Publication: Modeling of standardized groundwater index of Bihar using machine learning techniques
dc.citedby | 10 | |
dc.contributor.author | Kumari S. | en_US |
dc.contributor.author | Kumar D. | en_US |
dc.contributor.author | Kumar M. | en_US |
dc.contributor.author | Pande C.B. | en_US |
dc.contributor.authorid | 58164893400 | en_US |
dc.contributor.authorid | 58248506100 | en_US |
dc.contributor.authorid | 57713959100 | en_US |
dc.contributor.authorid | 57193547008 | en_US |
dc.date.accessioned | 2024-10-14T03:18:14Z | |
dc.date.available | 2024-10-14T03:18:14Z | |
dc.date.issued | 2023 | |
dc.description.abstract | Groundwater is the most preferred source of water resource for the human needs. Over-exploitation of the groundwater has been led to the tremendous effect on the groundwater drought. Assessment of groundwater drought is difficult to understand due to its complexity, non-linearity feature. In this study, groundwater drought indices of the state of Bihar, India, have been modeled using machine learning technique. The prediction of SGI was done by using Artificial Neural Network (ANN) and Random Forest (RF) machine learning models. The best input combinations of Gravity Recovery and Climate experiment (GRACE) satellite water equivalent data, rainfall data and groundwater level data was used to predicted the SGI. In this study, SGI of 38 districts of Bihar was calculated using groundwater data from 2002 to 2019. The accuracy and efficiency of the RF and ANN models were measured based on the mean square error (MSE) and correlation coefficient value (r). Compared to two models are shown the RF model is a performs superior as compare to ANN model, which model superior is decided based on the correlation coefficient value (r) as 0.95 and MSE value of 0.11. The results show both ML models such as ANN and RF is showed best results with the input combination of GRACE satellite water equivalent data, rainfall and groundwater data. � 2023 Elsevier Ltd | en_US |
dc.description.nature | Final | en_US |
dc.identifier.ArtNo | 103395 | |
dc.identifier.doi | 10.1016/j.pce.2023.103395 | |
dc.identifier.scopus | 2-s2.0-85151276292 | |
dc.identifier.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85151276292&doi=10.1016%2fj.pce.2023.103395&partnerID=40&md5=3b5fb50d66ed1793dba925536da9dfb2 | |
dc.identifier.uri | https://irepository.uniten.edu.my/handle/123456789/34164 | |
dc.identifier.volume | 130 | |
dc.publisher | Elsevier Ltd | en_US |
dc.source | Scopus | |
dc.sourcetitle | Physics and Chemistry of the Earth | |
dc.subject | Artificial neural network and random forest | |
dc.subject | GRACE satellite | |
dc.subject | Groundwater drought | |
dc.subject | Standardized groundwater index | |
dc.subject | Bihar | |
dc.subject | India | |
dc.subject | Drought | |
dc.subject | Forestry | |
dc.subject | Geodetic satellites | |
dc.subject | Groundwater resources | |
dc.subject | Learning algorithms | |
dc.subject | Machine learning | |
dc.subject | Mean square error | |
dc.subject | Neural networks | |
dc.subject | Rain | |
dc.subject | Artificial neural network and random forest | |
dc.subject | Artificial neural network modeling | |
dc.subject | Correlation coefficient | |
dc.subject | Gravity recovery and climate experiment satellites | |
dc.subject | Groundwater drought | |
dc.subject | Machine learning techniques | |
dc.subject | Means square errors | |
dc.subject | Random forests | |
dc.subject | Standardized groundwater index | |
dc.subject | Water equivalent | |
dc.subject | artificial neural network | |
dc.subject | GRACE | |
dc.subject | groundwater | |
dc.subject | modeling | |
dc.subject | rainfall | |
dc.subject | Groundwater | |
dc.title | Modeling of standardized groundwater index of Bihar using machine learning techniques | en_US |
dc.type | Article | en_US |
dspace.entity.type | Publication |