Citizens with drones can help fighting natural disasters

It was not by chance that drones became the gadget of the year in 2014. By then, thousands of units were being sold worldwide with prices ranging 30€ to 30,000€ and big electronic retailers were reporting huge surges in sales. Now, a few years down the line, this trend has continued in the rise and drones are a relatively common leisure for taking pictures and shooting impressive aerial videos. However, did you know they can also be used to fight disasters?

After Typhoon Haiyan hit the Philippines in 2013, an unprecedented number of drones patrolled the skies to aid in the humanitarian response. Thanks to this, a much rapid mapping of the affected areas was possible, which was essential to setting up humanitarian base camps, detecting the most affected communities, locating victims in need of help, and assessing the state of infrastructures for transportation, among others.

The importance of drones in disasters is that they provide a quick view from above of the affected zone. For decades, this information was only obtainable using planes for aerial photos, or satellites, which have a number of limitations including cost, data sharing restrictions, cloud cover, and the time needed to acquire images. In contrast, UAVs can provide a bird’s eye perspective quickly, if people are at site, and at a far higher resolution and at much lower cost.

An additional key aspect is that drones can also offer a view that is not perpendicular to the ground. For instance, when assessing damage after the disaster, whereas satellite vision allows seeing if a building has a roof but not if it has four walls, oblique vision from drones can answer this question and many others that require more three-dimensional information.

But overall, the biggest advantage is that, unlike satellites, citizens can own UAVs and this means that disaster-affected communities can participate in response to a crisis. Now, after major disasters such as the Philippines typhoon, but also the Haiti earthquake, these countries have taken the lead in involving citizens and there is a growing number of grassroots initiatives to teach local people to operate their own drones in emergencies.

At the I-REACT project we believe in the potential of citizen participation in disaster response at European level and we are developing an app that will allow connecting emergency professionals and drone users. Our partner AnsuR is leading this task to allow decision makers at control centres to request and conduct flights over affected areas, both from amateur and professional drones, in case of floods, fires and extreme weather events. This ways, they will be able to assess and ensure the relevance of the images while drones are still flying.

In order facilitate the engagement of volunteers from local areas, AnsuR is building a database for drone volunteers who potentially can be involved in the event of an emergency in their area of operation, and creating a efficient system for communicating the images they capture. This way, any European citizen from local communities can become an integral part of the fight against disasters, improving rescue operations and protecting their communities.

If you own a drone and would like to contribute, drop us a line and join us in quest for a more resilient future!

,

Predicting the next heatwave

This year organisers at Royal Ascot horse races announced that they are considering relaxing the strict dress code for the first time in history. And this is because Europe is scorching. This summer, from London to Siberia, stifling heatwaves are razing across the continent in an unprecedented fashion. And this summer is not the exception. Due to climate Change, heatwaves are becoming more and more frequent. And, even if they have been considered a minor hazard that do not affect infrastructures as much as floods, fires or earthquakes, they are still heavily impacting on the population.

Because, although Royal Ascot’s may seem like a funny anecdote, only in UK, this year there were 907 deaths more than the average after the mercury rose to 38.1c. This shows how problematic heatwaves can get, especially for vulnerable sections of the population, such as children, pregnant women or the elderly. And besides their effect in public health, their impact on agriculture can be also devastating as new research points out that they will damage crops, worsening the global food crisis.

But, what can be done to overcome the effects of these waves of extreme temperatures?

To anticipate to any disaster, the best thing you can have at hand is a good prediction. And you may lay aside crystal balls and tarot cards. Or hunches. There are scientific, accurate, and real tools to succeed: the so-called risk models.

Take temperature, relative humidity, wind speed, and rainfall and relate them with some mathematics and you will be able to unravel the risk of a wildfire. Or combine them with a terrain elevation model, soil properties and drainage directions to make your own flood risk model to be prepared when the water rises after the next perfect storm. For heatwaves, maximum temperature is the parameter you need to have under the radar.

Put in this way it could sound straightforward, but creating a risk model is a huge scientific challenge. It takes time to select the correct parameters and design the proper equations that define the process you want to understand to the limit of prediction. Sometimes there are pre-existing models available and tuning them a little bit is easier, as you can add small adjustments and validate them with as much data as you can find. Or you can even be luckier and leverage upon open risk model services where you can extract processed risk information.

