Remote Sensing provides valuable data to track tectonic activity, study seismic zones, and evaluate potential earthquake impacts. By using satellite imagery and geospatial technology, remote sensing aids in mapping surface deformations pre- and post-earthquake, aiding in risk assessment and management. The consequences of earthquake occurrences are widely known on the impact the have on the society, economic, civil protection and science. Can satellite sensing assist in the prevention process? Can earthquakes be predicted? Doctor Stefano Salvi has the answers.
Dr. Salvi participated the 44th annual “International Geoscience and Remote Sensing Symposium - IGARSS 2024” of the IEEE Geoscience and Remote Sensing Society, in Athens from 7-12 July 2024.
Dr. Stefano Salvi is technological director at the National Institute of Geophysics and Volcanology (Istituto Nazionale di Geofisica e Vulcanologia: INGV), Osservatorio Nazionale Terremoti (ONT), Rome, Italy. In 1999 he founded the ING Remote Sensing Laboratory, and in 2001 the INGV Geodesy and Remote Sensing Laboratory. He works in a research group including engineers, geophysicists and geologists experienced in the use of space geodetic data for the study of ground deformation due to various phenomena, earthquakes, volcanoes, tectonics, gravitational mass movements, sinkholes, anthropogenic subsidence. He has authored over 80 papers on peer-reviewed journals on these subjects. He has been PI or co-PI for several research projects funded by EC, ESA, ASI, NASA, Italian Antarctic program, national and bilateral research programs, on the use of remote sensing data and techniques for geophysical applications and geohazard assessment. He coordinates the Italian Joint Research Unit supporting the European Plate Observing System (EPOS). He is a member of the CEOS Working Group on Disasters and co-lead of the CEOS Seismic Risk Initiative. Since 2014 he is Chair of the Scientific Advisory Committee of the GEO-Geohazard Supersites and Natural Laboratories global initiative.
I work at the Italian National Institute of Geophysics and Volcanology in Rome. In my research group we mainly carry out research based on remote sensing data on earthquake and volcanic hazards and provide support for monitoring earthquakes and volcanoes for the Italian Civil Protection. I am also advocating for Open Science, and manage an open-data global initiative called the Geohazard Supersites and Natural Laboratories, established in 2007 in the framework of the Group on Earth Observations (GEO). The initiative has created a network of 14 Geohazard Supersites, which are special seismic and volcanic areas where scientists freely exchange ground and satellite data and collaborate using an Open Science approach.
In Greece we have the Enceladus Hellenic Supersite, which covers the Corinth Gulf from the Ionian islands to Athens and is a seismic supersite, coordinated by the Greek Civil Protection. We help the scientists which are part of the supersite community to obtain satellite data from global space agencies and they use these data to explore and monitor the earthquake hazard before and after the earthquakes and to assess their consequences.
In essence the supersite programme connects local and international scientists and scientific institutes with global space agencies and with the local civil protection agencies. These are the three main stakeholders. The scientists receive useful satellite data from the space agencies and provide access to in-situ data acquired by their own network; they generate scientific results or services to monitor the occurrence of volcanic and seismic activity and provide them to the local civil protection agencies.
Among the supersites we have the San Andreas fault in California, the Hawaiian volcanoes, the Iceland volcanoes, the Marmara fault near Istanbul, and several other seismic and volcanic areas in New Zealand, Italy, China, Ecuador, Nicaragua, Chile, Russia. For example, the two Italian volcano Supersites are coordinated by INGV, which is the main reference institute for monitoring volcanic and seismic activity in Italy. All the research results we generate using satellite data and ground data are then delivered to the Italian civil protection and to other government agencies, to be used for decision-making in hazard assessment, risk prevention and of course for response to a damaging earthquake.
The Corinth Gulf is an area where active seismic faults have been mapped on both sides of the sea channel, and are generally oriented East-West. Such faults can generate large earthquakes, and the area is constantly monitored by ground instruments. Using satellite data and especially radar data, it is possible to accurately measure the deformation of the ground through time, with a spatial resolution of a few meters. These data can provide images of how the ground is moving through time -e.g. 10-20 years-time- with a precision of few millimeters per year.
