It is inappropriate to interpolate over a large area, such as a cloud area. Since you have time series data, the data in the mask area is calculated and replaced in the previous image.
And then ou can use RASTERIO on google colab to handle raster image.
If you need to interpolate some areas, you can use the module below.
Maybe. You would need to know if the single latitude and longitude value you have is the center of the image or a corner? This might be problematic- if you have drone imagery the lat/long is likely the aircraft location and the pitch, roll, and yawl of the camera at the time of capture my not have resulted in an image that is not rectangular.
You would also ...
One thing you can do is to unmask the image using a proxy value before the expression and then catch that proxy value:
var proxy = -999
image = image.unmask(proxy)
var currentHS = image.expression(
"(b('current') == proxy) ? 0.0" +
": (b('current') < 0.13) ? 1.0" +
": (b('current') > ...
The following script should do the same thing as you've done, except it relies on .map() instead of .iterate(), which improves parallelization. However, it uses reduceRegion instead of reduceRegions so it may be a wash in terms of time. I was reluctant to use reduceRegions since it looks like you have points that span years and months that you extract band ...
The new Sentinelsat v0.14 has been just been released with some bug fixes and esp. improved handling of Long-Term Archive (LTA) data search and download. It is available from here:
To be fully interpretable, the NDVI has to be computed based on "top-of-canopy" reflectance values. By definition, reflectance values are positive numbers between 0 and 1 (which are often multiplied by a power of 10 for storage issue (better to store 8 or 16 bit integer than float). Therefore, in theory, the only case where you could get an invalid ...
NDVI=0 is a valid value, but If you got NAN value there is probably pixles that couldn't get a valid value because they were NAN in the beginning (NAN=Not A Number). Anyway when you got NAN that DOES NOT mean it is 0.
You should compute the NDWI first then georeference it. This is because NDWI is a ratio, and the linear combination of ratio is not the same as the ratio of the linear combination. You therefore reduce the risk of having artefacts by resampling after computing the NDWI (the resampling will smooth the NDWI a little bit, except if you use a nearest neighbour ...
That is possible. Here are two links explaining the details of how scale and resampling work in Earth Engine:
I was lucky to locate the "None object" in geometry (last row) and thus create a new dataframe from the original one minus the last row:
# Deleting the last row (Wheat) where geometry=None
land_use_ref = land_use_ref[:-1]