In I-REACT we are combining all these options for the most common hazards: floods and fires. We are extracting data from European services (EFAS and EFFIS) and adapting and improving different pre-existing models for these hazards. But for heatwaves we need a brand new solution combining models in a decision-support system. Because, although fires and floods have been studied for several years, heatwaves are the new kid on the block of hazards and there is no European-wide available service or model for this phenomenon. That’s why our partners at Fondazione Bruno Kessler (FBK) are working on one of the first European-wide heatwaves geospatial risk maps. And novelty always comes with extra challenges: combining 32 years of temperature data with high resolution 14 days forecast for real-time emergency surveillance.

It is expected that by the end of the year, we will have up-and-running our top-notch geospatial risk models for fires, floods and heatwaves. Altogether, they will be a the most complete tool to date to anticipate these hazards.

Until then, please, follow the common instructions: drink water frequently, restrict activities in the open air to morning and evening, when possible remain in the shade and find something fresh that suits you for the horse’s races.

 

The I-REACT consortium successfully concludes the First Year Review

We are one year closer to having the most advanced technological solution to prevent and fight disasters. This was the impression after the meeting held at the Finnish Meteorological Institute premises, on the 22nd and 23rd of June. At the event, the 20 partners of the I-REACT consortium reviewed the progress of the work and agreed on the next steps towards the finalisation of a emergency management system to be validated in real scenarios next year.

At the moment, the project is deeply immersed in the implementation phase, with intense activity in the three technical work packages that are the core of I-REACT. As part of the initial effort, the project has been actively working on the integration of existing data sources and systems related to natural hazards, in particular floods and fires, to fuel the overall system with useful information. These data sources includes existing ones such as Copernicus or local EMS as well as the Sentinell-1 satellite, whereas other information is currently being generated, such as the I-REACT historical disaster database. 

Discussion around the creation of the historical disaster database led by Gunter Zeug (Terranea).

Sequentially, several partners are working on how to model these data to extract additional valuable information, which include climate change and weather forecast models or social media analysis. Finally, this information will be channelled and made available to end-users thorugh serveral technologies including a decision support system, a web interface, or, remarkably, a wearable for which the first prototype is available.

Presentation of the I-REACT wearable prototype by Srdjan Tadic (Bitgear).

Overall, the progress of the work has been very successful and the increasingly stong consortium is facing the coming efforts with the confidence that an effective solution to disasters will be market-ready in less than 2 years time.

Group photo of the I-REACT team at the Finnish Meteorological Institute premises.

The latest wearable technology to help rescue teams

A trend in technology is the one that does its job without you even noticing. This is the basis of wearables, whose ever expanding list of application ranges from capturing body parameters to sleep quality. But wearables are now much more than just leisure gadgets: their ability to report positioning and sense the environment can bring about a revolution to many professional fields. This is especially true for disaster response.

Although the forefather of wearable technology is a miniature Chinese abacus ring from the XVII th century used for mathematical calculations, the first popular reference are wristwatches. Since the early XX century they dominated the market and evolved into different uses until they were progressively replaced by cellphones and other more recent wearables. Consumer market is flooded with devices equipped with different sensors for activity tracking, heart rate or oxygen level monitoring. There are literally thousands of very low-cost fitness, health or wellness-oriented wearable devices. But also, among the mainstream markets there are various medical and assisted living devices for continuous health monitoring. Wearable technology thus helps the growing number of patients overloading hospitals and medical centers, while increasing their life quality.

Today the most distinctive feature of wearable technologies is the ability of exchanging data without human intervention thanks to electronic sensors and new firmware/software. This passive gathering of data is particularly crucial in the event of an emergency where the capacity of professionals for acting is very limited by time. In this scenario, capturing information about the status of the environment (e.g. temperature, air quality etc.) and of the rescue teams (location, activity, vital signs etc.) can be critical.

Wearables are commonly used in disaster response with examples like the wristband of Morphix technologies for the detection of hazardous chemicals, among others. However, the technology is not exploited in its full potential. As part of I-REACT, the Serbian company Bitgear is in charge of the development of a wearable for first responders that will be the first device applied to disasters with both positioning and sensing capabilities.

3D representation of the I-REACT wearable

The advanced navigation technology provides a much more accurate position than regular GPS, that can have high deviations of accuracy and large positioning errors in urban environments. For this, Bitgear is using a multi-constellation receiver which combines raw satellite navigation data not only from American GPS but from the European Galileo/EGNOS and Russian GLONASS. The integration of different sources with the processing of raw data through algorithms and coupling with the inertial sensors (INS) provides a much reliable positioning than any portable device used in disasters nowadays. Bitgear is also working towards expanding the initial device concept to state-of-the art real time location system (RTLS) that will combine Ultra-wide band radio (UWB) to provide indoor positioning of the rescue teams at critical situations.

