MiningWatch — Belgium's Data-Mining Tool for Targeting Social-Fraud Inspections
Belgium
Since 2014, Belgium's federal social security service has used the MiningWatch data-mining tool to rank construction, cleaning and hospitality employers …
Ghana · Accra · See the Ghana profile · See the Accra profile
Top 83% 40/100 · Ask Evidence Copilot about this practice
Ghana's Minerals Commission runs a National Mine Surveillance Centre using drone imagery and AI to target illegal 'galamsey' mining, expanded from a Western Region pilot to Ashanti by 2026, though its Deputy CEO says policy still lags the technology.
Illegal small-scale mining, known locally as 'galamsey', has driven severe river and land degradation across Ghana's Western and Ashanti Regions, historically outrunning the Minerals Commission's capacity for manual, complaint-driven site inspections.
The Commission built a National Mine Surveillance Centre, launched in 2023, that feeds imagery from drones patrolling mining corridors into a central control room where AI models help flag unauthorised sites, assess environmental damage and check compliance with approved mining plans. The programme, run with the National Anti-Illegal Mining Operations Secretariat (NAIMOS) and the Ghana Police Service's Allied Police Unit, began as a pilot in the Western Region and had expanded into the Ashanti Region by February 2026.
Ghana's ICT-sector press has reported striking figures for the programme: AI-assisted detection accuracy rising from 58% in 2022 to 92% in 2025, average response time falling from five days to under twelve hours, a fleet that has grown past 120 drones, and an estimated ₵400 million in gold-smuggling losses prevented. Separately, in February 2026 the Commission's Deputy CEO, Emmanuel Kwamena Ayeme, publicly confirmed the real-time monitoring capability and its regional expansion, while stating that 'technology must be supported with clear, forward-looking policy' and calling for stronger legal frameworks and institutional capacity.
The accuracy, response-time and loss-prevention figures trace to sector-commentary reporting rather than an identifiable Minerals Commission audit or publication, so they should be read as indicative rather than independently verified. No source names the specific AI model or vendor involved, and the Commission's own deputy chief executive frames the legal and institutional framework around the technology as still a work in progress.
Read the full analysis: https://www.myjoyonline.com/ghana-deploys-ai-and-drones-to-shift-mining-regulation-from-reactive-to-preventive-minerals-commission/
Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.
Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.
Where this practice's information was retrieved from, and when.
Belgium
Since 2014, Belgium's federal social security service has used the MiningWatch data-mining tool to rank construction, cleaning and hospitality employers …
Chile
ChileCompra cross-checks officials' asset declarations against suppliers' beneficial owners, flagging conflicts of interest before contracts are awarded. In 2025, flagged …
South Korea
Ahead of April 2024 elections, South Korea banned AI-generated deepfakes in campaigning within 90 days of polling. The National Election …
Japan
MLIT runs a national catalog certifying AI and sensor-based bridge/tunnel inspection technologies against published performance criteria. Listings grew from 12 …
Open full copilot Grounded in cited practices — always check the sources.