Modeling of standardized groundwater index of Bihar using machine learning techniques

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 st...

Full description

Saved in:
Bibliographic Details
Main Authors: Kumari S., Kumar D., Kumar M., Pande C.B.
Other Authors: 58164893400
Format: Article
Published: Elsevier Ltd 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-34164
record_format dspace
spelling my.uniten.dspace-341642024-10-14T11:18:14Z Modeling of standardized groundwater index of Bihar using machine learning techniques Kumari S. Kumar D. Kumar M. Pande C.B. 58164893400 58248506100 57713959100 57193547008 Artificial neural network and random forest GRACE satellite Groundwater drought Standardized groundwater index Bihar India Drought Forestry Geodetic satellites Groundwater resources Learning algorithms Machine learning Mean square error Neural networks Rain Artificial neural network and random forest Artificial neural network modeling Correlation coefficient Gravity recovery and climate experiment satellites Groundwater drought Machine learning techniques Means square errors Random forests Standardized groundwater index Water equivalent artificial neural network GRACE groundwater modeling rainfall Groundwater 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 Final 2024-10-14T03:18:14Z 2024-10-14T03:18:14Z 2023 Article 10.1016/j.pce.2023.103395 2-s2.0-85151276292 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85151276292&doi=10.1016%2fj.pce.2023.103395&partnerID=40&md5=3b5fb50d66ed1793dba925536da9dfb2 https://irepository.uniten.edu.my/handle/123456789/34164 130 103395 Elsevier Ltd 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/
topic Artificial neural network and random forest
GRACE satellite
Groundwater drought
Standardized groundwater index
Bihar
India
Drought
Forestry
Geodetic satellites
Groundwater resources
Learning algorithms
Machine learning
Mean square error
Neural networks
Rain
Artificial neural network and random forest
Artificial neural network modeling
Correlation coefficient
Gravity recovery and climate experiment satellites
Groundwater drought
Machine learning techniques
Means square errors
Random forests
Standardized groundwater index
Water equivalent
artificial neural network
GRACE
groundwater
modeling
rainfall
Groundwater
spellingShingle Artificial neural network and random forest
GRACE satellite
Groundwater drought
Standardized groundwater index
Bihar
India
Drought
Forestry
Geodetic satellites
Groundwater resources
Learning algorithms
Machine learning
Mean square error
Neural networks
Rain
Artificial neural network and random forest
Artificial neural network modeling
Correlation coefficient
Gravity recovery and climate experiment satellites
Groundwater drought
Machine learning techniques
Means square errors
Random forests
Standardized groundwater index
Water equivalent
artificial neural network
GRACE
groundwater
modeling
rainfall
Groundwater
Kumari S.
Kumar D.
Kumar M.
Pande C.B.
Modeling of standardized groundwater index of Bihar using machine learning techniques
description 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
author2 58164893400
author_facet 58164893400
Kumari S.
Kumar D.
Kumar M.
Pande C.B.
format Article
author Kumari S.
Kumar D.
Kumar M.
Pande C.B.
author_sort Kumari S.
title Modeling of standardized groundwater index of Bihar using machine learning techniques
title_short Modeling of standardized groundwater index of Bihar using machine learning techniques
title_full Modeling of standardized groundwater index of Bihar using machine learning techniques
title_fullStr Modeling of standardized groundwater index of Bihar using machine learning techniques
title_full_unstemmed Modeling of standardized groundwater index of Bihar using machine learning techniques
title_sort modeling of standardized groundwater index of bihar using machine learning techniques
publisher Elsevier Ltd
publishDate 2024
_version_ 1814061044112293888
score 13.209306