Open Hub
Open Hub

 Settings |  Report Duplicate

0
I Use This!
Very Low Activity

Commits : Listings

Analyzed about 7 hours ago. based on code collected 1 day ago.
Nov 05, 2025 — Nov 05, 2026
Commit Message Contributor Files Modified Lines Added Lines Removed Code Location Date
1182. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Delaunay Triangulation plot - related to 1181 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Neural Network Model of Urban Extent, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Aerial transportation graph for Drone navigation, Autonomous Online Shopping Delivery and Drone Electronic Voting Machine, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 12 December 2021
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
--------------------------------------------------------------------------------------------------------------------------------------------- 1182. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Delaunay Triangulation plot - related to 1181 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Neural Network Model of Urban Extent, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Aerial transportation graph for Drone navigation, Autonomous Online Shopping Delivery and Drone Electronic Voting Machine, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 12 December 2021 --------------------------------------------------------------------------------------------------------------------------------------------- 1182.1 python-src/image_pattern_mining/ImageNet/GISUrbanSprawlAnalytics.py has been changed to define Function draw_delaunay_triangulation() to add Delaunay triangulation plot in testlogs/SEDAC_GPW4-11_PopulationDensity2020_edited-contourlabelled.jpg 1182.2 Delaunay triangulation is the dual of Voronoi diagram and quite crucial urban sprawl analytics tool as it approximates transportation graph (aerial and surface) between prominent urban contour centroids and thus could be a Hamiltonian (traverse each vertex once) or Eulerian circuit (traverse each edge once - https://networkx.org/documentation/stable/reference/algorithms/generated/networkx.algorithms.euler.eulerian_circuit.html#networkx.algorithms.euler.eulerian_circuit) estimator tool for autonomous drone delivery of services (Drone EVM, Drone online shopping delivery) so as to visit each edge connecting cities or each city vertex once. 1182.3 Delaunay triangulation plot has been added as layer to testlogs/SEDAC_GPW4-11_PopulationDensity2020_edited-contourlabelled.jpg by 8-connected lines of cv2.line() while Voronoi diagram has been plotted by antialiased cv2.line(). 1182.4 Logs and affected image files for this update are: python-src/image_pattern_mining/ImageNet/testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_FaceGraph.jpeg python-src/image_pattern_mining/ImageNet/testlogs/SEDAC_GPW4-11_PopulationDensity2020_edited-contourlabelled.jpg python-src/image_pattern_mining/ImageNet/testlogs/GISUrbanSprawlAnalytics.log.12December2021
Srinivasan Kannan
More... almost 5 years ago
-------------------------------------------------------------------------------------------------------------------------------------------- 1181. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Correction to FaceGraph Plot - Dual of Voronoi Diagram - Centrality Measures of Urban Sprawl Facegraph - related to 1180 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Neural Network Model of Urban Extent, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 10 December 2021 --------------------------------------------------------------------------------------------------------------------------------------------- 1181.1 ImageGraph_Keras_Theano.py has been updated to change the way facegraph is plotted - instead of centroids from cv2.connectedComponentsWithStatsWithAlgorithm(), centroids of the contours are now being used for plotting the facegraph which is the dual of Voronoi Diagram ensconcing the contour polynomials. Contour centroids are comprehensive and numerous compared to cv2.connectedComponentsWithStatsWithAlgorithm() and must be more suitable for urban sprawl analytics. 1181.2 GISUrbanSprawlAnalytics.py has been executed for this enhancement to compute a detailed facegraph of urban area contours and its Degree,Betweenness,Closeness and PageRank centrality measures for urban vertices which are essential ranking metrics. 1181.3 Following are the affected logs, Facegraph DOT and JPEG image files for this change: testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_FaceGraph.jpeg testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_ImageNet_Keras_Theano_Segmentation_FaceGraph.dot testlogs/GISUrbanSprawlAnalytics.log.10December2021