Earthquakes are generated when the long-term stress accumulated by the tectonic plates motion overcomes the resistance level of the faults, thus by studying the plate motions and deformations at the surface the scientists investigate the earthquake generation process.
The time occurrence of earthquakes cannot be accurately predicted, but for a given area or fault you can calculate the probability of occurrence of any ground shaking level, within a given time interval. So scientists can give structural engineers fundamental data to design seismically resistant buildings which can withstand the local maximum ground shaking level.
For instance, studies using also satellite data have calculated a very high probability of occurrence, between 40 and 70 %, of a large magnitude earthquake (larger than M 7) in Istanbul during the next 30 years. These kinds of studies are important to map the seismic hazard, which is then useful to civil protection agencies to put in place a number of different measures aiming at preventing or reducing the consequences of such events.
For earthquake hazard investigations we use a technique called Synthetic Aperture Radar (SAR) interferometry to continuously monitor the ground deformation. This technique was developed starting 30 years ago, and today it is blooming due to the availability of a growing number of radar satellites, being deployed by national space agencies and commercial companies. However, not all these satellite data are openly accessible by scientists, and the Geohazard Supersite initiative aims at fulfilling this information gap.
There is a lot of work going on in this field and AI is being used especially for data modelling. Presently the majority of the models that we use are based on a deterministic assessment. AI uses statistical techniques based on large information databases and it is likely that its use will gain weight in the next 10 years.
Earthquakes cannot be predicted, due to a large variety of still poorly known conditions that drive their triggering, and the difficulty of acquiring information from the considerable crustal depths at which they nucleate.
Predicting earthquakes is like predicting when you will catch a cold. The event is subject to several different conditions and variables which make a precise prediction (minutes, hours or days) impossible. Of course in the future we will have the computer capacities and AI techniques which might allow to refine these times, but it will likely take many more years anyway.
The field of electromagnetics, the contribution of remote sensing and a philosophical life-changing perspective, aligned together in the fight against climate change. Kamal Sarabandi's forty years of experience in researching applied electromagnetics turns into distilled wisdom in this eye-opener interview.
Professor Kamal Sarabandi is a distinguished Iranian American scientist holding the Fawwaz T. Ulaby Distinguished University Professor of EECS and Rufus S. Teesdale endowed Professor of Engineering positions at the University of Michigan. Professor Sarabandi's research focus encompasses a wide range of topics in the area of applied electromagnetics. With expertise in microwave and millimeter wave radar remote sensing, wireless technology, electromagnetic wave propagation and scattering, metamaterials, antenna miniaturization, and nano antennas, Sarabandi has made significant contributions to the field.
I'm a professor in the Department of Electrical Engineering at the University of Michigan. My area of research expertise is applied electromagnetics. When I started my PhD, I wanted it to do something that would be impactful. There are a lot of different applications of electromagnetics that goes from communications to defense and remote sensing. I wanted to use radar systems in order to understand how radar signal would interact with natural terrain.
And then I thought maybe this is an impactful area that I can use my engineering and mathematical background to put it into practice. I started looking into the issue of global warming. I'm talking about 1984. This is almost forty years ago. My thesis was the first thesis -or among the first- that would start looking at modelling of vegetation -be it a forest canopy or crop land- and the goal was to mathematically model these in order to be able to predict what a radar would see from targets like that. As you know radars were only used to find targets like aircraft that are landing in airports or for military applications. So, we used the radars to look at the ground, and then evaluate the data collected from the ground. It just so happens that the signal is very sensitive, because most of vegetation, as you know, is filled with water, and water has a huge electromagnetic response. It's like warming your food in a microwave oven, because it has a very high dielectric constant and the response to that signal is quite high. /p>
So, in this manner we started modelling vegetation. That's how I got started. I wanted this to be an impactful area of research. I wanted to dedicate my life to something that would matter to humanity as a whole. I didn't want to just solve a problem. I didn't want to just fix a cell phone tower for example or anything like that. Let me also digress a little bit to tell you why I thought like this. People point at the sky, and they think that is heavens. Well, we know that all the stars are made-up of plasma, an environment full of explosions and fusion reaction. So, when one actually looks at the sky or a star, they should realize that this is more like hell, not heaven. The only heaven we know, is here. So, how do we save our heaven? This should be really the motto of our society. We need to save this heaven. The heaven that is given to us by the past generation. The heaven that is not only for us, but for the next generation to come. So, we are at a stage where we have started monitoring and we are trying to understand how human activity affects the heaven we live on. Most unfortunately, most of our activities has been destructive to the heaven that we are living on.
