“Airborne And/Or Spaceborne Optical Flood And Flood Damage Sensory System And Method Thereof” in Patent Application Approval Process (USPTO 20230401651): Swiss Reinsurance Company Ltd.
2024 JAN 03 (NewsRx) -- By a
This patent application is assigned to
The following quote was obtained by the news editors from the background information supplied by the inventors: “Flood, and in general disaster detection, has been one of the most active research areas in remote sensing today because saving human lives is one of the priorities once a disaster occurred. It is crucial in the coordination of fast response actions after a destructive disaster such as landslide and flood. Prior art systems have primarily concentrated on detecting changes occurred due to disaster, depending solely on in-situ sensors, and manually adjusted image processing techniques, such as band differencing and band rationing, post-classification comparison and object-based change detection method. To increase the accuracy of detection, some systems implement machine learning to improve the efficiency of extracting feature. Some prior art detection system use detection based on machine learning, e.g. hierarchical shape features in the bags-of-visual words setting to detect large-scale damage. Some of the cyclone track forecast systems use artificial neural networks, as e.g. multilayer feedforward neural networks, radial basis neural networks, and Random Forests in earthquake damage. Other damage detection system use 2D and 3D feature of the scene or execute deep learning method in geological disaster recognition.
“However, still, prior disaster detection systems are mostly focusing on in-situ sensors, and they are unsophisticated. Therefore, they encounter several significant problems. For instance, the range for inspecting the occurrence of the disaster is limited due to the inadequate number of sensor and also the accuracy of information transmission is low due to verbally transmitted information. This is also true for satellite imagery-based systems. For those systems, the systems involved are also often unable to handle a massive amount of satellite imageries and detect disaster occurrence in short period of time. Consequently, this may lead to misinterpretation of information or overlook of occurrence of a disaster. Based on this example, it shows the fact that it is difficult to access immediate performance improvement on disaster detection and management based on prior art systems. Therefore, one technical objective is to build an automatic disaster detection system through inspecting the occurrence of a disaster in a broader range via satellite or aerial imagery and monitoring every single disaster, e.g. assisted by deep learning techniques as
“Reliable flood recognition systems are technically especially needed. Among the most impacting, damaging, and destructive natural or geophysical disaster of the world, floods are most frequent and uncertain type. Floods endangers lives, properties, infrastructures and damage a lot of livelihoods within a short period of time. FIG. 1 showing the physical impact of floods measured by monetary losses incurred in different countries. Controlling floods are difficult, but minimizing the impact by technical approaches is necessary. It is difficult to identify which measure is the better strategy and policy to deal with the floods. The combination of the human vulnerability and the physical exposures result in flood hazards. These losses and hazards can be minimized by making aware the public beforehand by providing them the reliable and suitable measuring data about flood risks, i.e. about the measurable probability value of having a certain impact strength to an object by an occurring flood event with a certain strength. Reliable prediction by technical forecast systems relying on measuring parameter values, preparedness, prevention, diminishing, and damage assessment are the stages of flood disaster management. Flood inundation maps are an important technical tool for providing the data in an accessible way. They reflect for different flood event types, the topographic forecasted pattern of a particular site, the sum of people and physical objects at risk, population anticipation and coping with the disaster and flood protection works. These are a crucial technical requirement for automated flood risk mitigation and risk-transfer rate pricing, municipal planning, ecological studies and set up of emergency action plans. Advancements in Remote Sensing (RS), technical modelling and forecasting and Geographic Information Systems (GIS) turned out to be important and particularly technically useful in flood inundation mapping. Floods can be predicted and flood risk areas can be identified via modelling with appropriately selected sensory input like hydrologic engineering centers-river analysis system (HEC-RAS) and hydrologic engineering centers-hydrologic modelling system (HEC-HMS) clubbing with GIS and Remote Sensing(RS). For example, for one-dimensional and unsteady-flow simulations of the designed floods, HEC-RAS and GIS can be used. Flood maps be generated for different return periods and these maps can be mapped to provide a comparison with other maps, e.g. using gradient or deviation measurements. This can be required for the technical prediction of floods.