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
-------------------------------------------------------------------------------------------------------------------------------------------- 1181. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Correction to FaceGraph Plot - Dual of Voronoi Diagram - Centrality Measures of Urban Sprawl Facegraph - related to 1180 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Neural Network Model of Urban Extent, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 10 December 2021 --------------------------------------------------------------------------------------------------------------------------------------------- 1181.1 ImageGraph_Keras_Theano.py has been updated to change the way facegraph is plotted - instead of centroids from cv2.connectedComponentsWithStatsWithAlgorithm(), centroids of the contours are now being used for plotting the facegraph which is the dual of Voronoi Diagram ensconcing the contour polynomials. Contour centroids are comprehensive and numerous compared to cv2.connectedComponentsWithStatsWithAlgorithm() and must be more suitable for urban sprawl analytics. 1181.2 GISUrbanSprawlAnalytics.py has been executed for this enhancement to compute a detailed facegraph of urban area contours and its Degree,Betweenness,Closeness and PageRank centrality measures for urban vertices which are essential ranking metrics. 1181.3 Following are the affected logs, Facegraph DOT and JPEG image files for this change: testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_FaceGraph.jpeg testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_ImageNet_Keras_Theano_Segmentation_FaceGraph.dot testlogs/GISUrbanSprawlAnalytics.log.10December2021
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
updated references - GMIS and HBASE
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
1180. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Voronoi Tessellation Diagram implementation engulfing urban sprawl contours - related to 1174,1175,1179 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Neural Network Model of Urban Extent, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 9 December 2021
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
--------------------------------------------------------------------------------------------------------------------------------------------- 1180. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Voronoi Tessellation Diagram implementation engulfing urban sprawl contours - related to 1174,1175,1179 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Neural Network Model of Urban Extent, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 9 December 2021 --------------------------------------------------------------------------------------------------------------------------------------------- 1180.1 GISUrbanSprawlAnalytics.py has been updated to implement function draw_voronoi_tessellation() to draw Voronoi polygons surrounding contour polynomials of urban sprawl extents thus approximating them by a polygonal packing of 2D surface. 1180.2 Facets from Voronoi 2D planar subdivision are enumerated and polygons are drawn by OpenCV2 polylines(). 1180.3 Centroid of each polygon in tessellation is the centre of minimum enclosing circle around the urban sprawl contour polynomials. 1180.4 Voronoi diagram has been written as a layer on SEDAC_GPW4-11_PopulationDensity2020_edited-contourlabelled.jpg. 1180.5 Big urban areas are covered by multiple Voronoi polygons. Asymmetry in areas of the polygons is a measure of skewed development and every polygon is a mix of urban area and rural hinterland depending on it as nearest economic fulcrum for livelihood. 1180.6 Sustainable urban development therefore is to strive for almost equally sized Voronoi polygons. Area of Voronoi polygon around an urban contour is thus susceptible to expansion and future urbanization. 1180.7 python-src/image_pattern_mining/ImageNet/ImageGraph_Keras_Theano.py has been changed to revamp the for loops adding edges to facegraph of Voronoi tessellation 2D subdivision. 1180.8 Logs and contour-convexhull segmented images for this update: python-src/image_pattern_mining/ImageNet/testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_FaceGraph.jpeg python-src/image_pattern_mining/ImageNet/testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_ImageNet_Keras_Theano_Segmentation_FaceGraph.dot python-src/image_pattern_mining/ImageNet/testlogs/SEDAC_GPW4-11_PopulationDensity2020_edited-contourlabelled.jpg python-src/image_pattern_mining/ImageNet/testlogs/GISUrbanSprawlAnalytics.log.9December2021
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
