Merken

Keynote III - Geospatial Analytics in Risk Management

Zitierlink des Filmsegments
Embed Code

Automatisierte Medienanalyse

Beta
Erkannte Entitäten
Sprachtranskript
a we start with our
next guilt speaker is that the west so that came from Unix is from you every reinsurance 1 of the biggest reassurances in the world I think you also studied at least 2 years and 1 so it's kind of coming back to his home and will talk about you spatial delivery system with management get you have to alright thanks a lot to thanks for the invitation and thank you very much for the fantastic conference so fun for the fantastic location to great so things for that of geospatial analytics and
risk management I want to talk a little bit about there are some aspects of this topic from our perspective from the perspective of the insurance or reinsurance industry and to is not a few words about what reinsurance or insurance is or gossip actually so I think everyone Wallace knows 1 insurance is that's pretty straightforward everyone has 1 probably an insurance insures private people or companies against different but risks against different dangers and the reinsurance to make it simple insurance the insurance so what do we ensure what different types of of things we have and what everybody who knows what comes to mind as property what we call a property insurance so that that is if you ensure your building against storm damage earthquake-damaged crop image for instance but also it's not only that but the building itself even more important often is the content so the building I might have a certain value but of course if you think of semiconductor favorite um factory for instance than the content the machines within this building our their value is much much higher and another thing just what was a very interesting and and and important is what we call a business interactions so this is if for instance the street gets damaged that might not be a big damage simply to repair the street but the the time and costs to repair this feature which might cause that so the company cannot deliver their goods to port nearby and so they cannot make business for what we go into this damage might be much much higher than the property damage to other lines of business as we call them architecture to for instance marine so this is some marinas for instance if you think of a of a big big cargoes boat but it's not only the boat itself what is mostly much more of much more value the cargo on this boat and that can nowadays sum up until around 500 million dollars for instance these ships can transport about 20 thousand containers nowadays and if such a shift things then it's really getting into each of damage other things would be engineering so this is while ritual big building is built the macro so this is crop failure for instance so where the risks of them are insured here cyber risks of something you don't have a lot of different lines of business which play a role in in insurance and reinsurance and not only what we think of in the 1st term of office building and that's interesting so we have here some but from what is the quality of things that are not displaying on your computer and OK uh no difference or what about something which I want to mention is um what is also playing a role in in our terms is the difference between a single rose in the portfolio risk recall effect which achieve what treaty a factor 2 chief risk is 1 single rescue know exactly where it is it is it is a big or is there have you expect occasionally a nuclear plant for instance and you can't really do a detailed risk analysis for this 1 the risk of a treaty on the other side that's a huge portfolio 1st so that would be all houses of audience in the area of the insured against storm for instance when you have thousands or 10 thousands of cigarettes you do not analyze each and every single but you look at it as a whole and you often don't even have the information we uris exactly is located so you might only get the information OK and this sparse codes only have 10 millions and the sparse codes only 5 million etc. etc. this is of course this makes it different difficult if you want to model this was against flooding instance because in front you should have an exact location because it might make a difference if it's exactly at the root 100 meters away and so we have to think about ways how you can handle these a lack of information actually tool will finally come to buttress management and something special which I wanted to mention because it's also interesting from a from a point of from the natural catastrophe point of fuel is what we call a trigger products of parametric insurance In this case it works a little bit different than what we normally know from insurance is normally you have damage here and send this to your insurance company and insurance company hopefully pays for it In the trigger products you have the insurance company does not pay for the damage it pays when a certain event or across so when a certain tradeoff sort of physical parameters quality is triggered by an event so for instance if the speed of a storm exceeds a certain but what I want to and partners power then we should get the insurance payment the advantage is that as an insured person would isn't it should state nation I don't have to wait and until all the damages are capitalized but I immediately get my insurance payment as soon as the event is triggered period I'm sorry I got the code a little bit so I have to think every so talking about risks and the disasters in reinsurance on the insurance business so that we may need to make a difference between not that's and may make up so that natural catastrophes in man-made catastrophes and the natural catastrophes we have some main sections that we just ain't metrological events that would be all kind of storms more less to
physically events that creates tsunamis but also would panic eruptions for instance
hydrological events that would be made floods and then we have on climate to logically
events as we call them for instance 5 and on this map
you get a little overview over the events of 2015 we have what we call in that counts service so that so few guys in our company who collect all the events natural test to 250 events it would be you could hope and tried to put collective all information about these events like um what was the last what was the true loss home many people were killed and how many people how many fatalities do we have etc. and you can see those events and identified by the column and in in terms of the type of events and identified by the size of the then in order to display V the the the the uh the size of the and and I want to pick out a few more just to to point out in some things that you are important in this case
