Evaluation of correlation of physicochemical parameters and major ions present in groundwater of Raipur using discretization

Q4 Engineering

Measurement Sensors Pub Date : 2024-07-10 DOI:10.1016/j.measen.2024.101278

Mridu Sahu , Anushree Shrivastava , D.C. Jhariya , Shivangi Diwan , Jalina Subhadarsini

{"title":"Evaluation of correlation of physicochemical parameters and major ions present in groundwater of Raipur using discretization","authors":"Mridu Sahu , Anushree Shrivastava , D.C. Jhariya , Shivangi Diwan , Jalina Subhadarsini","doi":"10.1016/j.measen.2024.101278","DOIUrl":null,"url":null,"abstract":"<div><p>Groundwater, vital for human consumption and agriculture, ecosystem support, and industrial activities, requires sustainable management using proper quality assessment techniques. This study examines the relationship between physicochemical parameters and major ions in groundwater samples collected from 44 regions in Raipur, using sensor-based data acquisition alongside traditional methods. Employing K-means clustering for data discretization, correlations between parameters are highlighted. Results show positive associations among EC, TDS, TH, and TA. ArcGIS interpolation maps visualize spatial distribution. Addressing class imbalance, an upsampling technique is utilized. Machine learning algorithms, including Logistic Regression and Random Forest, classify water quality with accuracies of 98.8 % and 98.3 %, respectively. This research, blending traditional and sensor-based methods, emphasizes informed water management<strong>.</strong></p></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"34 ","pages":"Article 101278"},"PeriodicalIF":0.0000,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266591742400254X/pdfft?md5=bebf3fe3c74e04f17b1ad4fcf00fdd06&pid=1-s2.0-S266591742400254X-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Measurement Sensors","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S266591742400254X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Engineering","Score":null,"Total":0}

引用次数: 0

Abstract

Groundwater, vital for human consumption and agriculture, ecosystem support, and industrial activities, requires sustainable management using proper quality assessment techniques. This study examines the relationship between physicochemical parameters and major ions in groundwater samples collected from 44 regions in Raipur, using sensor-based data acquisition alongside traditional methods. Employing K-means clustering for data discretization, correlations between parameters are highlighted. Results show positive associations among EC, TDS, TH, and TA. ArcGIS interpolation maps visualize spatial distribution. Addressing class imbalance, an upsampling technique is utilized. Machine learning algorithms, including Logistic Regression and Random Forest, classify water quality with accuracies of 98.8 % and 98.3 %, respectively. This research, blending traditional and sensor-based methods, emphasizes informed water management.

查看原文本刊更多论文

利用离散化方法评估赖布尔地下水中物理化学参数和主要离子的相关性

地下水对人类消费、农业、生态系统支持和工业活动至关重要，需要利用适当的质量评估技术进行可持续管理。本研究采用基于传感器的数据采集和传统方法，研究了从雷普尔 44 个地区采集的地下水样本中物理化学参数和主要离子之间的关系。采用 K-means 聚类法对数据进行离散化处理，突出了参数之间的相关性。结果显示 EC、TDS、TH 和 TA 之间存在正相关。ArcGIS 插值地图将空间分布可视化。为解决类不平衡问题，采用了上采样技术。包括逻辑回归和随机森林在内的机器学习算法对水质进行了分类，准确率分别为 98.8 % 和 98.3 %。这项研究融合了传统方法和基于传感器的方法，强调知情的水资源管理。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