index.rst for https://astroinfer.readthedocs.io/en/latest/
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
--------------------------------------------------------------------------------------------------------------------------------------------- 1179. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Urban Sprawl Extent from NASA SEDAC 2020 GPW 4.11 Population Density by contour, convex hull segmentation and minimum enclosing circles - related to 1174,1175 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Neural Network Model of Urban Extent, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 8 December 2021 ---------------------------------------------------------------------------------------------------------------------------------------------
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
--------------------------------------------------------------------------------------------------------------------------------------------- 1179. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Urban Sprawl Extent from NASA SEDAC 2020 GPW 4.11 Population Density by contour, convex hull segmentation and minimum enclosing circles - related to 1174,1175 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Neural Network Model of Urban Extent, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 8 December 2021 --------------------------------------------------------------------------------------------------------------------------------------------- 1179.1 Estimation on Urban Sprawls of Southern India (which has since been chosen because of heavy urbanisation) from NASA SEDAC GPW 4.11 Population count 2020 imagery https://sedac.ciesin.columbia.edu/data/set/gpw-v4-population-count-rev11/data-download in 1175 was based on population count which has been revised in Population density 2020 imagery https://sedac.ciesin.columbia.edu/data/set/gpw-v4-population-density-rev11 to include latest urban area boundaries and new urban sprawls. 1179.2 SEDAC GPW 4.11 Population Density 2020 image SEDAC_GPW4-11_PopulationDensity2020.jpeg has been GIMP photoshopped to remove non-urban area pixels and edited image is stored in SEDAC_GPW4-11_PopulationDensity2020_edited.jpeg 1179.3 SEDAC_GPW4-11_PopulationDensity2020_edited.jpeg has been contour and convex hull segmented and minimum enclosing circles are drawn around urban sprawls. 1179.4 Urban sprawl ranking are updated accordingly and written to logs testlogs/GISUrbanSprawlAnalytics.log.8December2021. 1179.5 Similar to https://sedac.ciesin.columbia.edu/data/set/urbanspatial-urban-extents-viirs-modis-us-2015/maps/services urban extent learner which uses sophisticated machine learning methods of Random forests, Gradient boost machine, Ensemble and neural networks for US cities based on NASA MODIS and VIIRS mentioned in 1175.12.8, following simple Neural network (perceptron) could be defined for learning urban sprawls based on SEDAC color coding and night lights (which is per se statistical while Urban sprawl extent estimation in NeuronRain is Computational geometric and polynomial packing based): 1179.5.1 For pixel value p, weight a and bias b, if a*p + b > threshold_brightness add pixel to urban area. 1179.6 Following are the affected logs and convexhull-contour segmented image files for SEDAC GPW 4.11 Population Density 2020: testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_FaceGraph.jpeg testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_ImageNet_Keras_Theano_Segmentation_FaceGraph.dot testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_contour_segmented.jpeg testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_convex_hull_segmented.jpeg testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationDensity2020_edited_segmented.jpg testlogs/SEDAC_GPW4-11_PopulationDensity2020_edited-contourlabelled.jpg testlogs/SEDAC_GPW4-11_PopulationDensity2020_edited.jpeg
Srinivasan Kannan
More... almost 5 years ago
ML models for Urban Sprawls from VIIRS and MODIS
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
Community detection and urban sprawls
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
Updated DNFSAT MARA for Urban sprawls
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
Updated references - SEDAC 4.11 Population density
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
+--------------------------------------------------------------------------------------------------------------------------------------------- +1178. (THEORY and FEATURE) GIS Analytics - MongoDB GridFS backend standalone client implementation - related to 1173,1174 and all sections on GIS Urban sprawl analytics and weather analytics,Streaming analytics, Merit of Large Scale Visuals - 6 December 2021 +---------------------------------------------------------------------------------------------------------------------------------------------