“Not all flood events have the same impact, wherein the impact may vary in strength as well as in type and time duration and topographic parameters e.g. influencing the flow strength and direction etc. In urban contexts, for example, flooding can e.g. pose a significant hazard to moving vehicles and causes traffic disruption by placing water flow in the transportation network, resulting in vehicles being swept away, injuries, and the loss of life of passengers. The remote detection of urban flooding over a large area will allow cities to develop flood maps to reduce risk during weather events. Mapping urban flood events is a challenge for three main reasons: the urban environment is highly complex with waterways at submeter resolutions, the flooding will be shallow and ephemeral, and ponding means that the flooding extent will be discontinuous. Hydrologic models that are the conventional approach in flood forecasting struggle with these factors, making the application of these techniques difficult. Attempts have been made in the prior art to map urban flooding and flood risk with traditional prior art methods. However, high resolution hydrologic modelling structures may be effective at small scales (e.g., a few urban blocks) but the computational resources and highly accurate inputs required to properly model urban flooding at the community scale are not widely available with the current technology. These limiting factors exemplify the need to find technically based methods of mapping or predicting flooding that are less computationally intensive. The advantage of remote sensing is flood detection for large scale flood mapping without the need for highly accurate inputs and computationally intense processes to advance flood risk management.
“While extreme flooding, especially that which falls in the 100-year event category, is quite understood, and mapped by a plurality of prior art systems, minor flooding is difficult to map and predict. This less severe flooding, known as nuisance flooding or NF, poses less of a hazard to lives and property, but can still be inconvenient or even dangerous, especially to drivers. Though drier regions such as
“In the technical field of remote sensing, systems have been developed in flood detection using optical methods such as aerial photographs or satellite imagery, such as SAR and LiDAR (Light Detection and Ranging) systems. SAR, or Synthetic Aperture Radar, is an especially promising technique. As an active sensor, the radar can detect the Earth’s surface no matter what time of day it is or what cloud conditions prevail. Some prior art systems for the detection of flooding with SAR try to combine SAR imagery measurements from COSMO-SkyMed (Agency Spaziale Italiana,
There is additional background information. Please visit full patent to read further.”
In addition to the background information obtained for this patent application, NewsRx journalists also obtained the inventors’ summary information for this patent application: “It is one object of the present invention to provide an automated system and method for reliable forward-looking measurements and ratings of physical impacts of occurring location-dependent catastrophic events, as flood events, to a specific object, and in automated conduct and provision/generation of appropriate covers and/or hedging against the impacted damage to the specific object. It is further an object of this invention to provide a new and better automated system and method for providing a dynamic parametric cover, which does not have the above-mentioned disadvantages of the prior art. In particular, it is an object of the present invention to provide a risk-transfer cover based on an extend of a flooded area. Further it is an object, to generate a pricing based on the chosen limit (payout cover) as well as exposure (flooded area) of the insured. The extent of flooded area is generated by assessing an Area of Interest (AOI) using automated systems such as Synthetic Aperture Radar or Drones and by dividing the area into equally spaced measuring points. In ideal case, the system should be automated to disperse payments. The payments are dispersed via an electronic payment transfer module based on the generated parametric coverage monetary pay-out parameter. In particular, it is an object of the present invention to provide an automated method and system for providing dynamic parametric cover to an individual in case of an occurrence of a flood event by using an adaptive risk-transfer structure based on physical flood event measurements.
“According to the invention, the above-mentioned objects related to airborne and/or spaceborne optical flood sensory systems and methods for measuring and/or forecasting a weightage-specific, quantitative flooding measure value and/or a weightage-specific, quantified flooding impact extent measure value, the weightage being based on an object density of a selected topographic and/or geographic area impacted by an occurrence of a flood event, are achieved, particularly, (i) by measuring, by means of aerial and/or space-based remote sensing devices, digital imagery sensory data and transmitting said imagery sensory data via a data transmission link to a central ground station, (ii) by capturing, by a predefined data structure of a flood map generator, a geographic and/or topographic area to be covered, the data structure at least comprising definable area parameters capturing geographic location and/or geographic extent of said geographic and/or topographic area, and generating, by the flood map generator, a flood map based on the transmitted digital imagery sensory data using the predefined data structure, (iii) by splitting the geographic area to be covered by a spatial grid with equidistant grid cells of definable size, (iv) by detecting and aggregating, for each grid cell or group of grid cells of the spatial grid, definable physical objects located in a specific grid cell or group of grid cells and generating for each grid cell or group of grid cells an object density-based weightage value, and applying a normalized weight to each of the grid cells by dividing the weight per grid cell with the sum of weights for all the grid cells of the grid, (v) by measuring, after an occurrence of a flood event, an affected area of said geographic area based on measuring a flooding within the grid cells of the spatial grid, wherein grid cells measured as flooded are contributing to the measured affected area while grid cells measured as not flooded are not contributing to the measured affected area, and (vi) measuring a summed up value of the normalized weights for all the affected grid cells, and measuring the flooding extent measure value and/or flooding impact extent measure value of the affected area based on a pre-defined trigger and said summed up value of normalized weights.