I for instance we have last April we had this has played in the Apollo 9 I wasn't people all losses . 8 billion dollars so pretty high in insured losses only to 110 million dollar and if you compare this to the winter storm event in the US and Canada for instance um then we have only a few fatalities there we have pretty high overall losses but not as high as in the past for instance but much much higher insurance losses and this is of course something which is for us pretty important knowledge Franks a big difference for the insurance company what is big catastrophe in the human terms and which is a big event might not necessarily be be given for the insurance company companies and the other way round something which is not that big if you think of it in terms of catastrophes might be a huge damage for the insurance company and the man-made catastrophes they don't have such nice pictures for them unfortunately so just a few bullet points here fire and explosion would be some uh would be a major reason for man-made cats terrorism of course text just to name
a few you and he has a little overview of the events in 2015 news you can see you how hiding for process have been what was supposed to use events and in comparison to that the most closely and every and to point out the man-made cuts the events on 2015 would come to this later again and it was explored exposure to the Port of Tianjin and I don't know how many people if you even have heard of it or if you remember what it because it was not that big in the newspapers there was a little bit but not that big and it was a huge damage for the insurance industry also it's what's really located pretty much on on 1 place the the damage is still not sure how much it really is but it's about 3 billion US stocks so that's a really big damage cells to come to our topic smallest what can we do with geospatial politics in risk management or risk and disaster management what it's all about what do we do in our company where where where busses to spatial aspect common to into all of that and not just listed that few feel there we do geospatial analytics risk assessment is 1 of them and that's a qualitative approach so that's really about getting an idea where your risks are exposure is so that's what we call the exposures all the signal on the aggregated some information about what the insurance where's your exposure and where it in relation to the hazards of course so that you get an idea where is the radical where this at all and you would be surprised at how many people in the insurance industry don't have any to where their exposure so it's really surprising I risk modeling and pricing that would be that the more quantitative approach so that it's really about getting a price and and finally you need to know how much do I have to to 0 at a certain time you should not need to pay more than that you then you because then you get into trouble so along a time it has to pay off so you need to model year risk you need to know OK in this area every 50 years I have total damage and then you can more or less calculate how much you should get from this risk accumulation country that's a pretty important issue and that's more or less working in in the company you need to avoid so that all of your short exposures in 1 place because if you have everything in the lines and then you have Katrina then you're in trouble and cropped so you need to to know where your exposure is and you have to make sure that not everything is concentrated in 1 single point and finally disaster management that this 1 is when it all happened to see as fast as possible what happens and what was what what was damaged and how much to estimate more or less how much it will cost these company is OK risk assessment not cut 1 example use natural hazard maps so it's pretty simple actually I mean it's simply a matter of road map which shows that has the classifier grade in this case it's of great great so what classes from yellow to pretty simple and not displayed on top of it and the green dots this exposure and as you can imagine as people who have to do with culture graffiti and with maps the darker green the the the thought is on that the larger the body is the and the largest total sum insured so pretty easy but this is something which a lot of people in the insurance companies don't know they had ever seen their exposure and certainly surprising because if you can if you see it like this you need to be gettin idea where your exposure is and what kind of problems you might run into another example and this is not really catastrophe it's more damage but I wanted to integrated because there were a few interesting steps in that from the Geospatial point of view and what was it all about it was about sup-CK William pipeline damage so when you have an offshore wind park or if you want to connect to an island on 2 continents by bias sup-CK would you somehow put it on the ground of the of the the and if you ever damage there then it gets expensive so why is there a damaged but 1 of them was few most reasons the damage the anchoring got that fishing and what we did was we created a risk map pretty simple 1 I have to say what the greater the risk map displaying this was in the area for chronic fishing and anchoring damage so we talk information from the air as the automatic identification system that every ship above a certain size has displaying its location and that was speeded cetera and the well I would say we trust these data we did a lot of editing there and analysis also by integrating some Hadoop mechanisms to wall what England's not that big data is already a little bit so this was also a test case of POC to to see what we can do with big data in and finally we came up with the risk map displaying these the most affected areas so it was only for a certain study area in the northern we came up with this list met is playing areas of high danger subsea cables and pipelines again that is