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
--------------------------------------------------------------------------------------------------------------------------------------------- 1178. (THEORY and FEATURE) GIS Analytics - MongoDB GridFS backend standalone client implementation - related to 1173,1174 and all sections on GIS Urban sprawl analytics and weather analytics,Streaming analytics, Merit of Large Scale Visuals - 6 December 2021 --------------------------------------------------------------------------------------------------------------------------------------------- 1178.1 New standalone MongoDB GridFS client python-src/backend/GISMongoDBGridFSStreamingClient.py has been implemented which can independently upload and download large scale visuals to and from MongoDB GridFS backend. 1178.2 Two functions streaming_upload() and streaming_download() have been defined in GISMongoDBGridFSStreamingClient.py which respectively wrap GridFS put() and get(). Visuals are lookedup and retrieved by fileid(s) created by put() and get(). 1178.3 Need for such a client separated from Streaming_AbstractGenerator facade arises because of necessity for an alternative command line interface upload and download facility for bulk visuals to and from GridFS without installing Robomongo3T and Studio3T. 1178.4 Storing large scale visuals in MongoDB GridFS is not straightforward and requires additional shape metadata. Function streaming_upload() also inserts the shape information per image and returns a tuple of image fileid, shape fileid and image name which are inturn used in streaming_download() to get the image and shape as strings. Image string is a flattened ndarray which is reshape()-d by shape information eval()-ed from shape fileid string. 1178.5 This client for large scale visuals can be plugged into NeuronRain backend/MongoDB_DBClient.py for text data which uses find()-insert_one() pair and Streaming_AbstractGenerator.py facade optionally. 1178.6 An example invocation of GISMongoDBGridFSStreamingClient.py uploads a contour labelled NASA SEDAC GPW 4.11 Urban Sprawl GIS image ../image_pattern_mining/ImageNet/testlogs/SEDAC_GPW4-11_PopulationEstimate2020_edited-contourlabelled.jpg to GridFS and downloads it to testlogs/GISMongoDBGridFSStreamingClient_ExampleImage.jpeg and the logs are at testlogs/GISMongoDBGridFSStreamingClient.log.6December2021
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
Updated BestPractices.txt
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
-------------------------------------------------------------------------------------------------------------------------------------------- 1177. (THEORY and FEATURE) GIS Urban Sprawl Analytics - a Multiple Agent Resource Allocation Algorithm - related to 1174,1175 and all sections on Fair division, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation, Constraint satisfaction problems, Ramsey Coloring of sequences, Arithmetic progressions - 3,4 December 2021 --------------------------------------------------------------------------------------------------------------------------------------------
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
Updated sections 1158 and 1174
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
Updated Requirements.txt
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
------------------------------------------------------------------------------------------------------------------------------------------- 1176. (THEORY and FEATURE) GIS Weather Analytics and Climate Analytics from OpenWeatherMap PyOWM and ECMWF CliMetLab - implementation - 30 November 2021 - related to 148,445,446,463,1165,1171 and all sections on Correlation between gravitational effects of Mined Celestial N-Body Patterns and terrestrial extreme weather events (or Gravitational effects on climate change), Drone natural obstacle avoidance, Drone autonomous online shopping delivery, Drone Electronic Voting Machine, Large Scale Visuals Recognition, Artificial Intelligence models for Climate Change ---------------------------------------------------------------------------------------------------------------------------------------------
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