“This has, inter alia, the advantage that an automated cover transfer, e.g. an appropriately adapted payout and/or electronic payment transfer signaling is based on measurable parameters, i.e. the optical measured extend of flooded area and the corresponding weightage for each grid cell. The inventive system allows to user-specific parametrization and setting of a total area to be covered (Area of Interest-AOI). This area to be covered is split, in particular dynamically split based on the geographically and/or topographically and/or land-cover-induced required resolution (urban and/or rural and/or highly jointed and/or high/low density of situated objects etc.) into a spatial grid with an adaptable size of spatial grid cells, for example, of ˜500 m x 500n (0.005 x 0.005 deg). This technical structure allows to assign a weightage factor for each grid cell (or group of grid cells). The weightage can be based on the exposure of one or a set of objects to be covered, population density, building stock and/or kind of buildings etc. This can be predefined and/or dynamically captured or adapted by object recognition of the optical sensory data. The inventive application of normalized weight to each of the grid cells (dividing the weight per cell with the sum of weights for all the grids) allow to aggregate the different impact strength of each grid cell to a target total, i.e. to measurably parameterize the total impact strength based on the optical measuring values. A threshold trigger to automatically identify affected grid cells after a flood event, can be set to be measured as totally flooded, or a definable percentage by the threshold trigger, providing a large adaptability and flexibility of the technical approach, which cannot be provided by the know prior art systems. Further, by generating the sum of the normalized weights for all the affected grid cells, the cover, e.g. the payout transfer, can be based on an adaptable or pre-defined trigger operation or function and the measurable captured sum of weights. The present invention also allows to set priorities, for example, for the areas, which are having more exposure either by the number of physical objects located therein, or by the geographic characteristics influencing the measured exposure value, or both of them. In this embodiment variant, area of lower interest can e.g. be given weightage of 0 and thus excluded from calculations. Finally, the technical structure of the inventive system also allows to be customized user- or client-specifically based on different types of weights related e.g. to population density, operative exposure, type of industrial or agriculture exposure etc. It is to be mentioned, that since the inventive system allows to add weights to each cell allows to improve the technical ability of the system to reflect the actual riskiness of the underlying set of objects to be covered. It is clear that depending on the size of the grid and the AOI, the present inventive system can end to comprise a lot of grid cells to be measured. Lower grid cells will be better in capturing variation of flood; however this can be computationally in respect to the required processing power challenging.
“In an embodiment variant, the method further comprises (i) providing a dynamic parametric flood impact cover for an object physically impacted by the occurrence of the flood event by using an adaptive risk-transfer structure based on the flooding extent measure value and/or the flooding impact extent measure value, (ii) generating the parametric coverage covering a possible loss associated with the occurrence of the flood event and impacting the geographic area measured by the affected area, as per the adjustable risk-transfer structure a threshold measure and is triggered by a threshold-trigger, wherein the threshold-trigger is selected from a percentage of the affected area given by the measured affected area to the geographic area; and (iii) transferring, by an electronic payment transfer module, based on the generated parametric coverage monetary pay-out parameter values by electronic payment transfer to the individual.
“The grid cells can e.g. be measured as flooded when each grid cell of a specified area is flooded. The grid cells can e.g. be regularly spaced within the spatial grid with a pre-definable spacing. The grid cells can further e.g. be essentially 0.005 x 0.005 deg grid cells. The grid cells can be defined as grid cells of two dimensional m x n blocks. The m x n blocks are of approx. 8.72 radian. The network points measured as flooded can e.g. be determined using at least a neural network approach, and the affected area is measured using airborne and/spaceborne imaging devices comprising optical sensing devices of unmanned or manned aircrafts, drones, zeppelins, satellites and/or spacecrafts.
