AI-Driven Spatial Data Analysis of Groundwater Level and Gravimetric Data in Roorkee Region, India

Excessive consumption of groundwater can lead to a significant imbalance between groundwater recharge rates and water demand. This disparity underscores the importance of accurately estimating future groundwater storage to ensure global water and food security, in line with sustainable development g...

Full description

Saved in:
Bibliographic Details
Main Authors: H. Sarkar, C. S. P. Ojha, S. K. Ghosh
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-annals.copernicus.org/articles/X-G-2025/763/2025/isprs-annals-X-G-2025-763-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849319712633126912
author H. Sarkar
C. S. P. Ojha
S. K. Ghosh
author_facet H. Sarkar
C. S. P. Ojha
S. K. Ghosh
author_sort H. Sarkar
collection DOAJ
description Excessive consumption of groundwater can lead to a significant imbalance between groundwater recharge rates and water demand. This disparity underscores the importance of accurately estimating future groundwater storage to ensure global water and food security, in line with sustainable development goals (SDGs) related to clean water and sanitation and sustainable cities and communities. However, traditional methods face challenges in predicting groundwater storage due to their inherent complexity. To address this gap and align with SDGs, this study aims to develop a regression-based machine learning model for spatially varying groundwater level prediction. The primary goal is to improve local water resource management and encourage responsible water usage. The study evaluates the use of K-Nearest Neighbour (KNN), Random Forest (RF), Support Vector Machine (SVM), XG Boost and Polynomial regression models, using two groups of input parameters. The results show that the XG-Boost model establishes a strong relationship between input and output parameters. The developed KNN model can be reliably used for local groundwater level prediction and can also contribute to sustainable urban development, ultimately aligning with the SDGs.
format Article
id doaj-art-71a998fac6874477ab7c424636d07449
institution Kabale University
issn 2194-9042
2194-9050
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-71a998fac6874477ab7c424636d074492025-08-20T03:50:21ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502025-07-01X-G-202576377010.5194/isprs-annals-X-G-2025-763-2025AI-Driven Spatial Data Analysis of Groundwater Level and Gravimetric Data in Roorkee Region, IndiaH. Sarkar0C. S. P. Ojha1S. K. Ghosh2Department of Civil Engineering, Indian Institute of Technology Roorkee, IndiaDepartment of Civil Engineering, Indian Institute of Technology Roorkee, IndiaDepartment of Civil Engineering, Indian Institute of Technology Roorkee, IndiaExcessive consumption of groundwater can lead to a significant imbalance between groundwater recharge rates and water demand. This disparity underscores the importance of accurately estimating future groundwater storage to ensure global water and food security, in line with sustainable development goals (SDGs) related to clean water and sanitation and sustainable cities and communities. However, traditional methods face challenges in predicting groundwater storage due to their inherent complexity. To address this gap and align with SDGs, this study aims to develop a regression-based machine learning model for spatially varying groundwater level prediction. The primary goal is to improve local water resource management and encourage responsible water usage. The study evaluates the use of K-Nearest Neighbour (KNN), Random Forest (RF), Support Vector Machine (SVM), XG Boost and Polynomial regression models, using two groups of input parameters. The results show that the XG-Boost model establishes a strong relationship between input and output parameters. The developed KNN model can be reliably used for local groundwater level prediction and can also contribute to sustainable urban development, ultimately aligning with the SDGs.https://isprs-annals.copernicus.org/articles/X-G-2025/763/2025/isprs-annals-X-G-2025-763-2025.pdf
spellingShingle H. Sarkar
C. S. P. Ojha
S. K. Ghosh
AI-Driven Spatial Data Analysis of Groundwater Level and Gravimetric Data in Roorkee Region, India
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title AI-Driven Spatial Data Analysis of Groundwater Level and Gravimetric Data in Roorkee Region, India
title_full AI-Driven Spatial Data Analysis of Groundwater Level and Gravimetric Data in Roorkee Region, India
title_fullStr AI-Driven Spatial Data Analysis of Groundwater Level and Gravimetric Data in Roorkee Region, India
title_full_unstemmed AI-Driven Spatial Data Analysis of Groundwater Level and Gravimetric Data in Roorkee Region, India
title_short AI-Driven Spatial Data Analysis of Groundwater Level and Gravimetric Data in Roorkee Region, India
title_sort ai driven spatial data analysis of groundwater level and gravimetric data in roorkee region india
url https://isprs-annals.copernicus.org/articles/X-G-2025/763/2025/isprs-annals-X-G-2025-763-2025.pdf
work_keys_str_mv AT hsarkar aidrivenspatialdataanalysisofgroundwaterlevelandgravimetricdatainroorkeeregionindia
AT cspojha aidrivenspatialdataanalysisofgroundwaterlevelandgravimetricdatainroorkeeregionindia
AT skghosh aidrivenspatialdataanalysisofgroundwaterlevelandgravimetricdatainroorkeeregionindia