Efficient flood waters analysis from spatio-temporal data fusion and statistics

A computer program product comprising:

• one or more computer readable storage medium, and program instructions collectively stored on the one or more computer readable storage medium, the program instructions executable by a computing system to cause the computing system to perform a method comprising:
• classifying regular waters by using cartographic data in a first location;
• generating, by one or more processors, a water stream network including a watershed based on elevation data, wherein the water stream network delineates a watershed starting from a location that has known flood waters, wherein the water stream network comprises an interconnected system of channels that collect water that subsequently drains to the watershed;
• performing statistical analysis over pixels classified as water bodies of spectral information to distinguish regular water from other lands from a multi-spectral satellite imagery comprising vectorized data, radio wave data and pulsed laser light data in visible and infrared wavelengths over water bodies including the regular waters and flood waters using the pixel statistics to identify pixels of flooded land within an identified water shed by separating image data within specific wavelength ranges across an electromagnetic spectrum by filters using spectral analysis in terms of spectrum of frequencies with frequency dependent energy values of photons;
• correlating the spectral statistics of the multi-spectral satellite imagery to kinetic energy of the flood waters using machine learning techniques and physical modeling;
• building a learning model based on the correlation between the spectral statistics and the flood waters with the kinetic energy;
• allowing, by the learning model, a distributed geospatial database to automatically generate geo-referenced raster imagery of estimates of flood waters kinetic energy, solely based on an input as minimal as a cartographic map of water bodies and a single multi-spectral satellite image;
• estimating kinetic energy of flood waters in a second location using the learning model;
• and
• evaluating a flooding risk for the second location based on the estimated flood waters kinetic energy in conjunction with a weather prediction for an upcoming flooding event.

A computer system comprising:

• one or more computer processors, one or more computer readable storage medium, and program instructions stored on the one or more computer readable storage medium for execution by at least one of the one or more computer processors, the program instructions, when being executed by the at least one of the one or more computer processors, cause the computer system to perform a method comprising:
• classifying regular waters by using cartographic data in a first location;
• generating, by one or more processors, a water stream network including a watershed based on elevation data, wherein the water stream network delineates a watershed starting from a location that has known flood waters, wherein the water stream network comprises an interconnected system of channels that collect water that subsequently drains to the watershed;
• performing statistical analysis over pixels classified as water bodies of spectral information to distinguish regular water from other lands from a multi-spectral satellite imagery comprising vectorized data, radio wave data and pulsed laser light data in visible and infrared wavelengths over water bodies including the regular waters and flood waters using the pixel statistics to identify pixels of flooded land within an identified water shed by separating image data within specific wavelength ranges across an electromagnetic spectrum by filters using spectral analysis in terms of spectrum of frequencies with frequency dependent energy values of photons;
• correlating the spectral statistics of the multi-spectral satellite imagery to kinetic energy of the flood waters using machine learning techniques and physical modeling;
• building a learning model based on the correlation between the spectral statistics and the flood waters with the kinetic energy;
• allowing, by the learning model, a distributed geospatial database to automatically generate geo-referenced raster imagery of estimates of flood waters kinetic energy, solely based on an input as minimal as a cartographic map of water bodies and a single multi-spectral satellite image;
• estimating kinetic energy of flood waters in a second location using the learning model;
• and
• evaluating a flooding risk for the second location based on the estimated flood waters kinetic energy in conjunction with a weather prediction for an upcoming flooding event.