Mining-induced displacement and livelihood restoration: A data-driven approach

Mining-induced displacement and loss of livelihood assets are extreme social impacts that affect host communities. This research directly addresses the challenges faced by displaced subsistence farmers who must secure alternative agricultural land to rebuild their livelihoods by exploring how the resources of the mining project can be leveraged to help these farmers identify suitable arable land. The study demonstrates how data collected during mining exploration can be repurposed to assess the agricultural potential of nearby land, and effective ways to communicate this information to affected farmers. The research introduces a data-driven land evaluation approach that contrasts with traditional expert-dependent methods. Using a case study in Burkina Faso, maximum entropy modelling (MaxEnt) is applied to identify suitable land for locally grown crops by integrating crop planting locations from community land use maps—originally produced for compensation assessments—with environmental data. The mining exploration data were successfully combined with publicly available datasets using free and open-source software to generate crop suitability maps that were then tailored for illiterate and semi-literate users. The findings highlight how mining exploration data and spatial technologies can support agricultural planning and aid displaced farmers in securing better agricultural outcomes. The method is transferable to diverse environments and agricultural systems and is particularly suited to mining applications in developing countries where detailed agricultural data is collected during environmental and social impact assessments. This scalable and resource-efficient approach provides a valuable tool for enhancing livelihood restoration of farming communities following mining-induced displacement. • Data by-products of mining exploration enable land suitability assessments. • Cropping potential inferred from mining data aids restoration of farming livelihoods. • Compensation maps facilitate data-driven crop suitability modelling using MaxEnt. • Data fusion of categorical and continuous maps improves environmental prediction. • Maps for illiterate map users assist livelihood restoration for displaced farmers.