Using an ensemble machine learning model to delineate groundwater potential zones in desert fringes of East Esna-Idfu area, Nile valley, Upper Egypt

Abstract

The effects of climate change and rapid population growth increase the demand for freshwater, particularly in arid and hyper-arid environments, considering that groundwater is an essential water resource in these regions. The main focus of this research was to generate a groundwater potential map in the Center Eastern Desert, Egypt, using a random forest classification machine learning model. Based on satellite data, geological maps and field survey, fifteen effective features influencing groundwater potentiality were created. These effective features include elevation, slope angle, slope aspect, terrain ruggedness index, curvature, lithology, lineament density, distance from major fractures, topographic wetness index, stream power index, drainage density, rainfall, as well as distance from rivers and channels, soil type and land use/land cover. Collinearity analysis was used for feature selection. A 100 dependent points (57 water points and 43 non-potential mountainous areas) were labeled and classified according to hydrogeological conditions in the three main aquifers (Basement, Nubian and Quaternary Aquifers) in the study area. The random forest algorithm was trained using (70%) of the dependent points. Then, it was validated using (30%) and the hyper-parameters were optimized. Groundwater potential map was predicted and classified as good (5.1%), moderate (0.1%), poor (4.2%) and non-potentiality (90.6%). Sensitivity (92%), F1-score (94%) and accuracy (97%) are validation methods used due to the imbalanced dataset problem. The most important effective features for groundwater potential map were determined based on the random forest and the receiver operating characteristics curve. Groundwater management sustainability was discussed based on the predicted groundwater potential map and aquifer conditions. Therefore, the random forest model is helpful for delineating groundwater potential zones and can be used in similar locations all over the world.

Groundwater Potential Assessment in the Upper Oum Er-Rbia Basin, Northern Morocco

“…The hydrogeological potential is fundamentally linked to the lithological nature of the terrain. The hydrogeological properties of aquifer materials are mainly defined by their lithology [Morgan et al, 2023]. Rock characteristics like porosity and permeability control water movement and storage [Mandal K.K.…”

“…Depending on its texture, the soil regulates how much water may reach underlying formations, which affects groundwater recharge [Anusha et al, 2022;Morgan et al, 2023]. Groundwater availability depends on the saturation level of the vadose zone, which is affected by soil texture [Arulbalaji et al, 2019;Mandal K.K.…”

“…The Chromic Luvisols medium-textured unit has an area of 1099 km 2 (32%), while the Chromic Luvisols fine-textured unit covers 183 km 2 (5%). TWI TWI, or topographic wetness index, reflects the impact of topography on the amount of runoff generated and flow accumulation [Morgan et al, 2023;Yadav et al, 2023]. This index is used here to consider the part of topography in conditioning infiltration [Castillo et al, 2022;Upwanshi et al, 2023].…”

Artificial intelligence ‐ driven sustainable development: Examining organizational, technical, and processing approaches to achieving global goals

“…While we have identified certain trends and gaps within the scope of our review, we acknowledge that there are indeed studies that have adopted AI in addressing critical global issues such as climate change and public health. For example, Morgan et al (2023) have used an ensemble machine learning model to delineate groundwater potential zones in desert fringes, contributing to our understanding of climate change impacts in specific regions. Similarly, Nguyen et al (2022) have adopted AI in vaccine development, specifically in designing a multi‐epitope candidate vaccine to control African swine fever spread.…”

Investigating machine learning and ensemble learning models in groundwater potential mapping in arid region: case study from Tan-Tan water-scarce region, Morocco

“…LightGBM-C outperformed the other models, showing an AUC of 0.921. Morgan et al (2023) used the RF EL model to assess GWPM in dry wadis within arid conditions, focusing on the East Idfu-Esna area in Egypt's Eastern desert. The research achieved an impressive accuracy rate of 97%.…”