Once we understand the impact of what we do, I'm sure humans are smart enough to take corrective actions to the way we use energy, fossil fuels, and the way we destroy resources.
Well yes, I am positive. Because I think that what we were doing was a mere product of ignorance. We didn't know really what is happening to our planet and we thought the planet has the ability to compensate, no matter what we do. That there's an innate mechanism that controls the processes of the Earth's environment, climate, vegetation, etc. We thought that the Earth is big enough and it will self-correct, no matter how much we pollute. But this is not right. And how do we know it is not? Because all of the activities that the scientists in geoscience and remote sensing are engaged in point to the contrary. Because we have been trying to understand these processes and to inform decision makers, politicians, the industry, and the society at large as to what is to their benefit.
For example, if you are shipping something you don't want it to encounter a storm or a hurricane. I mean that we have to understand that what each one of us does has an impact on anyone. If our actions are beneficial for the environment, then these actions are going to also be beneficial to all. As a result in this manner things are going to be mutually beneficial. This will be beneficial to both industry, the environment, other species on this planet and human beings. So, you have to strike a balance for a sustainable future. We should also realize that we live in a closed system, hence what we do, for example, in the United States will have an effect on Europe and the rest of the world and vice versa. Because we now having a better understanding how these processes are connected, we have a chance to fix our past mistakes.
Be focused on this: sustain life on this planet for the younger generation. If you plan your life around altruistic goals, you will not only succeed yourself, but also you will enable others to succeed. You know, we are all social animals. I cannot have a good life in a community, when the rest of community is deprived of that. Just concentrate on what's good for all inclusive of all forms of life. If your actions are responsible, then they will benefit others. I say this to my own children: don't focus only on money. A lot of people focus merely on increasing their own standard of living without considering the cost or its consequences. Just an average level of living standard, no matter how high it is, does not necessarily make you happy. Humans have a limited range of emotional experiences, meaning there is a maximum level of happiness or sadness one can feel. The brain is unable to generate feelings beyond these set levels and interesting enough these set levels are independent of the average level of living standard. Therefore, it is beneficial to focus on expanding the brain's dynamic range of happiness and managing your life to stay more on the happier side and less on the sad side. We should focus on activities that bring us long-lasting happiness. For instance, losing money can make us sad, but if we never had it, we wouldn't feel that loss. In contrast, helping someone brings a lasting sense of fulfillment. This is why I love working with students. When I share some knowledge with them and see their eyes light up with understanding, that moment of joy lasts much longer than the fleeting excitement of winning $10,000.
Exactly, because our perspective has to change in order to save the planet. When it comes to possessions and maintaining a high standard of living, I often recall a saying by the Persian philosopher Rumi: "We are all climbing the ladder of life, but it is guaranteed that everyone will eventually fall off. The higher one climbs, the harder the fall." This wisdom serves as a reminder to reassess our priorities and focus on what truly matters.
The distinguished ESA personalities participated IGARSS 2024, in Athens and in particular chaired the session on Copernicus and DestinE platform ecosystem opportunities. The particular session highlighted efforts and opportunities within the Copernicus Data Space and DestinE Core Platform to empower users to contribute to a robust ecosystem of services, fostering sustainability, resilience, and positive planetary impact.
