and parallelization capabilities for fast processing. Moreover, it autonomously learned and identified data patterns, resulting in fewer outlier predictions. The CNN model achieved the highest accuracy in GWL prediction, with an RMSE of 0.0558 and an R 2 of 0.9948. It also showed no outlier data predictions, indicating its reliability. Spearman and Pearson correlation analyses revealed that P and E were the dataset’s most influential variables on GWL. This research has significant implications for water resource management in Izeh City and the Khuzestan province of Iran, aiding in conservation efforts and increasing local crop productivity. The approach can also be applied to predicting GWL in various global regions facing water scarcity due to population growth. Future researchers are encouraged to consider these factors for more accurate GWL predictions. Additionally, the CNN algorithm’s performance can be further enhanced by incorporating additional input variables. |
format |
Article in Journal/Newspaper |
author |
Feng, Fan Ghorbani, Hamzeh Radwan, Ahmed E. |
spellingShingle |
Feng, Fan Ghorbani, Hamzeh Radwan, Ahmed E. Predicting groundwater level using traditional and deep machine learning algorithms |
author_facet |
Feng, Fan Ghorbani, Hamzeh Radwan, Ahmed E. |
author_sort |
Feng, Fan |
title |
Predicting groundwater level using traditional and deep machine learning algorithms |
title_short |
Predicting groundwater level using traditional and deep machine learning algorithms |
title_full |
Predicting groundwater level using traditional and deep machine learning algorithms |
title_fullStr |
Predicting groundwater level using traditional and deep machine learning algorithms |
title_full_unstemmed |
Predicting groundwater level using traditional and deep machine learning algorithms |
title_sort |
predicting groundwater level using traditional and deep machine learning algorithms |
publisher |
Frontiers Media SA |
publishDate |
2024 |
url |
http://dx.doi.org/10.3389/fenvs.2024.1291327 https://www.frontiersin.org/articles/10.3389/fenvs.2024.1291327/full |
genre |
DML |
genre_facet |
DML |
op_source |
Frontiers in Environmental Science volume 12 ISSN 2296-665X |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3389/fenvs.2024.1291327 |
container_title |
Frontiers in Environmental Science |
container_volume |
12 |
_version_ |
1810441333960081408 |