BLUE VISION EARLY WARNING DISASTER SYSTEM BASED ON MULTISPECTRAL REMOTE SENSING OF THE EARTH Plamenka Borovska, Desislava Ivanova Computer Systems Department Technical University of Sofia CONTENT Remote Sensing of the Earth Early Warning Disaster System – Problem Statement Blue Vision Software Experimental Platform Results and Analysis Conclusion and Future work REMOTE SENSING OF THE EARTH Earth remote sensing is data collection on the environment, geology, climate, and other characteristics of the Earth by means of sensors positioned in the air or in Earth orbit. Sensors can be mounted on different platform ladder, tall building, crane balloon plane or other airborne structure satellite orbiting the Earth REMOTE SENSING EARTH Sensors have different parameters in terms of resolution: Spectral Resolution from 3 to 220 spectral bands Spatial Resolution from 0.4 to 1000 m Temporal Resolution OF THE from few hours to more than 16 days Remote sensing is quick and relatively cheap technique for monitoring Earth’s surface on a large scale EARLY WARNING DISASTER SYSTEM PROBLEM STATEMENT Disasters can be detected Fires Deforestation Soil Salinity Water pollution Flood detection Water pollution Soil Salinity Deforestation Fire Flooding BLUE VISION SOFTWARE BLUE VISION Software: parallel computational models 5 modules implement parallel algorithms for detection of: PARFIRE for fire detection PARDEFOR for detection of deforestation PARSOIL for detection of high soil salinity PARWATER for detection of water pollution PARFLOOD for flood detection MODIS - MODERATE RESOLUTION IMAGING SPECTRORADIOMETER On board of NASA’s Terra and Aqua satellites near-polar orbit four images per day two day and two night time TERRA satellite 36 spectral bands 705 km above the Earth surface in visible and infrared spectrum spatial resolution 250 m (bands 1-2) 500 m (bands 3-7) 1000 m (bands 8-36) AQUA satellite HDF (Hierarchical Data Format) files Provides relevant data for disaster monitoring based on multispectral analysis ALGORITHMS Based on multispectral analysis Utilize data in several spectral bands NASA’s Enhanced Fire Detection Algorithm Normalized Difference Vegetation Index (NDVI) BRDF – Bidirectional Reflectance Distribution Function Albedo Vegetation indices FPAR - Fraction of Photosynthetically Active Radiation LAI – leaf area index Soil Salinity Index NDVI - normalized difference vegetation index Salinity Index NASA’s Chlorophyll Water Analyses Algorithm the algorithm uses the temperatures generated in the thermal infrared spectral channels of MODIS sensor at a wavelength of 4 μm and 11μm. The algorithm determines the areas of water pollution by assessing the concentration of chlorophyll, which is used as an indicator of phytoplankton biomass. Time change detection PARALLEL COMPUTATIONAL MODELS SPMD parallel paradigm small communication overhead Results gathered by master process position coordinates PARALLEL COMPUTATIONAL MODELS Message Passing Interface (MPI) distributed memory model course grained parallelism Multithreading (OpenMP) shared memory model fine grained parallelism PARALLEL COMPUTATIONAL MODELS Hybrid parallel model MPI + OpenMP HDF EXPERIMENTAL PLATFORM Bulgarian Supercomputer – IBM Blue Gene/P Heterogeneous Compact Computer Cluster – “High-Performance and Cloud Computing Lab”, Computer System Department, Technical University - Sofia “High-Performance and Cloud Computing Lab”, Computer System Department RESULTS AND ANALYSIS Linear Speedup Good Scalability Processing of one Data Set RESULTS AND ANALYSIS Results Visualization Google map RESULTS AND ANALYSIS Multispectral Analysis of the Remote Sensing of the Earth BLUE VISION SOFTWARE PARFIRE, PARDEFOR, PARSOIL, PARWATER, PARFLOOD Good Scalability with respect to data sets and parallel computer architectures FUTURE WORK Improvements and Extension of Existing Early Warning Disaster System based on Multispectral Remote Sensing of the Earth RADAR SATELLITE IMAGING Earth-observing radar satellites data - Radar satellite data offer the great advantage, over its optical counterparts, of not being affected by meteorological conditions such as clouds, fog, etc., making it the sensor of choice when continuity of data must be ensured. CLASSIFIER - Improving radar observations of disasters with classifier based on parallel algorithm for implementation of Fast Wavelet Transforms (Mallat's pyramid algorith) THANK YOU FOR YOUR ATTENTION!
© Copyright 2019