Copernicus Data Space Ecosystem is the new data access and data exploration element of the Copernicus Program. The Data Space represents a paradigm shift from data distribution via downloads towards in-code API access, allowing processing, filtering, and statistics calculation, limiting downloads to the resulting information. Destination Earth unlocks the potential of digital modelling of the Earth system at a level that represents a real breakthrough in terms of accuracy, local detail, access-to-information speed and interactivity.
The session aimed to highlight efforts and opportunities within the Copernicus Data Space and DestinE Core Platform to contribute to a rich ecosystem of advanced applications and services, providing an overview of how they work together and empowering users to access and provide actionable information to measure and act to improve sustainability and resilience to the benefit of our planet.
Professor Kamal Sarabandi is a distinguished Iranian American scientist holding the Fawwaz T. Ulaby Distinguished University Professor of EECS and Rufus S. Teesdale endowed Professor of Engineering positions at the University of Michigan. Professor Sarabandi's research focus encompasses a wide range of topics in the area of applied electromagnetics. With expertise in microwave and millimeter wave radar remote sensing, wireless technology, electromagnetic wave propagation and scattering, metamaterials, antenna miniaturization, and nano antennas, Sarabandi has made significant contributions to the field.
Jolyon Martin: I work on the Copernicus programme, which is one of the key pillars of the European Space Agency programmes. It is literally the European eyes on the Earth. ESA has been entrusted by the European Commission to develop and operate a series of satellites called the Sentinels, providing essential observations for a host of applications. The uses of the Copernicus data are very wide: from monitoring agriculture and helping to avoid overfertilization, using efficient water resources, to pollution detection like oil spills or atmospheric emissions, as well as for climate change or deforestation. The data are made available from the Copernicus data space ecosystem and they are available to the public and many other institutions and initiatives such as the Digital Twins of the Earth.
Jolyon Martin: The data are open and free to everyone. Anybody can freely register to download the data through the Copernicus data space ecosystem . Moreover, ESA is making the data available on the cloud to also facilitate its processing in a much more environmentally friendly way. Providing the data together with tools and resources for the processing.
Kathrin Hintze: Destination Earth is an initiative of the European Commission to build a digital replica of the Earth. This replica allows users to design accurate and actionable adaptation and mitigation strategies. Destination Earth builds two initial digital twins of the Earth, one for climate adaptation and one for weather-induced extremes. ESA is implementing the platform where users can access these digital twins and build their own applications, that are relevant to their cities or their countries.
Kathrin Hintze: The digital twin for the climate adaptation, for example, provides simulations for the next decades at a very precise level -hourly level- for the entire globe with the resolution of a few kilometers. This can be used at the local level. It's a big amount of data because for every point of the earth there are more than hundred variables that are made available to the users through the platform. The platform also makes available to the users, tools in order to use the data for their own purposes and to visualize the data. For example, there is a very nice tool for storytelling and users can use the data to tell a story that it is tailored to their area.
Kathrin Hintze: The initiative is only two years old, and we just had the launch of the first version of the system which gives the basic building blocks to the users and now what we are expecting is a ramp-up in the next two years where we enable users to build these services and test the scenarios such as the one you describe.
Haris Kontoes: In the National Observatory of Athens and the BEYOND Center for EO Research and Satellite RS we
are using the big Sentinel data to run models and assist the decision making and the management of physical
phenomena processes on the planet. For example, in Greece we have problems with wildfires. The firefighting
authorities need to have operational data to deal with the disaster. This is not simple. We couple big EO data
with advanced Artificial Intelligence models for generating the knowledge that is needed by the civil protection
control authority and the fire fighters. In this regard, the use of the Destination Earth platform is key.
https://dataspace.copernicus.eu
Haris Kontoes: There are several sectors that benefit by the ecosystem of data (so-called digital twin) available
through the Destination Earth initiative. One example is the Early Warning system EYWA to mitigate
Mosquito Borne Diseases. The system was developed in Europe under NOA’s coordination and nowadays is implemented
in different places all over the world. To achieve this, a multitude of Earth Observation satellites are used,
because they cover the whole planet and provide daily information that is necessary to assess the expected
epidemiological risk for Malaria, West Nile Virus, Dengue Fever. These diseases cause hundreds of thousands of
deaths in many countries worldwide.