------------------------------------------------------------------------------------------------------------------------------------------- 1176. (THEORY and FEATURE) GIS Weather Analytics and Climate Analytics from OpenWeatherMap PyOWM and ECMWF CliMetLab - implementation - 30 November 2021 - related to 148,445,446,463,1165,1171 and all sections on Correlation between gravitational effects of Mined Celestial N-Body Patterns and terrestrial extreme weather events (or Gravitational effects on climate change), Drone natural obstacle avoidance, Drone autonomous online shopping delivery, Drone Electronic Voting Machine, Large Scale Visuals Recognition, Artificial Intelligence models for Climate Change --------------------------------------------------------------------------------------------------------------------------------------------- 1176.1 GISWeatherAnalytics.py has been updated to define a new function weather_forecast() which imports Python client for OpenWeatherMap (https://openweathermap.org) - PyOWM - https://github.com/csparpa/pyowm - and makes REST API calls OpenWeatherMap weather data and OneCall forecast for a location by city name or latitude-longitude. 1176.2 PyOWM Weather details and forecast include humidity,temperature,rain,precipitation probability,wind,heat,clouds for a location. Forecast is made through one-call API for 1-week window per longitude-latitude. OpenWeatherMap sources weather forecasts from multitude of providers including ECMWF,NOAA. Function weather_forecast() might be invoked by a Drone autonomous delivery client or Drone Electronic Voting Machine and accordingly its mission plan could be charted avoiding longitude-latitude waypoints of extreme weather. An example invocation of current weather and 7-day forecast for location "Chennai" and its longitude-latitude has been shown in logs testlogs/GISWeatherAnalytics.log.30November2021. 1176.3 An alternative to PyOWM is ECMWF MetView Python Client - https://github.com/ecmwf/metview-python - but requires MetView 5.0 and above, significant preprocessing and shell script modifications (/usr/bin/metview) for environment variables to make it work. API access credentials are a prerequisite for access to ECMWF meteorological data by MARS client - https://confluence.ecmwf.int/display/WEBAPI/Access+MARS . MetView GUI can create python scripts for loading and analyzing datasets. 1176.4 Another function climate_analytics() has been defined which loads various climate datasources from ECMWF by CliMetLab python library and tries to model them using machine learning. CliMetLab obfuscates various dataset formats including GRIB. Presently few CliMetLab climate datasets - ECMWF-Copernicus-ERA5, NOAA Hurricane Dataset - HURDAT2, ECMWF-MARS, High-Low - have been sourced (optionally cast to Pandas Dataframes) and High-Low atmospheric pressure dataset is trained by a TensorFlow-Keras Sequential Linear Regression which could be used as forecast model - based on Jupyter notebook at https://climetlab.readthedocs.io/en/latest/examples/05-high-lows.html#Build-the-model. Logs testlogs/GISWeatherAnalytics.log.30November2021 print the trained model and its prediction on test high-low data. Such models add to the kitty of SequenceMining (by Class Association Rule-APrioriGSP,BioPython-ClustalOmega Multiple Sequence Alignment algorithms) models for correlating celestial n-body choreographies and terrestrial extreme weather events (Sections 17,148 and 445 detail some correlations already mined from USGS Earthquake and NOAA Hurricane datasets) 1176.5 ECMWF datasets ERA5, MARS and High-Low require ECMWF (https://apps.ecmwf.int/registration/) and Copernicus API Keys (https://cds.climate.copernicus.eu/api-how-to#install-the-cds-api-key) information in files ~/.cdsapirc and ~/.ecmwfapirc and there could be error messages of the form - " <user> has no access to service/mars " despite API key perhaps due to ECMWF MARS datacentre migration and dataset shutdown. Because of this limitation, ERA5 and MARS dataset invocations have been commented. 1176.6 Logs for this update are at testlogs/GISWeatherAnalytics.log.30November2021. Two functions for weather and climate segregate medium range weather forecast based on GIS and machine learnt analytics on historic climate data, the latter being an artificial intelligence challenge - Improve subseasonal-to-seasonal precipitation and temperature forecasts with Machine Learning/Artificial Intelligence - https://s2s-ai-challenge.github.io/. 1176.7 References: 1176.7.1 MetView Python - ECMWF - https://www.ecmwf.int/en/newsletter/162/computing/metviews-python-interface-opens-new-possibilities 1176.7.2 CliMetLab - https://events.ecmwf.int/event/211/contributions/1876/attachments/972/1700/Cloud-WS_Raoult.pdf 1176.7.3 MetView - https://cdn.knmi.nl/system/ckeditor_assets/attachments/112/egows2019_-_metview_in_a_pythonic_world_iain_russell_ecmwf.pdf 1176.7.4 MetView Python - https://www.ecmwf.int/sites/default/files/elibrary/2018/18720-metviews-new-python-interface.pdf 1176.7.5 OpenWeatherMap models - ECMWF-IFS,NOAA-GFS,GEM - https://openweathermap.org/models
