摘要
Groundwater potential (GWP) mapping in the drought prone hard rock terrains is a fundamental aspect towards development and management for the society and environment. The present research was carried out in parts of drought prone Manjeera basin, of Deccan basaltic province, India. This research aims to delineate GWP zones using application of machine learning (ML) models namely random forest (RF), support-vector machine (SVM) and artificial neural network (ANN) with geospatial technique to integrate hydrogeological/ geo-environmental groundwater conditioning variables. A total of 1598 well inventory data of groundwater was utilized in a 70:30 ratio of training and testing, respectively. The 3 ML models categorized the GWP zone into five classes namely excellent, good, moderate, poor and very poor. The RF, SVM and ANN models demonstrated that favourable GWP zone (excellent GWP + Good GWP) spatially accounts for 37.85, 38.82 and 32.36% of the study area, respectively. The model predictability was quantified using area under the receiver operation characteristics (A(R)UROC) curve values, which exhibits RF model with highest success rate (81.62%) followed by SVM (79.10%) and ANN (77.18%) model. This research proves that application of ML models with geospatial technique is a way forward for groundwater resource development and management.
学科与关键词
- A comparison of machine learning models for the mapping of groundwater spring potentialAl-Fugara, A'kif; Pourghasemi, Hamid Reza*; Al-Shabeeb, Abdel Rahman; Habib, Maan; Al-Adamat, Rida; AI-Amoush, Hani; Collins, Adrian L.Environmental Earth Sciences, 2020, 79(10): 206.被引 34
- Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern TunisiaTrabelsi, Fatma*; Ali, Salsebil Bel Hadj; Lee, SaroRemote Sensing, 2023, 15(1): 152.被引 8
- Characterizing groundwater distribution potential using GIS-based machine learning model in Chihe River basin, ChinaWang, Dejian; Qian, Jiazhong*; Ma, Lei*; Zhao, Weidong; Gao, Di; Hou, Xiaoliang; Ma, HaichunEnvironmental Earth Sciences, 2022, 81(12): 324.被引 4