Moreover, in the agriculture sector we use big EO data to systematically assess and project the development
of the crop and know beforehand the actions to be anticipated for protecting the yield and the food over large
territories.
Kathrin Hintze: And if I may add, also to optimize the use of fertilizers. By using all these data, we are
helping the planet towards resilience and sustainability Because we can know exactly how much is needed for the
growth of a specific plant in a specific area of the planet.
Another application is to project the level of the crop, and this is very important for the income of the
farmers but also very important for the sustainability of the planet and the resilience of societies. Think of
food security for example.
Outbreaks of diseases transmitted by mosquitoes is observed all over the world and particularly in Europe, and this is due to globalization and the climate crisis. Insects transmit diseases such as malaria and dengue, whose prevalence has increased over the past 30 years as global warming has produced warmer and wetter conditions, researchers conclude. Remote sensing is proving to be an ally in dealing with this threat to public health.
Sandra Gewehr is a biologist who has been working in Ecodevelopment since 1998 and is responsible for Public Health issues related to mosquitoes. She heads the company's Research and Development department, and she is also the President of the EMCA (European Mosquito Control Association). On Tuesday July 9, 2024, Sandra Gewehr participated in the session "Artificial Intelligence and Earth Observation Technologies Aid Decision Making in Wide Area Mosquito Control Projects" during the 44th Annual "International Geoscience and Remote Sensing Symposium - IGARSS 2024" of the IEEE Geoscience and Remote Sensing Society.
As Director of Research and Development in Ecodevelopment, a company specialized in mosquito control and as
President of the European Mosquito Control Association (EMCA), I am strongly concerned with dealing with the
consequences of climate change on mosquitoes. One of the most important consequences of climate change is the
impact on the ecology and the distribution of mosquitoes and the diseases they transmit. This is because the
rise in temperature allows mosquitoes to travel further north and additionally summer rainfall - you know that
there are no mosquitoes without water - favor their development. Also, globalization contributes, as it makes it
easier for people to travel. Our field is to see how we can make good use of the observational sciences to
predict mosquito-borne diseases. This is done as part of the European Innovation Council's first prize-winning
EYWA system - Early Warning System for Mosquito Born Diseases (EWS for Mosquito Born Diseases). It is a system
that predicts mosquito abundance in nearly real time, and it also predicts the outbreaks of mosquito-borne
diseases, such as West Nile virus.
Ever since observation and remote sensing entered our industry, many of our everyday tasks have been
made easier. Mapping is one example. The ability, that is, to locate surface water under the vegetation, which
is favorable for the development of mosquitoes. This gives us the opportunity to move from research to practice.
And by practice, we mean control. So, we control mosquitoes in two ways. One would be in the water as larvae
through larviciding and the other at the adult stage with adulticiding treatments. Remote sensing helps in both,
the detection and the treatment, in space and time, of mosquito breeding sites. We have daily weekly and monthly
forecasts and we can now monitor 42,000 mosquito breeding sites (e.g. in streams, canals, wetlands etc.) in
Central Macedonia we can predict if there will be mosquitoes in these breeding sites. Also, we provide an open
application for mobile device, called “Mosquito Vision”, which is very useful for the general public. Mosquito
Vision predicts the presence of adult mosquitoes in 2500 villages in four regions of Greece on a daily basis.
Predictive models need data. How are models developed? In addition to the data coming from the remote sensing of
the earth, which is freely accessible, there is also the field data, which gives us the actual mosquito
populations. This data need a lot of effort. There are new technologies that Internet of Things (IoT) networking
provides. With remote sensing we can detect a lot, but not everything. That is, if there is water under the
vegetation, it is very difficult for the optical satellite to "catch" it, because when there is cloud cover the
optical satellites cannot "see". In this case we also use radar imagery. In parallel, we work with IoT in a
pilot and with water sensors that we put in the field and that give us information when water enters an area.
So, the combination of satellite data with sensors will help us to locate in space and time when and where there
is water and therefore the probability for the development of mosquitoes.
