42  people killed, 145 hurt and more than 90 000 people evacuated. Those are the numbers of people affected by the wildfires that scorched the state of California last October. These fires destroyed more than 8500 structures, causing an estimated economic loss of 3.3 billion dollars. But these are only the direct costs. A part of California’s economy relies in wine production and the vineyards associated, some of which have burnt.

Up until last week, California was suffering also the Thomas fire in the area of Ventura, a wildfire that was active for more than a month, and is now considered the biggest wildfire in California’s history.  As of now, the economic impact that these wildfires will have in the future remains incalculable.

Figures as gigantic as these ones usually escape our comprehension. To understand the magnitude of these disasters, we can take a step back and try to see the big picture. To help us in this task, we can rely in satellite images. We have talked before about how satellites can help us tackling disasters, but now, thanks to the efforts of our colleagues at Terranea, we are able to show you how we can use Sentinel-2 imagery to estimate the area affected by wildfires.

Seeing through smoke

Image taken in the optical band
Image taken in the shortwave-infrared band

Almost half of the Earth’s atmosphere is covered by clouds all the time, so if we want to keep surveillance of a wildfire from space, we must be able to peek through the clouds and smoke.

Sentinel-2 satellites are equipped with a high-resolution multispectral imager. This means that they can take the same photo in different parts of the electromagnetic spectrum, from the visible (the image on the left, very similar to what you would see with your naked eye) to the shortwave-infrared (image on the right). This last one is the one that allows us to have a glance through the smoke, and spot the active fires underneath: the orange lights that you can see in the photo are the fires that were active the 12 of October.

Estimating the impact: before and after

Image taken before the fires
Image taken after the fires

The technology on board Sentinel-2 is able to identify the different types of land and vegetation underneath: shrubland, evergreen forest, pastures, vineyards… You name it, Sentinel-2 is able to identify it, like an avid landscaper. This allows us to make a before and after comparison —the dark areas that you see in the photos above are the areas burned by wildfires. Our colleagues at Terranea develop workflows to process the data fully automatically and compose the map that you can see below.

Image showing the area afected by wildfires

A total of 8.45 square kilometers of vineyards were burnt in the Napa Valley in October. That’s three times the area of Hyde Park, in London. In comparison, the Thomas fire that is currently active in California has been estimated to have burned more than 1000 square kilometers in Ventura and Santa Barbara counties, affecting almost 1000 buildings, and forcing 41200 people to evacuate. The types of land cover affected is still to be determined, but the Copernicus satellites will allow us to better estimate the impact of these fires, and study their progress, so we can be best equipped the next time it happens.

This last month has been a busy one for I-REACT. We completed the first half of the project, and presented our technology for the first time ever. But we haven’t stop there. This month we also organised two workshops: one in Boston, USA, and the other one in Incheon, South Korea.

In them, we were able to gather selected groups of professionals to discuss how modern technologies can be integrated in the fight against disasters, and the different solutions we are developing. Just so you do not miss anything, here is our brief summary of the two workshops:


The I-TENDER workshop focused on how public safety services can benefit from the use of technology to respond against disasters. Claudio Rossi presented a Keynote on I-REACT project, while the other 9 presentations presented papers on how to use data analysis to filter relevant information on a disaster situation; how positioning techniques can improve the response and safety of rescue parties and emergency responders; and how technology helps in the deployment of public-safety and emergency networks.

The workshop took part in Incheon, South Korea, on December 12 and was hosted within the ACM CoNext Conference. A list of all the papers presented at the workshop can be found here, and more information on the workshop can be consulted here.


The Data Science for Emergency Management (DSEM) was centered on the role of Big Data and Data Science in the natural hazard management area.

The keynote speaker, Prof. Carlos Castillo, presented an overview about the current state of the art on the Big Crisis Data topic and provided interesting insights on a better exploitation of crowdsourcing solutions. The DSEM workshop featured papers on novel and innovative solutions for emergency management: social media and unstructured data, crowdsourcing and user feedback, forecasting models, decision support systems, and resource allocation and crowd control during emergencies.

The workshop was held on December 11, 2017 in Boston, USA, co-located with the 2017 IEEE International Conference on Big Data. A list of all the papers presented at the workshop can be found here, and more information on the workshop can be consulted here.

We close this 2017 with a lot of activity,but we are not stopping here. This 2018 we are organizing a workshop within the ISCRAM 2018, the 15th International Conference on Information Systems for Crisis Response and Management. The workshop will be in May, but the deadline for submitting your paper is on January 15, so send it now!