a pretty easy thing it's not really rocket science but it wasn't it is an important on information for the people who would do contracts since the what we call the underwriters so it wasn't important information for the underwriters in their risk assessment as well as in their communications with their clients with the people who the insurance because they could easily show them OK this cable there we have certain problems in these areas so you should have some measures against that wall we need to have a higher price or whatever so and and build an application around this 1st map where the where the underwriter can simply drawing this some new plants pipeline or sup-CK and get something like if you can see you on the spot line this buffet line on on the map indicating the risk of the sup-CK this is another example here for amendment that would be conflagration analysis so if we want to insurance or reinsurance residential building something private houses against fire and explosion but we also need to know what is in the a circle of 200 meters to see little which might get from which might be to be there in case of an an explosion or fire and I mean this is something really classical it's a classical GS analysis is simply a behind summarize on this area and that's it so again Nowak rocket science but an important input for the risk assessment of this of this exposure the the of Cameroon go a bit faster with this because it's more or less as what you already said with the hazard maps in this case I'm talking about rate maps more-or-less the same but in this case it's really about the price so that be a hazard maps it's really about risk assessments of getting an idea feeling qualitative approach for the for the risk in this case there would be some some way behind it so there will be some information OK we will have adult total damage here every hundred years so you have to take this and this same of
man mankind in this case with the terrorism exposure so we have information whereas higher and there's a lower terrorist risk
accumulation control I mentioned that at beginning pretty important what you can't have your portfolio either this way
all either this way and if it is displayed on a map you see immediately if you displayed in a in annex which you don't have a clue at all so those 2 examples are exactly the same portfolio in terms of total sum insured people in terms of number of risks in terms of of whatever additional registered attributes might be there but from the application point it's a it's a big difference and as I mentioned if you have Katrina and you have a portfolio of like that 1 on the right side then you might be in trouble the
disaster management it's about getting an idea or information where the damage happened and how big it is and 1 of the things we did they are we tried there was by master thesis on to get a damage food friend out of social media data and unlikely to understand that he identified what he the apple he did this season and he tried to find out from for certain events can he also get this event information out of Twitter messages of trees can he identified that there and that that happened something can he identi fied damage and can also spatially identified so can he identified the region and what is just a few images here you can see some density maps on left side of and you can see you the Treaty on the lower right side and this is about An the the earthquake events and 2 years ago which has happened in the middle of the nite time the interesting thing is um it happened about 3 . 20 20 people AM and people who for all of bad and the 1st thing they do is send to treat so it's quite surprising but was actually works to a certain extent at least some he this map you can see on and the green shaded color us that would be the the event footprint what as we call it so that would be what we got from the yes and the red and blue squares or thoughts are indicating what we got from the trees and so on and it would be because for them and hotspot analysis so the red sports would be what we would have identified and it's not so bad actually but of course it's not really exact it's not there in not detected and you have certain problems there treats all not Europe Iran's especially if you will for instance if you go to Germany then you suddenly see that there no note to reference streets anymore but the you might have problems that in areas where there no 1 living then of course you don't get information all as tho there might be something which is interesting for you isn't sure if you think of industries for instance and the think happens in the middle of the nite you won't get any tweets there but you might have damaged so still a lot to do but in in an interesting approach to another example I was any mention it at the port of Kantian explosion and in this case we try something the satellite image analysis so just a few facts about this explosion point of tension and no 1 ever heard of it probably is 1 of the largest ports worldwide and there happened explosion and the chemical storage sites and in the 1st place no 1 knew what exactly was about and if it was not so not such a big thing and after a few days slowly there came the a surprising information that this is really a big thing for the insurance industry a lot of damage and the question was how do we get the information what really happened and how much is damaged because of the access to the area restricted and of course it's a suited for health reasons of course but perhaps in the same because of political reasons so it's very difficult to get information and what the critiques that together with the with the government in in units was they analyze the satellite image simply by means of a manual analysis of nothing fancy here again simply by manual analysis they looked at the image and try to find out why how how high the damages on the 1 side and then of course on the other side what was that what was and was the word radical was there's a container area was there's an area of of the castle located etc. and from this information they slowly gotten no idea about what the damages and what exactly happened and of course this is also something that we see a certain use case for local panicles information for Copernicus data especially from the EMS from the emergency room of mapping service have very good information in this case from so the flood event the newest cop yeah uh which might be of use for this the image analysis OK so some to sum it all up and some challenges for the future for the insurance industry and that's also something than which in 2nd step concerns as to choose beta department and the values of the it true for all of the the of buildings of the yeah whatever this the values in trees more and more and they're are more and more concentrated in certain areas and so we need more and more chances transparency to really get a good idea about what we are actually