And don't forget that our job is not only to observe them, but mainly to kill them. In this context,
applications are made also by aerial means, i.e. for large areas helicopters are used and for medium ones we now
use drones. Drones also give us the possibility of both, remote sensing and mapping, as well as spraying. In
Greece we are actually quite advanced because we are at the epicenter of the West Nile virus. Unfortunately, our
country, together with Italy, holds the first positions in the occurrence of West Nile virus cases. We have had
also cases of malaria in the past which were successfully dealt with by the country's public health services in
conjunction with mosquito control. And of course, West Nile virus cases also exist in other Mediterranean
countries, while they have been recorded in Germany as well.
Resilience to climate change in terms of mosquito-borne diseases is influenced by many factors. Public interventions do have limits. The tiger mosquito, for example, breeds primarily where the public has no access, that is, in our private space. That is why it is important for citizens to get involved. There are protective measures that the citizen can take to prevent the development of mosquitoes, for example covering the cesspools or not keeping water in the pot saucers. It is important that people know this so that they can contribute to protection. The last measure of course is personal protection. Zero mosquito is not possible so we must always take personal protection measures in order not to be exposed to the risk.
Satellite data is an invaluable tool for climate-smart agriculture. It enables farmers to monitor weather conditions, assess climate patterns, manage water resources, mitigate risks from extreme events, and make informed decisions to optimize productivity and sustainability. Delivering high accuracy, broad coverage and valuable insights, is fundamental to decision-making for government policies, business strategies, science research investments and financial risk advisory.
Dr. Nicos Spyropoulos is Director, Strategic Business Development EarthDaily Analytics. He has been involved in the commercial space industry for almost 30 years, working as executive at numerous satellite and space-balloon companies such as IIS-EOSAT Inc., Space Imaging (a Lockheed Martin, Raytheon and E-System Company), Definiens, Cosmotelco, KBI, 5CI, UrtheCast, Earthi, World View Enterprise and Space Perspective Inc. Dr. Spyropoulos received his BSc & MSc degrees in Land Reclamation, Hydraulics and Agr. Engineering from Athens University, MSc and Diploma in Remote Sensing from UCL and Imperial College, London and his PhD in Remote Sensing from the University of Athens. He has been Remote Sensing lecturer in postgraduate courses at University of Athens and Eurocourses at Joint Research Centre, European Commission, Ispra. His corporate functional experience together with international background and natural leadership enhance his strong negotiation skill and complex service selling capability.
Chris Rampersad is an experienced technical leader with over 20 years of experience working as a VP, Director, Technical Manager, Software Engineering Lead and Software Engineer. He possesses an excellent analytical aptitude and software engineering background, which he uses to help lead, develop software and provide technical guidance in the development of software systems. Chris has a solid track record of completing high-risk software projects on schedule by creating a clear vision and roadmap, and by leveraging effective software engineering practices including agile iterative development and risk management strategies. Currently, Chris Rampersad is Vice is President of Engineering at EarthDaily Analytics.
Cécile Tartarin pursued her education at L'Institut Agro Montpellier from 1996 to 1999, where she obtained a Master of Science degree in Agronomy and Crop Science. Cécile has a diverse work experience spanning over two companies. Cécile started her career at Union Invivo in 2001 as a Market Analyst and worked there until 2005. In 2008, she joined EarthDaily Agro as a Crop Analyst and later held various positions including Global Product Manager, Head of Product Management, and VP of Products & Solutions. Currently, she is serving as the VP of R&D at EarthDaily Agro.
Chris [Rampersad] and Cecilia [Tartarin] we are in Athens today for the IGARSS 2024 Symposium. Listening to the presentations this morning I realized that the climate change is here. It shows its facets with phenomena like wildfires, landslides and mega drought. So, I thought this is not climate change, this is climate crisis. So, I think we need to understand how our biosphere is behaving. And I was wondering, what is the best tool to use for this kind of global monitoring or a global change monitoring? Perhaps high cadence, scientific quality and robust satellites can be of great help and support. These could allow AI derived monitoring, predictive analytics or change detection alerting and thus help our planet or help us to understand its behavior. I don't know, Chris, what do you think about this?