The functionality of environmental sensing will be used for the detection of risky scenarios for first responders. For instance, if the oxygen level drops only four percentage points from the standard level (21%), this can impair coordination and judgement of the rescue teams. Thus, anticipating this environmental changes is essential. Also, by assessing the drops in oxygen levels we can obtain another relevant information as they might indirectly indicate the increase of toxic gasses. Thus, with the I-REACT wearable, rescue teams will know when they need to wear masks when necessary to prevent poisoning.

The I-REACT wearables will be connected via low-energy bluetooth to the mobile app developed in the context of the project. This way, the sensing and positioning will be sent to the big data structure and readily provided to decision makers at control centres.

For the implementation of this technology there are a number of challenges. On the technical side, the design of electronic devices for harsh environments, such as those found in emergencies, is always complex and requires good materials and insulation. Another challenge is posed by the proximity to the human body since it absorbs electromagnetic energy, which degrades the signal of the device. So the materials, the position of the antenna, the topology of the electronics have to be tweaked. Finally, one of the most important issues is to build the smallest possible device to avoid overloading of responders that are already forced to carry many gadgets. To this end the miniaturisation process will be very centred in the efficient placement of oxygen sensors, as these are usually very bulky, and minimization of obstruction of radio signals.

To date, different functional wearable prototypes have been produced and they are in the process of performance evaluation and environmental testing. Also, different options for boxing are under development. All in all, the device should be ready by the end of this year.

The application of wearables to the I-REACT project holds the promise of a safer and more effective coordination of rescue teams, and demonstrates that overall technologies are an essential ally to fight disasters.

The I-REACT team meets with the Sava River Commission and the World Meteorological Organisation

As the development of I-REACT is increasingly more tangible, our team is doubling efforts to contact the diverse stakeholders that could benefit from the technological solution of the project. This week has been particularly noticeable in this respect, with the celebration of several meetings that have led to the establishment of important connections.

On June 13th, our team was invited to meeting the International Sava River Commission to collaborate in the implementation of a new Early Warning system for floods funded by the World Bank. This system was presented in an advanced version under the name of Flood Forecasting and Warning System in the Sava River Basin (Sava FFWS), and was demonstrated to be ready for implementation. At the meeting, different ways of collaboration were explored. On the one hand, the possibility of integrating their data in the I-REACT platform was explored whereas, on the other, the consortium offered to provide different unique information derived from satellite modelling, social media analysis and citizen reports, for a better management of disasters in the region.

Sava River floods in 2014 (source Balkanist Magazine)

Later in the week, another meeting was held in Ljubljana hosted by the World Meteorological Organization (WMO) and the US Agency for International Development (USAID). The meeting was focused on the implementation of the South East European Multi-Hazard Early Warning Advisory System (SEE-MHEWS-A), a large joint initiative for improving meteorological, hydrological and marine forecasting, through the enhancement of modelling, nowcasting, ICT infrastructure and data provision. In this context, our project will contribute to this large effort with novel products and services, from the crowdsourcing of information to the gamification of citizen reporting.

Important conclusions were extracted from both meetings that are in line with the efforts of our project. Emphasis was made towards people-centered systems are key in order to reduce the impact of disasters, and on the communication effort to create a risk-informed society. Overall, the contribution of I-REACT was appreciated in supporting the integration of citizen data, in the communication of warnings and risk awareness information through mobile phones and social media, but also in the creation of a Cloud based ICT infrastructure that is scalable, reliable,  flexible, and capable of handling Big Data in real-time. To this end, the modular architecture of I-REACT will allow interoperability with existing systems and provision of added value data and service to other initiatives such as Sava FFWS and SEE-MHEWS-A, at transboundary, EU, and global levels.

Local predictions of global changes: a carbon-disaster footprint

When we hear of climate change and global warming, images of ice cracking in the Arctic come to our minds and, with them, the possible catastrophes that can occur in coastal areas when the ice melts and sea levels rise. This is the classic image of a disaster caused by climate change, but there are more.