insurance and we're ensuring and where it is the good quality all natural catastrophes get high and they're more frequent and we will have a problem what natural catastrophes or at least extreme events due to the climate change and we have to get prepared for that it and what's our some requirements for geospatial entities and they partly come out of that what I just mentioned but may part of the general requirements and I would say they are not only general requirements in our company but they are generally requirements in the business at all what we need is geospatial tools and apps for the business people we don't need any tools and apps for us as experts you know how to deal with them but we need them for the people who have no clue what achieves pages and it's really important for us in in our department but probably for everyone who wants to do some consulting in into spatial stuff still important to speak the business language to know what the people do what is the business what do they how do they earn the money and then to understand what we could do with our spatial knowledge and our speech Tuesday introduced to have those tools we have 1 view of those softer those systems they have to seamlessly integrate into the workflows and processes so it's pretty sad that you have an application vary from matter and all this nice stuff we're talking about his often normally you have a system which does a certain business thing I would call it like this and so in our case for instance you try to to price rescued the wall of the the wording so that you could use the treaty staff and all that kind of things and within the system you need some geo-information you do need some geocoding you need some point-in-polygon analysis put it that way and the user of he doesn't care and he doesn't know so our systems and our tools have to integrate in this in this form often already existing system and 3rd point which is the thing I think that's more important is and that we get more and more data and more detailed guide that data more up-to-date that so in this case it's really about that we have to hand in what they don't I many just put down the term Big data it's not necessarily big data but it's it's more data and performances and is an important issue OK I think laws it's a few
ideas and with few informations about what we do in risk assessment and risk analysis in the insurance business thanks a lot
Eichtheorie
Räumliche Anordnung
Physikalisches System
URL
Computeranimation
Informationsmanagement
Bit
Punkt
Natürliche Zahl
Extrempunkt
Analysis
Computeranimation
Meter
Wurzel <Mathematik>
Gerade
Verschiebungsoperator
DoS-Attacke
Parametersystem
Kategorie <Mathematik>
Cybersex
Gebäude <Mathematik>
Güte der Anpassung
Schwach besetzte Matrix
Biprodukt
Frequenz
Ereignishorizont
Katastrophentheorie
Teilbarkeit
Garbentheorie
URL
Information
Makrobefehl
Parametrische Erregung
Instantiierung
Subtraktion
Physikalismus
Interaktives Fernsehen
Term
Code
Virtuelle Maschine
Lesezeichen <Internet>
Perspektive
Datentyp
Nuklearer Raum
Inhalt <Mathematik>
Ereignishorizont
Bildgebendes Verfahren
Informationsmanagement
Analysis
Leistung <Physik>
Soundverarbeitung
Varianz
Gerade
Quick-Sort
Office-Paket
Flächeninhalt
Codierung
Verbandstheorie
Wort <Informatik>
Faktor <Algebra>
Räumliche Anordnung
Computerarchitektur
Zeitzone
Innerer Punkt
DoS-Attacke
Softwaretest
Einfügungsdämpfung
Spyware
Natürliche Zahl
Natürliche Zahl
Term
Ereignishorizont
Computeranimation
Gesetz <Physik>
Endlicher Graph
Mapping <Computergraphik>
Datentyp
Räumliche Anordnung
Verbandstheorie
Information
Ordnung <Mathematik>
Ereignishorizont
Instantiierung
Bit
Einfügungsdämpfung
Gewichtete Summe
Prozess <Physik>
Punkt
Natürliche Zahl
Natürliche Zahl
Computerunterstützte Übersetzung
Information
Computeranimation
Gradient
Metropolitan area network
Typentheorie
Schnitt <Graphentheorie>
Gerade
Softwaretest
Kraftfahrzeugmechatroniker
Datentyp
Sichtenkonzept
Katastrophentheorie
Ereignishorizont
Endlicher Graph
Vier
Information
URL
Computerunterstützte Übersetzung
Instantiierung
Subtraktion
Kontrollstruktur
Zellularer Automat
Unrundheit
Analytische Menge
Term
Physikalisches System
Informationsmodellierung
Hasard <Digitaltechnik>
Neunzehn
Ereignishorizont
Informationsmanagement
Analysis
Beobachtungsstudie
DISMA
Relativitätstheorie
Hasard <Digitaltechnik>
Mailing-Liste
Paarvergleich
Sollkonzept
Objektklasse
Mapping <Computergraphik>
Skalarprodukt
Flächeninhalt
Case-Modding
Räumliche Anordnung
Einfügungsdämpfung
Personal Area Network
Telekommunikation
Bit
Total <Mathematik>
Klassische Physik
Natürliche Zahl
Gewichtete Summe
Kartesische Koordinaten
Computerunterstützte Übersetzung
Analysis
Computeranimation
Metropolitan area network
Systemprogrammierung
Client
Kommunalität
Hasard <Digitaltechnik>
Meter
Gerade
Einflussgröße
Analysis
Metropolitan area network
Kreisfläche
Aeroelastizität
Verhandlungs-Informationssystem
Klassische Physik
Datenmodell
Hasard <Digitaltechnik>
Sollkonzept
Ein-Ausgabe
Bitrate
Design by Contract
Mapping <Computergraphik>
Flächeninhalt
Gerade Zahl
Information
Bitrate
Mapping <Computergraphik>
Gewichtete Summe
Total <Mathematik>
Punkt
Kontrollstruktur
Gamecontroller
Zahlenbereich
Kartesische Koordinaten
Term
Computeranimation
Attributierte Grammatik
Satellitensystem
Punkt
Euler-Winkel
Formale Sprache
Gewichtete Summe
Mathematik
Computerunterstützte Übersetzung
Kartesische Koordinaten
Gradient
Gesetz <Physik>
Analysis
Statistische Hypothese
Computeranimation
Homepage
Netzwerktopologie
Spezialrechner
Einheit <Mathematik>
Nichtlineares Zuordnungsproblem
Typentheorie
Mehragentensystem
Mapping <Computergraphik>
Flächeninhalt
Bilderkennung
Elektronischer Programmführer
DoS-Attacke
App <Programm>
Sichtenkonzept
Verhandlungs-Informationssystem
Gebäude <Mathematik>
Stellenring
Speicher <Informatik>
TLS
Soziale Software
Ereignishorizont
Katastrophentheorie
Dichte <Physik>
Arithmetisches Mittel
Dienst <Informatik>
Twitter <Softwareplattform>
COM
Fünf
Information
Cloud Computing
Datenfluss
Simulation
Prozessautomation
Message-Passing
Instantiierung
Kreisbewegung
Web Site
Wellenlehre
Stab
Taupunkt
EDV-Beratung
Sprachsynthese
Informationsmanagement
Term
Bildschirmmaske
Message-Passing
Schätzung
Neunzehn
Speicher <Informatik>
Maßerweiterung
Bildgebendes Verfahren
Analysis
Informationsmanagement
Binärdaten
Expertensystem
Physikalisches System
Sollkonzept
Satellitensystem
Mapping <Computergraphik>
Quadratzahl
Flächeninhalt
Formale Sprache
Mereologie
Hypermedia
Ruhmasse
Analytische Menge
Wort <Informatik>
Kantenfärbung
Einfügungsdämpfung
Computeranimation

