Hi, population is available at village/ Ward level from Census of India
You could also use the various sources for the polygons of villages. Since there are more than one search on this group. On Monday, September 10, 2018 at 3:14:14 AM UTC+5:30, Shubham Goel wrote: > > Hi, > > I'm currently working as a Machine learning engineer where I'm responsible > for extracting exact building footprints from High resolution satellite > imagery. We've been able to it successfully for some regions (and so have > Microsoft: https://github.com/Microsoft/USBuildingFootprints) > > [image: footprint_extraction.PNG] > > > Based on that experience, I have a feeling it can work for estimating the > poverty levels for different regions. The images you've attached are very > helpful, as they clearly show the stark contrast between the developed and > poverty-struck regions. > > In terms of data, Google does provide free satellite imagery up to a > certain limit per day. I'm not sure where population density would be > available, especially at a granular level. > > Suggestions and thoughts are welcome. > > Thanks, > > Shubham Goel > > > > On Thu, Sep 6, 2018 12:20 PM, Naraina aka Dilip Damle [email protected] > <javascript:> wrote: > >> [image: dwarka.PNG] >> HI, >> >> I think yes. >> >> But could it be Automated without a Human I have a doubt. >> >> With a Human eye it is possible to a good extent. >> >> Size, Pattern and Density of Housing indicates Economic prosperity to a >> great extent. >> >> Compare the Phots attached. >> >> Imagey + >> Population density data could be used to do what you want. You will also >> have to detect multistory buildings. >> >> >> Note: I am not a remote sensing expert but I use Google earth a lot for >> my professional work. >> >> >> >> >> >> >> >> >> >> On Wednesday, September 5, 2018 at 10:10:44 PM UTC+5:30, Shubham Goel >> wrote: >> >> Hi, >> >> I was wondering if remote sensing could be used to correctly predict >> economic indicators across India. Some Stanford researchers have done >> similar work for African countries. >> >> Link - http://sustain.stanford.edu/predicting-poverty/ >> >> They've used nightlight data from NOAA (available across the globe at 1m >> resolution) along with imagery from Google Static Maps API to build their >> CNN architecture (along with using survey data) >> >> Do let me know your thoughts on the same. >> >> Shubham >> >> -- >> Datameet is a community of Data Science enthusiasts in India. Know more >> about us by visiting http://datameet.org >> --- >> You received this message because you are subscribed to the Google Groups >> "datameet" group. >> To unsubscribe from this group and stop receiving emails from it, send an >> email to [email protected] <javascript:>. >> For more options, visit https://groups.google.com/d/optout. >> > -- Datameet is a community of Data Science enthusiasts in India. Know more about us by visiting http://datameet.org --- You received this message because you are subscribed to the Google Groups "datameet" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