And Cecile I think that kind of technology from space, I believe that helped a lot with the food security issues. You know what's your perception on this?
Yes. You mentioned the wildfire as an example of our climate crisis. This is only one example. The climate is also impacting a lot of the farmers and agriculture in general. So, we're seeing more and more drought events developing around the Mediterranean basin and we see some extreme events as well affecting the crops, that we can monitor with the satellites. With satellite technology, we can do amazing things like identifying crop from space and then estimate the vegetation health. This is how we can anticipate crop yields at different scales, which enable the food supply chain to anticipate any kind of disruption. So, with such a system, anyone can have a global view every day of the situation of the agriculture on the planet.
We, as engineers and scientists, we need to massage the information and bring it down to earth in a more applicable way. I heard in the previous day that that we need to go outside the bubble of science, and we need to make this technology more acceptable by the farmers or the firefighters. So, what do you think about this? Is that possible by simplifying the technology and absorbing the scientific processing burden and generate products digestible ready for consumption and analysis?
Yes, it is. Twenty 20 years ago, people would have used their eyes to look at satellite imagery, and nowadays there are just too many pixels. There are billions of pixels being captured every day. To interpret that, luckily, we have machine learning and different forms of AI. That's really the only way you can interpret data at this scale and then start to understand how things are changing. At the end of the day, we're not trying to see pretty pictures of a planet. We're trying to understand the dynamic physical processes of what's happening, whether it's in agriculture or with wildfire risk. That's more than a picture. That's scientific information that you get from more colours than just what your eyes can see. It's not just the red, green and blue. It's near infrared. It's long-wave thermal infrared. It's the short wave-infrared. These are spectral signatures that are out there. We can't see them with our eyes, but we can see them with satellite imagery and if we apply AI to that data, we can start extracting information and take action.
You have touched an interesting point as well about how to disseminate the research outputs down to real users. That's why we are working as well on a platform which allows us to operationalize the results of the science and bring practical solutions to the farmers, and as well through the whole supply chain. By answering very specific business questions this it's not only science but tools that anyone can use.
So, the future is bright for us, but also for the end users. People need this easy-to-get information, so they use to tackle their everyday problems.
Planet Earth has changed dramatically over the past few years: rising of the sea level, increasing levels of
ocean acidification, drought, or frequent and extreme floods, or heat waves. Meanwhile, the world population
growth and human activity amplify the effects of climate change. There is an increasing pressure on basic
resources, such as fresh water or food, an accentuated stress on land and marine ecosystems, a dramatic
explosion of environmental pollution, impacting health, and biodiversity. The question is how to monitor these
changes, and more, how to understand their causes, predict, minimize or adapt to their effects? Will a digital
Earth twin save the planet?
When it comes to Digital Twin Earth systems, hopes and fears abound in equal measure. In this interview
Prof. Mihai Datcu has the answers that set the record straight on how this transformational technology is
improving access to crucial information on the future of our planet.
Prof. Datcu participated the 44th annual “International Geoscience and Remote Sensing Symposium - IGARSS 2024” of
the IEEE Geoscience and Remote Sensing Society, in Athens from 7-12 July, 2024.
Prof. Mihai Datcu is the author of more than 800 scientific publications, among them about 170 journal papers,
and a book on number theory. He has served as a co-organizer of International Conferences and workshops, and as
guest editor of special issue on big data or quantum machine learning of the IEEE and other journals. Since
1993, he has been a scientist with the German Aerospace Center (DLR), Oberpfaffenhofen. He is developing
algorithms for model-based information retrieval from high complexity signals and methods for scene
understanding from Very High-Resolution Synthetic Aperture Radar (SAR) and Interferometric SAR data. His
research interests include Bayesian inference, information and complexity theory, artificial intelligence,
computational imaging, quantum machine learning, and image information mining for applications in information
retrieval and understanding high-resolution synthetic aperture radar (SAR) and optical observation. He is IEEE
Fellow.