“In another embodiment of the invention, wherein a premium is calculated based on the selected payout coverage. Further, the geographic area is of unvarying landscape representative of area covered by dry land and wetland. Further, the occurrence of the flood event is detected using loopback signaling.”
The claims supplied by the inventors are:
“1. An airborne and/or spaceborne optical flood sensory method for measuring and/or forecasting a weightage-specific, quantitative flooding measure value and/or a weightage-specific, quantified flooding impact measure value, the weightage being based on an object density of a geographic and/or topographic area impacted by an occurrence of a flood event, the method comprising: measuring, by aerial and/or space-based remote sensing devices, digital imagery sensory data; transmitting said digital imagery sensory data via a data transmission link to a central ground station; capturing, by a predefined data structure of a flood map generator, the geographic and/or topographic area, the predefined data structure at least comprising definable area parameters capturing a geographic location and/or a geographic extent of said geographic and/or topographic area; generating, by the flood map generator, a flood map based on the transmitted digital imagery sensory data using the predefined data structure; splitting, by the central ground station, the geographic and/or topographic area by a spatial grid with equidistant or adjusted grid cells of a definable or adjustably determined size; detecting and aggregating, for each grid cell or group of grid cells of the spatial grid, definable physical objects located in a specific grid cell or group of grid cells; generating for each grid cell or group of grid cells an object density-based weightage value; applying a normalized weight to each of the grid cells by dividing a weight per grid cell with a sum of weights for all the grid cells of the grid; measuring, after the occurrence of the flood event, an affected area of said geographic and/or topographic area based on measuring a flooding within the grid cells of the spatial grid, grid cells measured as flooded contributing to the measured affected area while grid cells measured as not flooded are contributing to an area measured as not affected; measuring a summed up value of the normalized weights for all the affected grid cells; and measuring a flooding extent measure and/or flooding impact extent measure value of the affected area based on a pre-defined trigger and said summed up value of normalized weights.
“2. The method according to claim 1, wherein the measuring of the flooding within the grid cells of the spatial grid is based on a measured total flooding of a grid cell and/or a definable flooded minimum percentage of a grid cell.
“3. The method according to claim 1, wherein the object density-based weightage value is set to 0 to grid cells of the spatial grid having a lower interest, excluding those grid cells from measurements.
“4. The method according to claim 1, further comprising assigning, for an operation of the pre-defined trigger, a relative weight to each grid cell, wherein aggregated relative weights of all grid cells sum up to a total value of 1.
“5. The method according to claim 4, further comprising determining the relative weight of each grid cell by a proxy weight adjusted to reflect a specific distribution of pre-defined object-specific and/or exposure-specific values of the definable physical objects located in the grid cells of the spatial grid.
“6. The method according to claim 1, further comprising triggering, in a case of all grid cells being measured as affected, monetary payout transfer of 100% of a pre-definable maximal cover.
“7. The method according to claim 1, further comprising: providing a dynamic parametric flood impact cover for an object physically impacted by the occurrence of the flood event by using an adaptive risk-transfer structure based on the flooding extent measure value and/or the flooding impact extent measure value, generating parametric coverage covering a possible loss associated with the occurrence of the flood event and impacting the geographic and/or topographic area measured by the affected area, by the adaptive risk-transfer structure adjusted based on the trigger and the measured flooding extent measure value and/or flooding impact extent measure value, and transferring, by an electronic payment transfer module, based on the generated parametric coverage monetary pay-out parameter values by electronic payment transfer to an individual.
“8. The method according to claim 1, wherein cell grids are measured as flooded when each grid cell of a specified area is flooded.
“9. The method according to claim 1, wherein the grid cells are regularly spaced within the spatial grid with a pre-definable spacing.
“10. The method according to claim 9, wherein the grid cells are essentially 500 m x 500 m and/or 0.005 x 0.005 deg grid cells.
“11. The method according to claim 9, wherein the grid cells represent two dimensional m x n blocks.
“12. The method according to claim 1, wherein the geographic and/or topographic area includes unvarying landscape representative of an area covered by dry land and wetland.
“13. The method according to claim 1, wherein the occurrence of the flood event is detected using loopback signalling.
