Map it, then stop it: How volunteer cartographers are mapping epidemics and atrocities

Warning: Trying to access array offset on value of type bool in /customers/a/2/c/africanstudies.co.uk/httpd.www/wp-content/themes/mh-magazine-lite/includes/mh-custom-functions.php on line 144 Warning: Attempt to read property "post_title" on null in /customers/a/2/c/africanstudies.co.uk/httpd.www/wp-content/themes/mh-magazine-lite/includes/mh-custom-functions.php on line 144

ON MAY 9th, the day after the first cases of Ebola were confirmed in Bikoro, an urgent request came into the headquarters of Médecins Sans Frontières (MSF), an international charity. Maps of this part of the Democratic Republic of Congo were needed to deliver vaccines and medical help. Yet accurate ones did not exist.

MSF turned to the crowd for help. Volunteers, trained using an online tutorial, started analysing satellite pictures and drawing maps. About 450 volunteers have already managed to plot some 67,000 structures and 1,000km of roads in the area of the outbreak, completing in days a task that could have taken months. Some of these new maps (see above) are already in the field.

This is not the first time humanitarian organisations have turned to crowdsourcing to help gather data. When Ebola spread through parts of west Africa in 2014, more than 3,000 people around the world helped add some 16m features to maps of the affected area.

Crowdsourced mapping is also proving useful in protecting human rights. Amnesty International, a watchdog, has used volunteers to map 326,000 square kilometres of Darfur, a troubled part of Sudan, to help identify war crimes carried out by the government. First they used satellite imagery to locate and mark villages. Then some 6,000 activists looked for changes over time—buildings that had lost their roofs or fences that had been torn down—as indicators that villages had been attacked.

The next step is to try to automate this labour-intensive task. Amnesty is working with computer scientists at University College London to develop algorithms that can mimic the work of volunteers in mapping structures and spotting when they are destroyed. Preliminary results show a 97% accuracy rate. Applying such algorithms to mapping areas affected by pandemics could mean maps are produced even faster, increasing the chances of containing outbreaks before they spread too far.

First published by The Economist.

Edited by NIAS.