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
1175. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Population Estimator from Urban Sprawl Contours - usecase study of few urban sprawls - related to 1174 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 21,22,23,24,25,26 November 2021
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
-------------------------------------------------------------------------------------------------------------------------------------------- 1175. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Population Estimator from Urban Sprawl Contours - usecase study of few urban sprawls - related to 1174 and all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics, Approximation of functions by polynomials, Weirstrass Theorem, Jordan Curve Theorem, Cellular Automaton Graph model of diffusion of opinions/memes/cybercrimes/pandemics, Multiple Agent Resource Allocation - 21,22,23,24,25,26 November 2021 -------------------------------------------------------------------------------------------------------------------------------------------- 1175.1 GISUrbanSprawlAnalytics.py has been updated to analyze NASA SEDAC GPW 4.11 Population Estimation 2020 imagery (revised from 2015 SEDAC GPW 4 estimates) for Southern India which has brought to light emergence of some new countermagnet urban sprawls between 2015 and 2020 (e.g Hosur UA as competitor to Bengaluru UA of almost equal area and density, Tirupur UA as countermagnet to Coimbatore UA, Amalgamation of Puducherry-Cuddalore as one huge urban sprawl of few million population). 1175.2 SEDAC GPW 4.11 Population Count 2020 image testlogs/SEDAC_GPW4-11_PopulationEstimate2020.jpeg has been downloaded and photoshopped by GNU Image Manipulation Program (GIMP) selection editor to remove non-urban low density area pixels by selecting only high population density urban areas. Few noise pixels along periphery of Urban Areas have been erased. Edited image has been written to testlogs/SEDAC_GPW4-11_PopulationEstimate2020_edited.jpeg 1175.3 Urban sprawl contour polynomials are closed curves sparsely packed on a 2D surface and by Jordan Curve Theorem any closed curve divides a planar region into interior and exterior half-plane regions. Simply connected regions do not have holes while multiply connected regions do. Thus unequal sparse packing of urban sprawl contours (as holes) on a 2D surface of a nation is multiply-connected. 1175.4 As there is no algorithm for packing arbitrary closed curves on a 2D surface, Voronoi tessellation diagram is the closest approximation of each urban sprawl closed curve contour by a polygon. By Weirstrass theorem, every function can be approximated by a series summation of polynomials within a bounded error and thus every Voronoi diagram polygon approximates an urban sprawl contour polynomial: |f(x) - l(x)| < epsilon f(x) = Urban sprawl contour polynomial l(x) = series summation of line equations for sides of Voronoi diagram polygon 1175.5 Earlier edited image testlogs/SEDAC_GPW4-11_PopulationEstimate2020_edited.jpeg has been contour and convex-hull segmented by GISUrbanSprawlAnalytics.py and minimum enclosing circles have been drawn around them. 1175.6 Estimating populations of Urban Areas requires conversion of Contour area to square kilometer area. Rough legend could be circumference_of_earth / length_of_GIS_imagery. 1175.7 Function urban_sprawl_from_segments() from GISUrbanSprawlAnalytics.py has been updated to pass on average population density as argument so as to compute population by formula contour_area_in_squarekilometers * population_density. 1175.8 Contour area to Square kilometer area conversion has been made configurable by passing ratio of contour area to square kilometer area as argument to urban_sprawl_from_segments(), because ratio depends on image size and requires prior knowledge from a training data of contour area and its corresponding square kilometer area E.g. Ratio of contour area 854.0 and corresponding square kilometer area of 266.0 for cityid 1356 (Kumbakonam UA) in SEDAC_GPW4-11_PopulationEstimate2020_edited-contourlabelled.jpg has been used as reference heuristic multiplicand for population density of 5000 per square kilometer area. 1175.9 Ratio of contour area of urban sprawl to total area of GIS image (height * width) has been computed which is an alternative ranking measure for urban areas. 