From the meteorological point of view, the relationship between climate change and natural disasters is full of examples. Because not only the ice melts, but also the oceans water heats up. An increase of ocean heat in some tropical regions can cause more convection activity producing extreme hurricanes and severe floods. Likewise, an increase of temperatures or a change in rainfall in some arid regions can cause severe droughts never experienced before. What is worse and concerning, if these two last events occur consecutively in the same region, flooding in an arid zone without vegetation -that normally holds the soil together- will lead to large landslides and, with them, great economic and natural losses.

This occurs globally, but nowadays it has local impact in areas of the planet that had never suffered catastrophes associated with this kind of extreme weather events. And many of them are not prepared. Our climate is changing and, particularly, extreme events can vary in their location and their frequency. Then, we must work to anticipate the future local impacts of this progressive global change. But, if predicting the short-term weather is sometimes tricky, how can we guess what will happen in 20, 50 or 100 years?

For this challenging task, we need the so-called Global Climate Models. These are mathematical models that take advantage of the power of computing and specialized software designed to solve the equations that describe meteorological phenomena. These models simulate what has happened since 1850 -just before the start of the Industrial Revolution- and what will happen until 2100.  The outcome of Global Climate Models are simulations, analysed as with a range of different scenarios and probabilities, of climate change that help us understand the uncertainty of this phenomenon. The models take into account the initial conditions (also called internal variability), the errors due to the lack of knowledge in some physical processes and also the unknown influence of other external perturbations in the future (such as the increase of atmospheric CO2, which is the main culprit for global warming).

The results of Global Climate Models have a very low spatial resolution, since these models study the Earth in grids of about 300km2 describing global scale phenomena, reason why we need to downscale them to obtain a much larger resolution and local impact of climate change. Our partner METEOSIM oversees developing downscaling techniques and adapting this valuable information to our I-REACTOR system. They are responsible for generating, calibrating and validating models that will tell us how likely certain European regions will suffer from these extreme phenomena due to climate change.

This information will be linked to that obtained with the technologies we both exploit and develop in the project and will enable us to implement emergency prevention throughout Europe with unparalleled accuracy.

Having this data under our control is a tremendous advantage but is not the only prevention action we can take. On an individual level, we can try to reverse the road to 1850, to see if luckily, we can reduce day by day our carbon footprint and the disasters it entails.

“During emergencies reality is not enough”

Imagine a fire at its peak. There is smoke everywhere and high flames that impair the vision. In this scenario, the actions of first responders are very compromised. But imagine again that this reality is not all they see. Through their glasses, they are able to know the position of all the team members, get information about the terrain and communicate with the control centre. This way they can make fast choices and act to tackle the emergency in a short time. Although you might think this scene belongs to the domain of fiction, it’s more than real: it’s Augmented Reality.

Augmented Reality is a technology used in devices to complement our vision with a virtual layer of information. Although its use in disasters is relatively new, the technology has been successfully applied to other fields since its development in the late 1960s. One of the first uses were attributed to the Air Force allowing military to control virtually guided operations. After, it was applied to advertising, tourism, industry and to the video games sector, with the recent exponent of Pokemon GO.

“Since Augmented Reality enhances our senses, its use in disaster situations can be crucial: during emergencies, reality is not enough” comments Giorgia Sassi Communication Manager at JoinPad, an Italian company specialised in this technology. As part of the I-REACT project, JoinPad is currently applying Augmented Reality to create smart glasses applications for first responders. “Either through an object recognition algorithm or through geolocalisation, the technology will able to identify objects in the responders’ field of vision and add important data to aid operations”, explains Sassi.

These glasses will condense all the information from the field and show it to the first responders. Agnese Ragucci, Interaction designer at JoinPad, explains that this way “they will be able to know the position of other teams, the missions assigned to each of them, alerts or warnings in the surroundings or even get help to navigate to assets or points of interest”. In addition, thanks to this technology, responders will be able to report from the ground without using their hands through videos, voice and text. “In I-REACT one of important tasks is to investigate speech-to-text and text-to-speech algorithms to enrich the user experience” adds Ragucci.

The project’s smart glasses offer another radical advantage by enabling the formulation of precise instructions from the control centres to the responders. “One of the biggest limitations in disaster response is when the operator has to describe the scenario remotely through a mobile phone and then be able to interpret the instructions in a very short timeframe” explains Ragucci. However, the I-REACT glasses will overcome this limitation as they are coupled to a camera to send videos to the control centre. “With our smart assistance system, the first responders will become the eyes of the decision-makers, which will greatly improve the operation efficiency and speed up the reaction times” she adds.

