Publication:
Groundwater level prediction using machine learning algorithms in a drought-prone area

Simple item page
dc.citedby25
dc.contributor.authorPham Q.B.en_US
dc.contributor.authorKumar M.en_US
dc.contributor.authorDi Nunno F.en_US
dc.contributor.authorElbeltagi A.en_US
dc.contributor.authorGranata F.en_US
dc.contributor.authorIslam A.R.M.T.en_US
dc.contributor.authorTalukdar S.en_US
dc.contributor.authorNguyen X.C.en_US
dc.contributor.authorAhmed A.N.en_US
dc.contributor.authorAnh D.T.en_US
dc.contributor.authorid57208495034en_US
dc.contributor.authorid57211647641en_US
dc.contributor.authorid57205552003en_US
dc.contributor.authorid57204724397en_US
dc.contributor.authorid36801761600en_US
dc.contributor.authorid57218543677en_US
dc.contributor.authorid57194545588en_US
dc.contributor.authorid57213267707en_US
dc.contributor.authorid57214837520en_US
dc.contributor.authorid57210116833en_US
dc.date.accessioned2023-05-29T09:37:10Z
dc.date.available2023-05-29T09:37:10Z
dc.date.issued2022
dc.descriptionCrops; Cultivation; Decision trees; Errors; Forecasting; Groundwater resources; Learning algorithms; Mean square error; Statistical tests; Support vector machines; Absolute error; Bangladesh; Correlation coefficient; Ground water level; Groundwater prediction; Locally weighted linear regression; Mean absolute error; Random tree; Root mean square errors; Squared errors; Groundwateren_US
dc.description.abstractGroundwater resources (GWR) play a crucial role in agricultural crop production, daily life, and economic progress. Therefore, accurate prediction of groundwater (GW) level will aid in the sustainable management of GWR. A comparative study was conducted to evaluate the performance of seven different ML models, such as random tree (RT), random forest (RF), decision stump, M5P, support vector machine (SVM), locally weighted linear regression (LWLR), and reduce error pruning tree (REP Tree) for GW level (GWL) prediction. The long-term prediction was conducted�using historical GWL, mean temperature, rainfall, and relative humidity datasets for the period 1981�2017 obtained from two wells in the northwestern region of Bangladesh. The whole dataset was divided into training (1981�2008) and testing (2008�2017) datasets. The output of the seven proposed models was evaluated using the root mean square error (RMSE), mean absolute error (MAE), relative absolute error (RAE), root relative squared error (RRSE), correlation coefficient (CC), and Taylor diagram. The results revealed that the Bagging-RT and Bagging-RF models outperformed other ML models. The Bagging-RT models can effectively improve prediction precision as compared to other models with RMSE of 0.60�m, MAE of 0.45�m, RAE of 27.47%, RRSE of 30.79%, and CC of 0.96 for Rajshahi and RMSE of 0.26�m, MAE of 0.18�m, RAE of 19.87%, RRSE of 24.17%, and 0.97 for Rangpur during training, and RMSE of 0.60�m, MAE of 0.40�m, RAE of 24.25%, RRSE of 29.99%, and CC of 0.96 for Rajshahi and RMSE of 0.38�m, MAE of 0.24�m, RAE of 23.55%, RRSE of 31.77%, and CC of 0.95 for Rangpur during testing stages, respectively. Our study offers an effective and practical approach to the forecast of GWL that could help to formulate policies for sustainable GWR management. � 2022, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1007/s00521-022-07009-7
dc.identifier.epage10773
dc.identifier.issue13
dc.identifier.scopus2-s2.0-85125521244
dc.identifier.spage10751
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85125521244&doi=10.1007%2fs00521-022-07009-7&partnerID=40&md5=4eee868d19776c11d068a70cb124a0dd
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/26845
dc.identifier.volume34
dc.publisherSpringer Science and Business Media Deutschland GmbHen_US
dc.sourceScopus
dc.sourcetitleNeural Computing and Applications
dc.titleGroundwater level prediction using machine learning algorithms in a drought-prone areaen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS