Where we work: Limpopo Basin
Digital Innovation’s work in the Limpopo Basin in Southern Africa (Botswana, Mozambique, South Africa and Zimbabwe) includes the following activities:
Digital Twin: Timely and actionable drought forecasts
Southern Africa is highly drought-prone, and its agricultural and hydrological systems are vulnerable. Climate forecasts provide tools for decision-making and adaptation to climate extreme events. Using multiple climate-relevant datasets, we first developed the climate diagnosis of the Limpopo basin and the relevance of using the SPEI drought index for characterizing droughts. The results showed strong climatic seasonality, in addition to the strong relationship between the seasonal drought conditions captured by SPEI. Based on the diagnostic study outputs, we are developing seasonal drought forecasts for the Limpopo River basin using four climate models, gridded rainfall observations, and a machine-learning method that generates a real-time probabilistic forecast of rainfall across the basin.
Digital Twin: AI-based water quality monitoring for management
Deteriorating water quality is a global challenge, more so in surface waters. Traditional methods of monitoring water quality are human resource intensive and require the active involvement of technical personnel in remote environments. The miniSASS was developed as a citizen science tool for monitoring the health of river systems and reflecting the water quality through assessing macroinvertebrates communities. The miniSASS samples the macroinvertebrate community in a river reach and compares the community present to the expected community under ideal natural conditions. The information garnered during a survey relies heavily on the accurate identification of macroinvertebrates by lows killed citizen scientists. This leaves a potential for errors in identification which may impact the accuracy of results and, ultimately, of the river health assessment. In response, we initiated the development of a smartphone application with built-in AI/machine-learning algorithms for the automatic, real-time identification of macroinvertebrates.
Digital Twin: 3D hydrodynamic modeling
To support the implementation of environmental flows (e-flows), we piloted a three-dimensional digital modeling approach to monitor the changes in river ecosystems. A high-resolution 3D model of study sites in the Crocodile River, South Africa, was constructed and used to test its utility and value to monitor changes in river ecosystem structure over time. The initial demonstration of the approach shows highly detailed 3D models of nine tracks across the study sites. The output represents the velocity-depth and bathymetry variability of each site in 3D. The dataset successfully demonstrated the potential value of adopting the approach for e-flow implementation to monitor the habitat dynamism to support the timely management of river health. In the next phase, this assessment will integrate the 3D modeling approach into a hydrodynamic modeling framework to investigate dynamic relationships between flow-ecosystem and ecosystem services.
Digital Twin: A user-friendly environmental flow assessment tool
The original PROBFLO was developed as a holistic environmental flow (e-flow) assessment tool. PROBFLO evaluates the socio-ecological consequences of various water resource scenarios and generates e-flow requirements on a regional spatial scale. It follows the ecological risk assessment exposure and effects approach, with multiple stressors, habitats, and ranked ecological impact relationships. Due to the complexity, PROBFLO is currently only used by skilled scientists. As a response to the demand partner in the Limpopo River basin, we are developing a new version of PROBLO in collaboration with the World Modeler program. The new version will be equipped with a user-friendly interface and streamlined workflow to make the tool more accessible to stakeholders.
Read about the Initiative’s other focus countries and regions: