P087_Kenya_Uganda_South Africa
Monitoring, Management and Mitigation of Environmental Challenges with Collaborative Data Analytics and Machine Learning for Sustainable Development
Cooperating countries: Kenya, Uganda, South Africa and Austria
Coordinating institution: Johannes Kepler University Linz, Ismail Khalil, ismail.khalil@jku.at
Partner institutions: African Centre for Technology Studies, Gulu University, Maseno University, Nkumba University, University of Pretoria
Project duration: 1 July 2023 - 30 June 2025
Abstract:
The United Nations’ Economic and Social Council has identified seventeen Sustainable Development Goals [2]. Several if not all of these goals face or specifically identify environmental challenges.
This is particularly and obviously the case of Goals 6, 11, 12, 14 and 15. They collectively concern the conservation and management of the planet resources and the design and implementation of sustainable development, consumption and production. Environment challenges are nonetheless major concerns for all the other goals as they have direct and indirect impact on all economic, social and political issues.
The objectives of the project is two-fold: At the social and economic level, the project aims to collect the data necessary for the intelligent monitoring, management and mitigation of environmental challenges. At the technical level, due to the fact that this data comes from distributed, heterogenous autonomous sources, and it may have different quality, modality and media, novel tools are required for the modelling, analysis and optimized control of complex systems. For which, the project devises new collaborative approaches that combine the sensing, analysis and optimization capabilities of the crowd, sensors and algorithms. The team wants to build surrogate models using machine learning tools for the simulation of various environmental challenges such as climate instability, loss of species, decreased bio-diversity, floods, and various forms of pollution and to contribute to the optimization of industrial symbiosis processes. In addition, of particular importance is the reliability of the results. We propose to adapt sensibility analysis techniques to evaluate the sensitivity of the results.