sentinel-hub / eo-learn

Earth observation processing framework for machine learning in Python
https://eo-learn.readthedocs.io/en/latest/
MIT License
1.13k stars 300 forks source link

Different numbers of samples for Sentinel-1 #32

Closed GalacticF closed 5 years ago

GalacticF commented 6 years ago

Different numbers of samples for Sentinel-1

key = 'TRUE-COLOR-S1-IW'
input_task = S1IWWCSInput(key, resx='10m', resy='10m', instance_id=INSTANCE_ID, maxcc=0.8)
workflow = LinearWorkflow(input_task)
time_interval = ['2010-01-01','2018-12-31']
bbox = BBox(bbox=[ 150.6450033,-32.4219569,150.6583071,-32.4383657], crs=CRS.WGS84)
results = workflow.execute({input_task:{'bbox':bbox, 'time_interval':time_interval}})

For this request I got 41 result for area of bbox since 2017, but in eo_browser available results from 2014 (126 samples). it there any way to got all results for this period of time (2014-2017) from eo_learn package?

batic commented 6 years ago

At the moment the oldest S-1 data on AWS is from mid 2017, while the data on eo-cloud (used on EO-Browser) goes back to 2014. Sentinelhub-py uses data from AWS by default, as to use data from eo-cloud requires additional access to our prototype system on eo-cloud. For that access, send us an e-mail to info@sentinel-hub.com.

Then you would enable access to eo-cloud data by fixing the base url in the config.json (in sentinelhub-py)

We have an example on how to do that on our "todo" list.

GalacticF commented 5 years ago

Hi, I've got acces, but with new access I still cannot get sentinel-1 data. I've tried to connect to new instance to get Sentinel-1 results but using this code I got "No value present" error. Is the any way to use new instance to connect via python? I've tried both change INSTANCE_ID in code and in config.json, but it doesn't works.

from eolearn.io.sentinelhub_service import S1IWWCSInput

INSTANCE_ID =  '2a10eb2a...'

key = 'TRUECOLOR'
input_task = S1IWWCSInput(key, resx='10m', resy='10m', instance_id=INSTANCE_ID)

workflow = LinearWorkflow(input_task)
time_interval = ['2018-01-01','2018-12-31']
from sentinelhub import WebFeatureService, BBox, CRS, DataSource
bbox = BBox(bbox=[ 150.6450033,-32.4219569,150.6583071,-32.4383657], crs=CRS.WGS84)

results = workflow.execute({input_task:{'bbox':bbox, 'time_interval':time_interval}})
AleksMat commented 5 years ago

Hi @GalacticF,

eo-learn package uses sentinelhub Python package for downloading data. In order to download data from EOCloud you also have to change base url in package's configuration file. Please check this forum post for further explanation.

We are also planning to prepare some examples about this in documentation.

GalacticF commented 5 years ago

It works, thank you!