Assessment of landcover impacts on the groundwater quality using hydrogeochemical and geospatial techniques

Abstract

Groundwater quality is signi cantly impacted by urbanization and land use land cover (LULC) changes.The current study investigated the impact of LULC on groundwater quality in Quetta city, Baluchistan province, Pakistan. During the years 2015 and 2021, a total of 58 groundwater samples were collected from drinking wells for chemical analysis. The hydrogeochemistry of groundwater was investigated using Gibbs diagrams, Piper diagrams, and spatial distribution maps. The water quality trend was depicted using the Wilcox, USSL diagram, and Water Quality Index (WQI) from 2015 to 2021. The LULC analysis of Quetta was carried out on Google Earth Engine's cloud-computing platform using imagery from the Sentinel-2 satellite with low cloud cover (<10%). The LULC data was later used to calculate the rate of landcover conversion between both years 2015 and 2021 which help to identify the spatial distribution of groundwater and assess its vulnerability to pollution. The ndings indicate an increase in the urban and agricultural classes while a decrease in the barren class. Moreover, according to the Piper diagram, groundwater in Quetta was primarily classi ed as CaMgCl type, CaCl type, and NaCl type. The Gibbs diagrams show water-rock interactions and rock weathering as the dominant evolution of hydrogeochemistry. The majority of the groundwater samples in both years were suitable for irrigation, according to the Wilcox diagram, USSL diagram, and other agricultural indices. The WQI demonstrated that the groundwater sources in the area are safe for human consumption; however, in the northern parts, WQI values are declining due to urbanization over six years.

Comparison of machine and deep learning algorithms using Google Earth Engine and Python for land classifications

“…According to studies, classification techniques, including machine learning (ML) and deep learning (DL) algorithms, play a vital role (Kussul et al, 2017;Jagannathan and Divya, 2021;Digra et al, 2022;Swetanisha et al, 2022;Wang et al, 2022;Azedou et al, 2023;Boonpook et al, 2023;Ebenezer and Manohar, 2023). DL models, demonstrated by Convolutional Neural Networks (CNN) (Jena et al, 2022) and Recurrent Neural Networks (RNN) (Gaafar et al, 2022), have gained importance due to their ability to extract and classify features efficiently (Swetanisha et al, 2022).…”

“…DL models, demonstrated by Convolutional Neural Networks (CNN) (Jena et al, 2022) and Recurrent Neural Networks (RNN) (Gaafar et al, 2022), have gained importance due to their ability to extract and classify features efficiently (Swetanisha et al, 2022). Spatial data, remote sensing, and machine learning analysis have a wide range of applications, including urban planning, agriculture, resource management, mineralogy for the environmental management and planning (Hussein et al, 2023;Iqbal et al, 2023;Kanakala and Reddy, 2023) and have been used for natural language processing (NLP) (Agga et al, 2022;Vankdothu et al, 2022). Deep learning models are recognized as intelligent modeling approaches, catalyzing advancements in land use modeling (Gaafar et al, 2022).…”

Machine Learning Algorithms for Predicting the Water Quality Index

“…Chemicals and microbial contamination frequently challenge water safety [9][10][11]. Groundwater has taken over as the primary water supply; it is the preferred sole source, particularly in arid and semi-arid regions where precipitation is inadequate and surface water resources are lacking [12][13][14][15][16][17]; also, waste material including sewage sludge on soil can increase crop production but contaminate groundwater [18][19][20][21][22][23][24][25].…”