Hi,

Here is a dedicated example demonstrating how you could work with eo-learn package.

Section 2. -4 demonstrates how you could create EOPatches, fill them with Sentinel-2 data, and compute indices using Sentinel Hub services.

Hi,

thanks for answering.

In this case: I have downloaded the bands for NDVI. The Data-download is completed.

Now I have to calculate the index with the EOPatch-Data witch is already on the the disk.

Can you give an example, how to do it?

I have no clue. I only find examples with downloading the data again/new.

Thank you very much for your help.

The example shows actually uses already downloaded bands (in that particular case, the downloaded bands are ["B02", "B03", "B04", "B08", "B11", "B12"]) to calculate NDVI.

To download:

band_names = ["B02", "B03", "B04", "B08", "B11", "B12"]
add_data = SentinelHubInputTask(
    bands_feature=(FeatureType.DATA, "BANDS"),
    bands=band_names,
    resolution=10,
    maxcc=0.8,
    time_difference=datetime.timedelta(minutes=120),
    data_collection=DataCollection.SENTINEL2_L1C,
    additional_data=[(FeatureType.MASK, "dataMask", "IS_DATA"), (FeatureType.MASK, "CLM"), (FeatureType.DATA, "CLP")],
    max_threads=5,
)

To calculate NDVI, NormalizedDifferenceIndexTask task is used:

# NDVI: (B08 - B04)/(B08 + B04)
ndvi = NormalizedDifferenceIndexTask(
    (FeatureType.DATA, "BANDS"), (FeatureType.DATA, "NDVI"), [band_names.index("B08"), band_names.index("B04")]
)

If you already have data downloaded, then you can load your eopatch(es) with LoadTask, which will load the existing eopatches in memory, and run ndvi task as defined above on it.