ERC ArtiMinDev

The ERC Consolidator ArtiMinDev is about the impact of artisanal and small-scale mining sector on local economic development in Africa.

Start date of the grant: January 2024

Team: 

• Louise Inguehere (Data scientist)

• Mathis Mohand (Data scientist)

Resume: The widespread adoption of green energy technologies worldwide is poised to have a profound impact on mineral demand in the foreseeable future. The burgeoning artisanal and small-scale mining (ASM) sector, employing around 40 million people, accounts for approximately 20% of the global supply of gold and diamonds, 25% of tantalum and tin, and up to 80% of sapphire. These figures underscore the ASM sector's pivotal role in the energy transition.
The ArtiMinDev project aims to comprehensively analyse the economic and social impacts of ASM in sub-Saharan African countries. To date, the absence of comprehensive time-varying data on ASM locations has hindered social scientists from accurately quantifying the sector's contribution to economic development.
This project harbours a twofold ambition. Firstly, I intend to create a detailed map of ASM openings and closures in sub-Saharan African countries between 2000 and 2020, providing precise GPS coordinates for each site. Two additional critical pieces of information will also be gathered: the size of each ASM and the mineral being extracted. I will employ machine learning techniques and satellite image time series to identify sediment and open-pit mining activities. Secondly, armed with this groundbreaking dataset, I aim to provide systematic and large-scale evidence of ASM's impact on violence and conflict, environmental degradation and health, and internal migration.
Rooted in quantitative economics, the proposal's objectives span multiple literatures across a diverse range of disciplines, seamlessly integrating cutting-edge machine learning techniques and remote sensing data. I anticipate that both the methodologies and findings will significantly advance the research frontier in several dimensions. Moreover, the project's conclusions will prove highly valuable to policymakers and NGOs seeking to enhance the monitoring of ASM activities and their associated impacts on conflict, health, and environmental degradation.

Related work

"Mapping Artisanal and Small-Scale Mines at Large Scale from Space with Deep Learning",  with S.Di Rollo, L.Inguere, M.Mohand and L.Schmidt (2022) PlosOne

Abstract: Artisanal and small-scale mines (ASM) are on the rise. They represent a crucial source of wealth for numerous communities but are rarely monitored or regulated. The main reason being the unavailability of reliable information on the precise location of the ASM which are mostly operated informally or illegally. We address this issue by developing a strategy to map the ASM locations using a convolutional neural network for image segmentation, aiming to detect surface mining with satellite data. Our novel dataset is the first comprehensive measure of ASM activity over a vast area: we cover 1.75 million km² across 13 countries in Sub-Tropical West Africa. Our procedure is remarkably robust, which makes us confident that our method can be applied to other parts of Africa or the World, thus facilitating research and policy opportunities on this sector