1175.10 putText() has been changed for font color, size and area append has been removed for better clarity of cityid displayed. City id(s) are displayed only for urban sprawls of non-zero contour area. 1175.11 Urban Sprawl network of southern India has undergone a metamorphosis from 2015 to 2020 based on SEDAC GPW 4.11 mapping and thus exemplifies preferential attachment in this real social network vis-a-vis virtual social networks such as Facebook and Twitter. 1175.12 GIS References - Human settlement and Climate: 1175.12.1 GHSL - European union - Visual analytics - https://ghsl.jrc.ec.europa.eu/visualisation.php 1175.12.2 WorldPop - https://apps.worldpop.org/woprVision/ 1175.12.3 Facebook Research HRSL - High Resolution Settlement Layer - which is the most recent addition and said to be accurate - https://research.fb.com/downloads/high-resolution-settlement-layer-hrsl/ 1175.12.4 ECMWF CliMetLab - Python package and GIS Dataset for Global Climate analytics - https://climetlab.readthedocs.io/en/latest/ 1175.12.5 UrbanSprawl - Python package for Urban Sprawl analytics - https://github.com/lgervasoni/urbansprawl 1175.12.6 NASA SEDAC GPW 4.11 - https://sedac.ciesin.columbia.edu/data/set/gpw-v4-population-count-rev11/data-download 1175.13 It can be observed that cities of huge urban sprawls have proportionately high population density (which is the real equivalent of average degree in virtual social networks) and Urban GDP is proportional to population density: estimated population = population_density * urbanarea => population_density = constant * urbanarea => estimated population = constant * (urbanarea)^2 which can be used as an alternative heuristic estimate in the absence of population density data. This heuristic has been implemented in GISUrbanSprawlAnalytics.py for constant value 6.22 (from training data of cityid 1356 for population of 440000 and 266 square kilometer area: 6.22 = 440000 / (266)^2) 1175.14 Following are the logs and GIS images contour and convexhull segmented by this code change: testlogs/GISUrbanSprawlAnalytics.log.22November2021 testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationEstimate2020_edited_FaceGraph.jpeg testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationEstimate2020_edited_ImageNet_Keras_Theano_Segmentation_FaceGraph.dot testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationEstimate2020_edited_contour_segmented.jpeg testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationEstimate2020_edited_convex_hull_segmented.jpeg testlogs/RemoteSensingGIS/SEDAC_GPW4-11_PopulationEstimate2020_edited_segmented.jpg testlogs/SEDAC_GPW4-11_PopulationEstimate2020.jpeg testlogs/SEDAC_GPW4-11_PopulationEstimate2020_edited-contourlabelled.jpg testlogs/SEDAC_GPW4-11_PopulationEstimate2020_edited.jpeg 1175.15 Theory References: 1175.15.1 Theory and Problems of Complex Variables - [Murray Speigel] - Schaum Series - Page 94-97 - Jordan Curve Theorem and Connected Regions 1175.15.2 Approximation by polynomials - [Burkill] - TIFR Lectures 1959 - Weirstrass Theorem - http://www.math.tifr.res.in/~publ/ln/tifr16.pdf 1175.16 Urban Sprawl Social Network could be formalized as a 2D tensor (each vertex of a graph is a graph) where each of the urban sprawl contour of various areas are vertices and every urban sprawl vertex is a social network graph in itself with role of average degree being played by population density. Urban sprawl vertices are interconnected by transportation graph having rural areas of lesser density as intermediary vertices. Urban sprawl network 2D tensor thus has two dimensional nesting of edges and vertices: 1175.16.1 Intra urban sprawl social network - every urban sprawl vertex is in itself a social network having people as its vertices and population density as its average degree (average number of people who might be in contact per person per unit area e.g in a suburban public transportation network). In Cellular Automaton Graph model for spread of memes/pandemics/cybercrimes/opinions average degree per person is a multiple of 8. 1175.16.2 Inter urban sprawl social network - Urban sprawl vertices are connected by transportation graph among cities,towns and metropolitan agglomerations. Transportation network between urban sprawls is the lifeline of intermediary rural regions as they depend on and gravitate towards nearest urban sprawls to make a living eventually devoured by nearest urban sprawl. 1175.17 Urban Sprawl Analytics thus automates urban planning, land usage statistics, multiple agent resource allocation(MARA) and has zero-error because of its completely algorithmic approach (bounding urban sprawls by watershed segmentation, convex hull, minimum enclosing circle, Voronoi diagram tessellation algorithms on VIIRS NightLights and other gridded population GIS imagery) with nil human intervention assuming algorithmic fairness.