Satellite remote sensing is playing a major role in this respect. Satellites are the only global, continuous Earth Observation (EO) data source. Hundreds of satellites capture land, ocean, polar areas, or atmosphere observation images. As an example, only the satellites of the European Copernicus programme that observe each point on the Earth's surface have captured more than 30 million images in just a few years' time. And needless to say, this EO data are now freely and openly accessible. However, satellite images are not mere photographs. These sensors are measuring the reflection of light, infrared or microwave radiation of Earth cover as vegetation, urban areas, lakes, or snow. Yet, these measurements are indirect. Remotely sensed observation of the relevant information in applications, as soil humidity, ocean temperature, or quantity and quality of crops and how these parameters are affected while the climate is changing, and adverse natural hazards are more often. The challenge is now how to extract this information from Big Data, a task much beyond the direct human capacity of analysis.
We have a method invented by Eratosthenes 2000 years ago. At that time, measuring the Earth's circumference was impossible. But Eratosthenes used an indirect observation, the shadows cast by the sun on a vertical pole at different geographical locations, and by calculation he estimated -in an extremely precise manner- the Earth's circumference. In EO we follow the same pattern: from indirect, remote satellite observation we extract the values of parameters of interest. Today, this is made possible by the availability of high-performance computing and the fantastic evolution of Artificial Intelligence (AI) as the epicentre of a new revolution boosted by Machine and Deep Learning (DL) methods, fostered by Big Data. Big Data is the process of collecting large volumes of data via EO satellite sensors, but also in-situ observations, people, or IoT, only to enumerate few modalities. AI is the convergence of theoretical methods and tools to transform Big Data in useful information and knowledge for making decisions, verify hypotheses, understand insights, or make predictions.
While satellite images are not photographs, and the objective of the EO data analysis is extraction of physical
parameters and understanding of causalities, a new AI field is developing. AI has the role to browse of large
global data sets and detect similar phenomena, as forest fires. Analyze the context, as relief -e.g. type of
vegetation, temperature and humidity, water resources, presence of settlements or industrial sites- and derive
the risk indicators but also the essential factors which could be used to avoid further disasters. Thus, the
requirements of EO satellite data analysis are promoting new theoretical studies, emerging in a new very
interdisciplinary branch of AI.
Modern AI, in synergy with satellite data, offers excellent prospects in learning the models of changes and
effects of global warming, and thus, defend nature at global scale. Conventional methods typically have to be
adapted for specific environments and regions. It is consequently very hard to implement harmonized, large-scale
analysis with high spatial and temporal resolution and, at the same time, high performance and precision. The
current AI based data driven approaches, are the major progress in support of EO data analysis for learning the
models of global changes.
The practical implementation of what I was describing earlier can be found in the new technology of Digital Twin
Earth (DTE) systems. DTE are interactive systems, a digital media to observe, understand and model the effects
of climate change via satellite EO and provide actionable information to local administration, industry,
research and directly to citizens. DTE systems provide capabilities to visualize, monitor and forecast effects
of climate change on natural phenomena and human activity on the planet in support of sustainable development
for a better environment protection.
Climate models describe changes at a scale of thousands of kilometers and for long time periods e.g. for many
decades. However, adaptation measures shall be applied at human activities scale, from 10m to 1km and periods
from days to months. The DTE systems implement a virtual, dynamic models of the world, continuously updated,
enabling simulations while providing more specific, localized and interactive information on climate change and
how to deal with its impacts answering “what if” questions. For example, how crops’ production will evolve if
drought is becoming excessive, or estimate forest damages as effect vegetation fires. The DTEs are also a tool
to largely interact with people raising awareness and amplify the use of existing climate data and knowledge
services, for the elaboration of local and specific adaptation. That is a step towards a citizen driven approach
with an increased societal focus.
The coupled DTE systems support to promote a geographical diversity approach, involving various regions and
communities, following a systemic approach converging several cross-modality themes and areas of innovation,
implemented as an inclusive methodology to bring together public administration, private sector, civil society,
and finally the citizens in person.