Cycle 9 (2020 Deadline)
Long-term impacts of land-use/land-cover dynamics on surface water quality in Botswana’s reservoirs using satellite data and artificial intelligence methods: Case study of the Botswana’s Limpopo River Basin (1984-2019)
PI: Yashon Ouma (yashon.ouma@mopipi.ub.bw), University of Botswana
U.S. Partner: Jiaguo Qi, Michigan State University
Project Dates: May 2021 - March 2024
Project Overview:
The rising demand for water, food, and energy due to increasing population continues to create immense pressure on water resources. In particular, water quality around the globe is systematically degrading, primarily due to climate change and agricultural intensification associated with rapid population growth and urbanization. In-depth assessments of the inter-linkages between land–water resources that combine land-use and water quality and availability within the catchment supply chains such as the Limpopo River Basin (LRB) in southern Africa are still lacking.
For water supply, semi-arid Botswana relies on the reservoirs within the Botswana’s LRB. Reservoirs are particularly susceptible to the negative impacts of land-use and land-cover (LULC) activities and runoff because of their complex dynamics, relatively longer water residence times, and their role as an integrating sink for pollutants from their drainage basins. Despite these interrelationships and significance in regional and global economic stability, land and water (L-W) are often treated in “silos”. To understand the complex L-W nexus within the LRB, this study will use data-driven artificial intelligence for quantitative determination of the relationships between LULC change, together with socioeconomic development indicators and climate change, and their impacts on water quality and availability within the basin, both for 1984-2019 and to predict future scenarios (2020-2050). To advance data acquisition for LULC analysis and climate change, the study utilizes optical Earth-observation and meteorological satellite data. To provide near real-time and cost-effective approach for continuous monitoring of reservoir water quality within the basin, the study will develop empirical models for water quality estimation and water quality index mapping using 35-years of in-situ water quality measurements and water spectral observations using drone-borne spectrometer and optical satellite imagery through regression modeling and geospatial methods.
This project addresses the scope of the solicitation by quantifying land change trajectories in an important region in southern Africa, understanding the physical and social causes and impacts of these dynamics on water quality, thereby advancing land change science and water quality dynamics, while providing policy relevant information on governance options. The project speaks to and will contribute towards Botswana's Sustainable Development Goals as mapped in the National Development Plan (NDP11) and Vision 2036 pillars on sustainable development, sustainable environment, and sustainable use of natural resources. The study results will be beneficial to the government policymakers and development partners including the USAID Southern Africa Resilience in Limpopo River Basin (RESILIM) project, the Limpopo Watercourse Commission (LIMCOM), and government ministries, including the Ministry of Land Management, Water and Sanitation Services (MLMWSS). Specifically, the study will contribute to the USAIID-RESILIM and LIMCOM work on the enhancement of the resilience of the people and ecosystems within the water-stressed Limpopo River Basin.
Summary of Recent Project Activities
In a joint field work campaign with the Water Utilities Corporation (Botswana), the PI and his team successfully carried out their planned water quality sampling for the Bokaa and Gaborone dams in December 2022. This included simultaneous UAV-drone imaging. Data from Sentinel-2 MSI and Landsat-8 ETM+ satellite sensors were downloaded, and the researchers then focused on modelling their water quality predictions with data from the sensors. The field work also involved land-use and land-cover classification ground-truth campaigns within the dam catchments.
Five final-year undergraduate student projects are continuing in the 2022/2023 academic year using the project UAV-drone, project data, and algorithms. These included demonstrations and hands-on implementations. While continuing with the set objectives, in the first half of 2023 the project team is working on new products with the potential of impacting the monitoring of water resources and development of management policies in the critical river basins within the region and specifically in Botswana's Limpopo River Basin. The tools will be used to demonstrate the concept and to inform stakeholders and policy makers on the role of Earth Observation and Artificial Intelligence (AI) tools in managing water resources for resilience under climate change and human influences as manifested in land-use and land cover change. Based on the concepts and preliminary results presented to Water Utilities Corporation (WUC), WUC is engaging with the project to test the potential, efficiency, and cost-effectiveness of dam water quality monitoring using UAV-drones and satellite imagery. The team is also working on an automated tool for mapping and monitoring the variability and impacts of climate change on dam reservoir water quantity using cloud computing within the Google Earth Engine (GEE). Other tools being developed include machine learning techniques for land-use land-cover (LULC) mapping and change detection, integrated with artificial intelligence to determine the long-terms impacts of LULC on reservoir water quality, and an automated GEE online-based dam water body surface area mapping tool using water indices.
In the process of implementing the project, observations have shown a critical shortage of expertise in the areas of Earth Observation, Big Data analytics, and AI-based competencies. To bridge the gap, a postgraduate program intended for graduates who will be involved in the acquisition, processing, design, and development of photogrammetric, remote sensing, geoinformatics data and computational analytics has been proposed. The rationale for the MSc in Geomatics in advancing training and specialization in Geomatics through postgraduate studies to meet the emerging national and regional demands and challenges in the public, private sectors, and academia. The PI reports that the Master of Science in Geomatics (Photogrammetry and Geoinformatics) degree program has been pre-approved at the Botswana Qualifications Authority (BQA) and approved at the Department and Faculty levels, with the potential to start by the next academic year, August 2023. Admissions will commence after University Senate and Council approvals.
At the time of his last report in April 2023, Dr. Ouma and his group were planning for a second water quality sampling campaign later that month, and they expect to host U.S. partner Dr. Jiaguo Qi during the summer. The researchers will continue to work on data collection, analysis, and upscaling of their pilot-scale models and algorithms. They expect to publish two more papers by July and are planning to organize a stakeholder outreach workshop to showcase the influence of land-use and climate change on dam water quantity.
Publications
Ouma Y.O., Keitsile, A., Nkwae, B., Odirile, P., Moalafhi, D. and Qi, J., 2023. Urban land-use classification using machine learning classifiers: comparative evaluation and post-classification multi-feature fusion approach. European Journal of Remote Sensing, 56(1), p.2173659. https://doi.org/10.1080/22797254.2023.2173659
Ouma, Yashon O., Ditiro B. Moalafhi, George Anderson, Boipuso Nkwae, Phillimon Odirile, Bhagabat P. Parida, and Jiaguo Qi. 2022. Dam Water Level Prediction Using Vector AutoRegression, Random Forest Regression and MLP-ANN Models Based on Land-Use and Climate Factors. Sustainability 14, no. 22: 14934. https://doi.org/10.3390/su142214934
Ouma Y.O. et al., 2022. Predicting the variability of dam water levels with land-use and climatic factors using Random Forest and Vector AutoRegression models. SPIE Remote Sensing 2022 Remote Sensing for Agriculture, Ecosystems, and Hydrology XXIV, 122620J. September 6-9, 2022, Berlin, Germany. https://doi.org/10.1117/12.2635933
Ouma Y.O. et al., 2022. Comparison of machine learning classifiers for multitemporal and multisensor mapping of urban LULC features. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLIII-B3-2022, XXIV ISPRS Congress (2022 edition), pp. 681-689. June 6-11, 2022, Nice, France. https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-681-2022
Ouma Y.O. et al., 2022. Land-Water (L-W) Nexus Project: Impacts of Land-Use & Climate Change on Water Quality and Quantity in Botswana's Limpopo River Basin (BLRB). United Nations/Ghana/PSIPW - 5th International Conference on the use of Space Technology for Water Resources Management. Accra, Ghana, May 10-13, 2022. https://www.youtube.com/watch?v=YXjWnaxTXDg
Back to PEER Cycle 9 Grant Recipients
|