Whereas big efforts are being made in the I-REACT consortium to collect and process information from multiple sources, the role of JoinPad is to ensure that this information is provided to the end-users in the most effective way. “Our main challenge lays in the user experience”, explains Ragucci, “we have to be careful to provide the best information, at the right time and in clear and simple way”. “The information will be provided in the responders’ field of vision so it has to be shown in a non-invasive way, not to compromise the operations” she states.

The company is expecting to have a prototype of the Augmented Reality interface in two months after which it will be implemented on the device.  A key issue in this process will be to provide continuity and interaction with the other applications in the project, such the mobile app or the wearables, that are also going to be used by responders. Finally, the technologies will be tested in several in-field demonstration to ensure a good performance in a realistic scenario.

“Our project will represent a breakthrough in the application of Augmented Reality to disaster management”, concludes Sassi. Indeed, the I-REACT smart glasses application will allow for a faster and more coordinated response, which might be vital to save lives during emergencies. This will be in a year’s time and, until then, we will have to content ourselves with the real world.

Floods of Water, Floods of Data

In August 2002, after more than a week of heavy rains over a large part of Central Europe, the Elbe and Danube rivers overflowed with such force not seen in a lifetime. This significant flood disaster resulted in billions of Euros in damages and took the life of twelve people.

During that time, it was not only the river banks that burst. The European Commission was inundated with information provided by many local sources that had significant variability in quality and therefore created a difficult problem when trying to plan an effective emergency response.

After the 2002 catastrophe, the need for a trustworthy European-wide source for flood related information became necessary and therefore the European Commission (EC) moved forward with the creation of the European Flood Awareness System (EFAS). This sophisticated flood early warning system that produces flood forecasts was developed and tested at the EC’s science and knowledge service: the Join Research Centre. Today, EFAS effectively produces pan-European flood forecasts up to ten days in advance providing valuable warning to regional and local authorities about potential flood dangers.

The EFAS services however, can be further complemented and enhanced. One of the goals in our project is to collect as much data and information as possible to help improve the resolution in sensitive areas and speed-up the information turnaround. To achieve this, I-REACT will complement and enhance flood forecasts by adding data about historical flood disasters and use social media and crowdsourcing to provide up-to-date streaming information about flood situations and reduce the time to identifying a flood event.

But access to data is just the tip of the iceberg because getting access to the wanted sources is already a significant challenge. For example, the quality of service varies significantly when it comes to Open Data services accessibility. This means that supposedly open access services are not open to everyone in reality or data is inaccessible because the web services are down which, given the short timeframes to react to during emergency situations can have serious consequences to the success or failure of the planned response.

Locating the best and most appropriate data is also not trivial. The databases where wanted information are stored can change locations often without warning or disappear altogether. Other databases are maintained by a single person who may be unreachable when needed. Furthermore, European-wide analysis requires merging data from different countries working in a variety of languages. This requires further work as one needs to correct terms and nuances introduced by the creators and is often challenging. Finally, political decisions can produce a barrier restricting the access to good and useful data. While there are high level initiatives such as GEOSS and INSPIRE to overcome data access and data harmonization issues respectively, they advance much more slowly than technical advances.

An important goal for I-REACT is to access the best information to be used in our models and make it available to the emergency responders today and ready to ingest new information when it becomes available.

It is no easy feat to produce a European solution based on Big and Diverse Data dedicated to natural hazards. Such an ambitious goal can only be achieved through cooperation and by joining forces with partners having diverse and relevant expertise in dealing with such issues. And we have to remember that after all, the overcoming the difficulties are part of the fun.

Photo Source: Thinkstock / bestdesigns

What the past can teach us about future disasters

It was once said that those who cannot remember the past are condemned to repeat it. This quote from the Spanish philosopher George Santayana intended to underline the importance of being aware of previous social and political events, but it can also be applied to a completely different matter: fighting against disasters as a consequence of natural hazards.

It is widely known that there are certain territories that are more disaster prone than others. Villages near to a river basin that have been flooded almost every year, small cities that had to be rescued from the fire flares more than once. And, in these places, every disaster comes with a lesson to learn. Gunter Zeug, our partner at TERRANEA knows this reality from experience. “My hometown lays on a river. Every few years the town was flooded. Even if all people knew it was coming and even if flood gates were closed and sandbags prepared, there were still entry points for the water and the damages were always high. After many years of planning, the government decided to build a wall along the river to protect the city. Also historic data was used to model today’s possible flood extents, and based on these results the wall was built.”

