You may have not heard of them yet but you will see a lot of them this year.  510 is a Red Cross start-up hosted by the Netherlands Red Cross, they focus on using data and Artificial Intelligence to help  with Disaster Risk Reduction, Resilience and response.  Their work is complex but holds exciting potential for the Humanitarian sector

An example: how to use intelligent data for rapidly-identifying badly impacted areas after a natural disaster?

Identifying priority areas for humanitarian aid can be a time consuming task that can last weeks, due to unsuitable conditions, road blocks, lack of personnel, etc. This long process sometimes struggles to properly evaluate damage to housing and to recognize the number of people affected and can be inefficient.

510 has co-developed with a team of students, volunteers and staff a state of ‘artistic’ data-driven solution, the Priority Index, which predicts damage just hours after a disaster strikes. Organizations like the Red Cross and Red Crescent National Societies, governments or UNOCHA can use these results to better understand the impact of a natural disaster and mobilize a humanitarian response faster, and with a focus on the most vulnerable and damaged areas.

This methodology is able to process and learn from similar disasters that happened in the past by comparing historical impact data with secondary data, for instance population, disaster statistics, wind speeds and rainfall. The whole process forecasts areas that are most likely to be badly affected and should therefore be considered a priority.

An amazing progress

In October 2016, Typhoon Haima destroyed and damaged more than 198,000 homes and took at least 14 lives (AFP). The first Priority Index was released within the next 24 hours with an accurate prediction. A data analyst from 510 went to the Philippines to support the IFRC and Philippines Red Cross in the month after to understand and implement these kind of predictions into the decision-making process of the emergency response services. This contributed to a faster shelter response in the worst-hit communities.

After comparison with the final data on the distribution of damaged houses, provided by the Department of Social Welfare and Development (DSWD) and the National Disaster Risk Reduction and Management Council (NDRRMC), both had quite similar results, proving the initiative to be accurate and effective.

Read the complete story here.

What’s next?

This Red Cross start-up will be hosted by the Airbus BizLab Accelerator in 2017. It will aim to develop new and better machine learning methodologies that can be applied in different countries using local data, and to reach a fast and sufficiently accurate damage prediction rate through progressive iterations. Applied research on this objective is ongoing for Typhoons (Philippines), Earthquakes (Nepal) and Floods (Malawi).

Pin It on Pinterest

Shares
Skip to toolbar