“14. The method according to claim 1, wherein the grid cells measured as flooded are determined using at least a neural network approach.
“15. The method according to claim 1, wherein the aerial and/or space-based remote sensing devices at least include unmanned or manned aircraft systems, and/or drones comprising airborne optical measuring systems, and/or satellites, and/or spacecrafts comprising spaceborne optical measuring systems.
“16. The method according to claim 1, wherein the affected area is measured using on-air imaging devices.
“17. The method according to claim 1, further comprising generating a premium based on a selected payout coverage.
“18. An optical-based flood impact measuring and forecasting system for measuring and/or forecasting a weightage-specific, quantitative flooding measure value and/or a weightage-specific, quantified flooding impact extent measure value, the weightage being based on an object density of a geographic and/or topographic area impacted by an occurrence of a flood event, the system comprising: aerial and/or space-based remote sensing devices configured to measure digital imagery sensory data and transmit said digital imagery sensory data via a data transmission link to a central ground station, a flood map generator including a predefined data structure and configured to capture the geographic and/or topographic area, the predefined data structure at least comprising definable area parameters capturing a geographic location and/or geographic extent of said geographic and/or topographic area; and generate a flood map based on the transmitted digital imagery sensory data using the predefined data structure, the and/or topographic geographic area being split by a spatial grid with equidistant grid cells of definable size, a density aggregator configured to detect and aggregate, for each grid cell or group of grid cells of the spatial grid, definable physical objects located in a specific grid cell or group of grid cells; generate for each grid cell or group of grid cells an object density-based weightage value; and apply a normalized weight to each of the grid cells by dividing a weight per grid cell with a sum of weights for all the grid cells of the grid, a flood detector configured to measure, after the occurrence of the flood event, an affected area of said geographic and/or topographic area based on measuring a flooding within the grid cells of the spatial grid, grid cells measured as flooded contributing to the measured affected area while grid cells measured as not flooded are not contributing to the measured affected area, and a trigger configured to measure a summed up value of the normalized weights for all the affected grid cells; and measure a flooding extent measure value and/or flooding impact extent measure value of the affected area based on a pre-defined trigger function and said summed up value of normalized weights.
“19. The system according to claim 18, wherein a parametric coverage is generated covering a possible loss associated with the occurrence of the flood event and impacting the geographic and/or topographic area measured by the affected area, as per an adjustable risk-transfer structure a threshold measure and is triggered by a threshold-trigger, the threshold-trigger is selected from a weighted percentage of the affected area given by the weighted affected grid cells, and by an electronic payment transfer module, based on the generated parametric coverage, monetary pay-out parameter values are transferred by electronic payment transfer to an individual.
“20. The system according to claim 18, wherein the grid cells are measured as flooded when each grid cell of a specified area is flooded.
“21. The system according to claim 18, wherein the grid cells are regularly spaced within the spatial grid with a pre-definable spacing.
“22. The system according to claim 21, wherein the grid cells are essentially 500 m x 500 m and/or 0.005 x 0.005 deg grid cells.
“23. The system according to claim 18, wherein the grid cells are defined two dimensional m x n blocks.
“24. The system according to claim 18, wherein the geographic and/or topographic area includes unvarying landscape representative of an area covered by dry land and wetland.
“25. The system according to claim 18, wherein the occurrence of the flood event is detected using loopback signalling.
“26. The system according to claim 18, wherein a premium is calculated based on the selected payout coverage.
“27. The system according to claim 18, wherein mesh network points measured as flooded are determined using at least a neural network approach.”
URL and more information on this patent application, see: BERNIER, Carl; MICHEL, Aaron; SREENIVASAN, Vipin Kozhikkoottingal; SUNDERMANN, Lukas. Airborne And/Or Spaceborne Optical Flood And Flood Damage Sensory System And Method Thereof.
(Our reports deliver fact-based news of research and discoveries from around the world.)
Patent Application Titled “Transportation Analytics Systems And Methods Using A Mobility Device Embedded Within A Vehicle” Published Online (USPTO 20230401650): Patent Application
Patent Issued for Dynamic limiting of vehicle operation based on interior configurations (USPTO 11840243): State Farm Mutual Automobile Insurance Company
Advisor News
Annuity News
Health/Employee Benefits News
Life Insurance News