Metadaten

Formale Metadaten

Titel Keynote III - Geospatial Analytics in Risk Management
Untertitel Geospatial Analytics in Risk Management
Serientitel FOSS4G Bonn 2016
Teil 65
Anzahl der Teile 193
Autor Zerweck, Thomas
Lizenz CC-Namensnennung 3.0 Deutschland:
Sie dürfen das Werk bzw. den Inhalt zu jedem legalen Zweck nutzen, verändern und in unveränderter oder veränderter Form vervielfältigen, verbreiten und öffentlich zugänglich machen, sofern Sie den Namen des Autors/Rechteinhabers in der von ihm festgelegten Weise nennen.
DOI 10.5446/20461
Herausgeber FOSS4G
OSGeo
Erscheinungsjahr 2016
Sprache Englisch

Technische Metadaten

Dauer 30:12

Inhaltliche Metadaten

Fachgebiet Informatik
Abstract At the Joint Research Centre (JRC), scientists involved in maritime situational awareness are confronted with a growing volume of data. Every day millions of ship positions from terrestrial and satellite receivers are gathered globally and in real-time, as well as optical and radar Earth Observation images, leading to a significant variety of data. To support the researchers, policy makers and operational authorities in their activities a analysis platform with WebGIS functionality has been developed with the aim of turning data into valuable information and demonstrating pre-operational tools for maritime awareness. The platform is mostly based on FOSS software and consists of a front-end visualization tool and a back-end analysis engine. Fusion algorithms provide the ability to integrate data from multiple sources on the fly. A series of tools provide predictive analysis, activity mapping, anomaly detection, and cross disciplinary information, to support maritime security and safety and to improve marine knowledge. The web application is developed using open source programming languages (e.g. Javascript, Python), frameworks (e.g. Django, Geoserver), and interchange data format (JSON) to enable researchers to seamlessly integrate ad hoc algorithms developed in scientific languages (e.g. R, Matlab). A case study will be presented, showing examples of how the WebGIS architecture can provide visualisation and analysis tools to support decision makers and scientific and operational actors in the fields of fisheries science, maritime spatial planning, and maritime surveillance.

Ähnliche Filme

Loading...