RAGA: An Artificial Intelligence Based System for Predicting Groundwater Availability

RAGA: An Artificial Intelligence Based System for Predicting Groundwater Availability

Principal Investigator

Dr Cyril Dziedzorm Boateng
Department of Physics
College of Science
Kwame Nkrumah University of Science and Technology (KNUST) Email: cyrilboat@knust.edu.gh
Phone: (+233)559580392

Executive Summary

Climate change and variability have been identified as the most significant human and environmental crises to hit the world in the 21st century with sub-Saharan Africa (SSA) being seriously affected. Africa in general and Ghana, in particular, is vulnerable because farming which is the main economic activity of majority of its populace is mainly rain feed. Hence, changes in the climatic parameters have a great impact on the livelihoods of the people and threaten to undo the developmental gains made over the past decades. Innovative solutions are therefore required to bolster the region’s capacity to counter and adapt to the adverse effects of climate change especially on water resources. Without good quality water, people get hungry, get sick, end up poor or even die. As freshwater bodies run dry, due to reduction in rainfall amounts in most SSA countries as well as the pollution of existing rivers, there is the need to find alternative sources of potable water supply. Ghana in recent times has seen a rapid rise in the utilization of groundwater for domestic, agricultural, and industrial purposes. However, the process of exploring and exploiting groundwater resources is very capital intensive with climate change and variability further exacerbating the reliability of these groundwater systems. We seek to develop an innovative web-based artificial intelligence (AI) driven open-source framework to predict groundwater availability in Ghana using Groundwater Levels (GWLs) as a proxy. We will call this project RAGA: Rapid Assessment of Groundwater Availability. This project will shift the paradigm of groundwater monitoring from a static process to a dynamic process to allow for the adaptation of resilient water management systems in response to climate change and variability. This study intends to achieve its aim by building a database of spatio-temporal hydrological, geological and physiographical, climate and groundwater level (GWL) variables for Ghana; developing AI algorithms and workflows for integration of varied data sources and prediction of groundwater availability and developing an open-source web-based application for rapid groundwater availability assessment to be used by stakeholders and the general populace. The rapid assessment of groundwater availability will make it easy to check the levels of groundwater in any location before deciding to site a borehole. The outcomes of the project include the development and scaling of responsible AI innovation for climate action; increased contribution of African research to international AI policy and practice through research publications and policy briefs; increased capacity of African innovators and researchers through the training of Masters students and water practitioners and the achievement of development goals as regards to water availability and its consequences (e.g., SDG 1, 2, 6, 13; Agenda 2063; National Water Policy; National Water and Sanitation Strategy; Ghana Poverty Reduction Strategy; Africa Water Vision 2025).

Objectives

The main aim of this research is to predict groundwater availability in Ghana in the face of climate change and variability. To achieve this, we will develop a system which will be made accessible to groundwater practitioners and the general public through a web portal. The name of the system will be Rapid Assessment of Groundwater Availability (RAGA).

The specific objectives of the project are:

  1. Build a database of spatio-temporal hydrogeological, climate and groundwater level (GWL) variables for Ghana.
  2. Develop AI algorithms and workflows for integration of varied data sources and prediction of groundwater availability.
  3. Develop an open-source web-based application for rapid groundwater availability assessment to be used by stakeholders and the general populace.