Unfortunately, sometimes this information only remains in the collective unconscious of locals. But if post-disaster knowledge was stored in a way that allows remote and quick access, it could be of enormous value. One way to do this is to save disaster related information in a central database.

In our project, we strongly believe in the importance of classifying this historical information to help improve risk mitigation in future events. Thus, TERRANEA, in collaboration with other partners, is building a historical disaster database that will represent an important source of information for the I-REACT system.

Building this kind of database at EU level presents several challenges posed by the important differences in the data collection systems and in the openness of the databases. “Ideally, events are recorded in a standardised manner and the data becomes open afterwards. However, the challenge we encounter is that the quality of the different data sources that we identified so far is varying and often there is no spatial information available but only information about affected towns or villages with no related coordinates”, says Zeug. In fact, some institutions have already studied the problem of building historical databases. “The EC/JRC conducted a study about the state of the art in the European Union. Their comparative analysis showed that methodologies for disaster related data collection and recording in Europe are heterogeneous and that the available national databases vary in their level of completeness and detail. IT systems vary in purpose, complexity and openness.” Being aware of these challenges, we can only roll up our sleeves and start to work.

As part of the I-REACT project we will start studying the countries that are represented in the consortium (Spain, UK, Italy, Finland) at a country-wide level. For those we will try collecting flood and forest fire data from different open sources for the past ten years since more recent events are usually better documented.

This database will help to identify hotspots for natural hazards, enhance forecast and nowcast models and improve the risk management of disasters. From the communication point of view, the web interface for exploring and accessing the catalogue of historical events will be a perfect tool to our partners in Scienseed that are already working in the identification of key stakeholders in sensitive communities.

Soon we will have our first results, and with the history in our hands, we will surely be more prepared for the future. Join us in this quest through time to fight disasters!

 

Image copyright W. Lang, Floods in Germany (Neuwied) 1920

A tweet can save lives

When Hurricane Katrina hit the American coast in 2005 Facebook was a newcomer to a still-to-be-developed world wide web, there was no Twitter to have news updates and less than 70% of citizens owned a mobile phone. Today, with more portable devices than citizens and an ever-constant interaction through social networks, the way we obtain and share information during crisis has drastically improved. This is proving very helpful in recent crisis like the 2013 super typhoon Haiyan in the Philippines where Twitter was the single greatest information source for response and recovery efforts.

Social media is becoming essential for authorities to access vital information provided by citizens that would not be available otherwise, which improves the prevention and response to critical events. However, social network information is largely unstructured arising from the fact that everyone can be an information source. From eyewitnesses to emergency responders or NGOs, that can provide information from the ground, to mass media that amplifies the message, or even outsiders showing sympathy and emotional support. In this context, there are many factors that affect how the information flows, such as the use of hashtags which is very diverse and can sometimes hamper the identification of relevant data. Thus, it is necessary to analyse social media to place the pieces of the puzzle together.

The extraction and analysis of social media information is an important part within the I-REACT project. This information obtained from citizens will complement data coming from earth observations, UAVs, or emergency responders, among others, to provide real time data on floods, wildfires, earthquakes and other natural disasters. For this, Natural Language Processing (NLP) technologies developed by the I-REACT partner CELI, are being used to analyse big data streams from social media.

To do this, great amounts of information are initially collected from social networks by using searches on generic keywords such as “earthquake” or “flood”. Although this information will be unstructured, all or most of the emergency-related material will be gathered this way. Since this data can be compared to that of past events and to “regular” behaviours on social networks, a vital information will be generated: detecting if something unexpected is going on and spotting the occurrence of an emergency in real time.

This information will then be validated through linguistic analysis and machine learning techniques. Here, it is possible to select the emergency-related contents and identify useful information such as the type and location of event, the casualties, or the damage to infrastructures and services. In addition, we can also have information about the sentiment of the message, which is important to create panic maps and to prioritise actions on the ground. And once the event is concluded, the system keeps collecting data so that it can be continuously tested in spotting new emergencies from social media. This way, this tool will progressively learn and refine its ability to identify disasters.

Overall, social media analysis provides fast and relevant information during emergencies, highlighting the fact that these communication channels are not only changing the way we live and interact with each other, but also making every citizen an essential part in the fight against disasters.