Dinesh Neupane

Mar 10, 2024 | gis.stackexchange.com | Dinesh Neupane

Asked Viewed 3 times I am currently working with Sentinel-2 images bands. Some of the bands I am taking have 10m resolution whereas others have 30m resolution. I have ground data of different locations and based on the locations I extracted the surface reflectance values for each of those bands. I then used those band values and ground sampled data to train my model (band values as x and ground data as y) and I have a trained regressor.

Dec 10, 2023 | nature.com | Dinesh Neupane |Christian Delles |James Sharman |Daniel T. Lackland |Michael Weber

This is a preview of subscription content, access via your institution Access options Subscribe to this journalReceive 12 digital issues and online access to articles118,99 € per yearonly 9,92 € per issueRent or buy this articlePrices vary by article typefrom$1.95to$39.95Prices may be subject to local taxes which are calculated during checkout ReferencesNeupane D, Hall B, Mukhtar, Q, Delles C, Sharman J, Cobb, L, et al.

Aug 3, 2023 | gis.stackexchange.com | Dinesh Neupane

Asked today Viewed 4 times I am using rasterstats python package for calculating the zonal statistics of a raster and a vectr geometry like this:stats = zonal_stats('tests/data/polygons.shp', 'tests/data/slope.tif',stats="count", all_touched=true)Is it possible to calculate the weighted mean of the pixels like: if a pixel has an overlap 50 % with the shape then it gets a weight of 0.5 and if the pixel lies fully within the polygon it gets weight 1.