Since several folks emailed me one-on-one, I am adding this clarification: 1. The link below only gives information on what the map is about, how it was made, and (importantly) what its accuracy levels are. https://www.arcgis.com/home/item.html?id=d6642f8a4f6d4685a24ae2dc0c73d4ac
2. To actually download tiles for your area, you need to go to the downloader page, which for some reason does not seem to work from the above page. You need to go to: https://www.arcgis.com/apps/instant/media/index.html?appid=fc92d38533d440078f17678ebc20e8e2 3. You can also download the whole set of tiles at once (60GB) https://soilspackage-useast.s3.amazonaws.com/EsriLandCover/GlobalEsri2020LandCover.zip 4. Upon perusing the documentation, and doing some ground truthing of my own for areas I have already mapped at high resolution, my observations are: a) the 10-fold classification is generally too coarse for many applications. E.g., 'trees' includes horticultural plantations (coconut, areca, eucalyptus, rubber, coffee, etc) along with forest of all densities and types. 'cropland' includes fallows. b) the documentation itself acknowledges that the accuracy for certain classes is low (~50%): grassland, and scrubland. Thus, most forest edges are classified as 'bare', when they are likely to be grassland or scrubland. In other words, the spatial resolution may be good, but the class-resolution (and associated accuracy) is not good enough for many applications. Not a criticism of this effort, but something to keep in mind when using the product. Again, a big thanks to Justin for bringing this source of data to our attention and hosting links on his website (https://revolutionarygis.wordpress.com/) which has tonnes of other goodies as well! Best, Sharad On Friday, June 25, 2021 at 11:29:50 AM UTC+5:30 Sharad Lele wrote: > Works! Thanks, Justin! > > Sharad > > On 25-Jun-21 08:15, J M wrote: > > Shared, > Let me know if this works! > > https://www.arcgis.com/home/item.html?id=d6642f8a4f6d4685a24ae2dc0c73d4ac > > Justin > > On Thu, Jun 24, 2021, 9:23 PM Sharad Lele <shara...@gmail.com> wrote: > >> Hi Justin, >> Thanks for this. I downloaded a tile, but could not find the legend >> information anywhere. Please advise. >> Sharad >> >> On Thursday, June 24, 2021 at 11:38:42 PM UTC+5:30 Justin wrote: >> >>> On Thursday, June 24, 2021 at 2:08:19 PM UTC-4 Justin wrote: >>> >>>> revolutionarygis.wordpress.com >>>> >>> -- >> 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 a topic in the >> Google Groups "datameet" group. >> To unsubscribe from this topic, visit >> https://groups.google.com/d/topic/datameet/w-Bz-XMqQUg/unsubscribe. >> To unsubscribe from this group and all its topics, send an email to >> datameet+u...@googlegroups.com. >> To view this discussion on the web visit >> https://groups.google.com/d/msgid/datameet/4fccab33-95a2-45a7-8def-dd0a0376c144n%40googlegroups.com >> >> <https://groups.google.com/d/msgid/datameet/4fccab33-95a2-45a7-8def-dd0a0376c144n%40googlegroups.com?utm_medium=email&utm_source=footer> >> . >> > -- > 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 a topic in the > Google Groups "datameet" group. > To unsubscribe from this topic, visit > https://groups.google.com/d/topic/datameet/w-Bz-XMqQUg/unsubscribe. > To unsubscribe from this group and all its topics, send an email to > datameet+u...@googlegroups.com. > > To view this discussion on the web visit > https://groups.google.com/d/msgid/datameet/CAOLgkyp4m5WRW9s7KG076K_vp8m%2BACqUOfPjU5dxgd%3Dq_q9X2Q%40mail.gmail.com > > <https://groups.google.com/d/msgid/datameet/CAOLgkyp4m5WRW9s7KG076K_vp8m%2BACqUOfPjU5dxgd%3Dq_q9X2Q%40mail.gmail.com?utm_medium=email&utm_source=footer> > . > > > -- 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 datameet+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/datameet/217d23a5-e97f-47cc-b6c7-93a86a7c6d23n%40googlegroups.com.
