Showmitra Kumar Sarkar, Swapan Talukdar, Atiqur Rahman, Shahfahad and Sujit Kumar Roy
The present study aims to construct ensemble machine learning (EML) algorithms for groundwater potentiality mapping (GPM) in the Teesta River basin of Bangladesh, including random…
Abstract
Purpose
The present study aims to construct ensemble machine learning (EML) algorithms for groundwater potentiality mapping (GPM) in the Teesta River basin of Bangladesh, including random forest (RF) and random subspace (RSS).
Design/methodology/approach
The RF and RSS models have been implemented for integrating 14 selected groundwater condition parametres with groundwater inventories for generating GPMs. The GPM were then validated using the empirical and bionormal receiver operating characteristics (ROC) curve.
Findings
The very high (831–1200 km2) and high groundwater potential areas (521–680 km2) were predicted using EML algorithms. The RSS (AUC-0.892) model outperformed RF model based on ROC's area under curve (AUC).
Originality/value
Two new EML models have been constructed for GPM. These findings will aid in proposing sustainable water resource management plans.
Details
Keywords
Ishita Afreen Ahmed, Shahfahad Shahfahad, Mirza Razi Imam Baig, Swapan Talukdar, Md Sarfaraz Asgher, Tariq Mahmood Usmani, Shakeel Ahmed and Atiqur Rahman
Deepor Beel is one of the Ramsar Site and a wetland of great biodiversity, situated in the south-western part of Guwahati, Assam. With urban development at its forefront city of…
Abstract
Purpose
Deepor Beel is one of the Ramsar Site and a wetland of great biodiversity, situated in the south-western part of Guwahati, Assam. With urban development at its forefront city of Guwahati, Deepor Beel is under constant threat. The study aims to calculate the lake water volume from the water surface area and the underwater terrain data using a triangulated irregular network (TIN) volume model.
Design/methodology/approach
The lake water surface boundaries for each year were combined with field-observed water level data to generate a description of the underwater terrain. Time series LANDSAT images of 2001, 2011 and 2019 were used to extract the modified normalized difference water index (MNDWI) in GIS domain.
Findings
The MNDWI was 0.462 in 2001 which reduced to 0.240 in 2019. This shows that the lake water storage capacity shrank in the last 2 decades. This leads to a major problem, i.e. the storage capacity of the lake has been declining gradually from 20.95 million m3 in 2001 to 16.73 million m3 in 2011 and further declined to 15.35 million m3 in 2019. The fast decline in lake water volume is a serious concern in the age of rapid urbanization of big cities like Guwahati.
Originality/value
None of the studies have been done previously to analyze the decline in the volume of Deepor Beel lake. Therefore, this study will provide useful insights in the water resource management and the conservation of Deepor Beel lake.