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
Updated Section 1174
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
Updated Section 1174
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
Section 1174 updated
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
--------------------------------------------------------------------------------------------------------------------------------------------- 1174. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Moments,Centroid,Minimum Enclosing Circle of an urban sprawl - 17,18 November 2021 - related to all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics ---------------------------------------------------------------------------------------------------------------------------------------------
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago
--------------------------------------------------------------------------------------------------------------------------------------------- 1174. (THEORY and FEATURE) GIS Urban Sprawl Analytics - Moments,Centroid,Minimum Enclosing Circle of an urban sprawl - 17,18 November 2021 - related to all sections on GIS Urban Sprawl Analytics, Merit of Large Scale Visuals, Computational Geometry, Intrinsic Merit Rankings, R Ricker and SEDAC GPW4 Convex Hull Population Estimations, Social Network Analytics, Space filling by Curves, Unequal Circle and Polynomial packing, Computational Geometry, Four color theorem, Economic Merit, Computational Economics --------------------------------------------------------------------------------------------------------------------------------------------- 1174.1 GISUrbanSprawlAnalytics.py has been updated to compute OpenCV2 moments of each urban sprawl contour and centroids from those moments.Each urban sprawl contour is bounded by a minimum enclosing circle (cv2.minEnclosingCircle() and cv2.circle()) drawn around it which is a better measure of extent of an urban area because an urban sprawl might consist of multiple smaller contours within a bigger contour interspersed by semi-lit areas. 1174.2 Two urban sprawls of Chennai and Bengaluru from NASA VIIRS India NightLights (https://resourcewatch.org/data/explore/cli061nrt-Daily-Nighttime-lights) imagery on 17 November 2021 - NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021.jpg - are compared. 1174.3 Ranking of Urban Sprawls has been changed to sorting based on circular area of urban sprawl radius computed from cv2.minEnclosingCircle() instead of contour area since multiple suburban contours are packed within a larger outermost urban sprawl contour as drawn in NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021-contourlabelled.jpg. In this example,Bengaluru as a landlocked sprawl has single contour and a minimum enclosing circle while Chennai has single largest contour and multiple suburban contours within perimeter of an outermost minimum enclosing circle which offers a glimpse of growth patterns in two metro areas. NightLights being only a lowerbound estimate of an urban sprawl, has to be superseded by minimum enclosing circle upperbound estimate. Based on area of minimum enclosing circle Chennai's urban sprawl exceeds Bengaluru significantly. Following are excerpts of the logs for areas of the 2 minimum enclosing circles of Chennai and Bengaluru: Chennai - 50645.060000000005 (excluding area of sea in the circle would reduce it to ~35000 by visual estimate) Bengaluru - 27157.860000000004 1174.4 Each urban sprawl contour is now identified by and id concatenated by its area rather than mere id earlier and fonts have been shortened. 1174.5 Bengaluru is roughly circular and heavily lit while Chennai's semi-cicular urban sprawl elongates heavily to west,north,south and comprises two large segments - first extending upto Kanchipuram in west,Tada in north and Tiruvanmiyur in south which is heavily lit and the second less lit segment of ECR till Kalpakkam - which comprises host of backwaters,beaches,marshes and waterbodies - as could be gleaned from NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021_segmented.jpg. Minimum Enclosing Circle for Urban sprawl area of Chennai earlier does not include aforementioned elongated western segment addition of which would further extend metropolitan agglomeration area to ~40000. 1174.6 Centroid of an urban sprawl is a crucial metric for assessing gradual movement of core of a city (over a period of time) around which economic activity takes place. 1174.7 Logs and images for this commit are: image_pattern_mining/ImageNet/testlogs/GISUrbanSprawlAnalytics.log.18November2021 image_pattern_mining/ImageNet/testlogs/NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021-contourlabelled.jpg image_pattern_mining/ImageNet/testlogs/NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021.jpg image_pattern_mining/ImageNet/testlogs/RemoteSensingGIS/NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021_FaceGraph.jpg image_pattern_mining/ImageNet/testlogs/RemoteSensingGIS/NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021_ImageNet_Keras_Theano_Segmentation_FaceGraph.dot image_pattern_mining/ImageNet/testlogs/RemoteSensingGIS/NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021_contour_segmented.jpg image_pattern_mining/ImageNet/testlogs/RemoteSensingGIS/NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021_convex_hull_segmented.jpg image_pattern_mining/ImageNet/testlogs/RemoteSensingGIS/NASAVIIRSNightLightsChennaiMetropolitanArea_17November2021_segmented.jpg 1174.8 Some GIS references: 1174.8.1 City of 1000 tanks - https://www.cityof1000tanks.org/ 1174.8.2 UN World Urbanization prospects - https://population.un.org/wup/
Srinivasan Kannan
More... almost 5 years ago
Updated Copyleft licensing header
Krishna iResearch - NeuronRain - K.Srinivasan
More... almost 5 years ago