Skip to content

Populating Algorithms: Mogpr from Fusets #80

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 26 commits into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
26 commits
Select commit Hold shift + click to select a range
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
136 changes: 136 additions & 0 deletions algorithm_catalog/fusets_mogpr.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,136 @@
{
"id": "fusets_mogpr",
"type": "Feature",
"conformsTo": [
"http://www.opengis.net/spec/ogcapi-records-1/1.0/req/record-core"
],
"geometry": null,
"properties": {
"created": "2025-01-09T00:00:00Z",
"updated": "2025-01-29T00:00:00Z",
"type": "apex_algorithm",
"title": "Multi output gaussian process regression",
"description": "Integrates timeseries in data cube using multi-output gaussian process regression. The service is designed to enable multi-output regression analysis using Gaussian Process Regression (GPR) on geospatial data. It provides a powerful tool for understanding and predicting spatiotemporal phenomena by filling gaps based on other indicators that are correlated with each other.",
"cost_estimate": 12,
"cost_unit": "platform credits per km²",
"keywords": [
"timeseries",
"Gaussian Process Regression (GPR)"
],
"language": {
"code": "en-US",
"name": "English (United States)"
},
"languages": [
{
"code": "en-US",
"name": "English (United States)"
}
],
"contacts": [
{
"name": "Bram Janssen",
"position": "Researcher",
"organization": "VITO",
"links": [
{
"href": "https://www.vito.be/",
"rel": "about",
"type": "text/html"
},
{
"href": "https://github.com/JanssenBrm",
"rel": "about",
"type": "text/html"
}
],
"contactInstructions": "Contact via VITO",
"roles": [
"principal investigator"
]
},
{
"name": "Pratichhya Sharma",
"position": "Researcher",
"organization": "VITO",
"links": [
{
"href": "https://www.vito.be/",
"rel": "about",
"type": "text/html"
},
{
"href": "https://github.com/Pratichhya",
"rel": "about",
"type": "text/html"
}
],
"contactInstructions": "Contact via VITO",
"roles": [
"service provider"
]
},
{
"name": "VITO",
"links": [
{
"href": "https://www.vito.be/",
"rel": "about",
"type": "text/html"
}
],
"contactInstructions": "SEE WEBSITE",
"roles": [
"processor"
]
}
],
"themes": [
{
"concepts": [
{
"id": "Normalised vegetation difference index (NDVI)"
},
{
"id": "Radar Vegetation Index (RVI)"
},
{
"id": "Multi-output Gaussian Process Regression (MOGPR)"
}
],
"scheme": "https://gcmd.earthdata.nasa.gov/kms/concepts/concept_scheme/sciencekeywords"
}
],
"formats": [
{
"name": "JSON"
}
],
"license": "other"
},
"linkTemplates": [],
"links": [
{
"rel": "openeo-process",
"type": "application/json",
"title": "openEO Process Definition",
"href": "https://raw.githubusercontent.com/ESA-APEx/apex_algorithms/09413be3c27e0e695d426c9ffe5a0fe90beefe65/openeo_udp/fusets_mogpr/fusets_mogpr.json"
},
{
"rel": "service",
"type": "application/json",
"title": "CDSE openEO federation",
"href": "https://openeofed.dataspace.copernicus.eu"
},
{
"rel": "license",
"href": "https://apex.esa.int/license"
},
{
"rel": "example",
"type": "application/json",
"title": "Example output",
"href": "https://s3.waw3-1.cloudferro.com/swift/v1/apex-examples/fusets_mogpr/fusets_mogpr.nc"
}
]
}
52 changes: 52 additions & 0 deletions benchmark_scenarios/fusets_mogpr.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
[
{
"id": "fusets_mogpr",
"type": "openeo",
"description": "Multi output gaussian process regression example on NDVI timeseries",
"backend": "openeofed.dataspace.copernicus.eu",
"process_graph": {
"fusetsmogpr": {
"arguments": {
"s1_collection": "RVI",
"s2_collection": "NDVI",
"spatial_extent": {
"coordinates": [
[
[
5.178303838475193,
51.252856237848164
],
[
5.178003609252369,
51.25109194151486
],
[
5.179280940922463,
51.25103833409551
],
[
5.179565949577788,
51.25278555186941
],
[
5.178303838475193,
51.252856237848164
]
]
],
"type": "Polygon"
},
"temporal_extent": [
"2021-01-01",
"2021-12-15"
]
},
"namespace": "https://raw.githubusercontent.com/ESA-APEx/apex_algorithms/09413be3c27e0e695d426c9ffe5a0fe90beefe65/openeo_udp/fusets_mogpr/fusets_mogpr.json",
"process_id": "fusets_mogpr"
}
},
"reference_data": {
"timeseries.nc": "https://s3.waw3-1.cloudferro.com/swift/v1/apex-examples/fusets_mogpr/fusets_mogpr.nc"
}
}
]
50 changes: 50 additions & 0 deletions openeo_udp/fusets_mogpr/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
# Sentinel-1 and Sentinel-2 data fusion through Multi-output Gaussian process regression (MOGPR)

This service is designed to enable multi-output regression analysis using Gaussian Process Regression (GPR) on geospatial data. It provides a powerful tool for understanding and predicting spatiotemporal phenomena by filling gaps based on other correlated indicators. This service focuses on fusing Sentinel-1 and Sentinel-2 data, allowing the user to select one of the predefined data sources.

## Parameters

The `fusets_mogpr_s1s2` service requires the following parameters:


| Name | Description | Type | Default |
| --------------- | -------------------------------------------------------------- | ------- | ------- |
| spatial_extent | Polygon representing the AOI on which to apply the data fusion | GeoJSON | |
| temporal_extent | Date range for which to apply the data fusion | Array | |
| s1_collection | S1 data collection to use for the fusion | Text | RVI |
| s2_collection | S2 data collection to use for fusing the data | Text | NDVI |

## Supported collections

#### Sentinel-1

* RVI
* GRD

#### Sentinel-2

* NDVI
* FAPAR
* LAI
* FCOVER
* EVI
* CCC
* CWC

## Limitations

The spatial extent is limited to a maximum size equal to a Sentinel-2 MGRS tile (100 km x 100 km).

## Dependencies

In addition to various Python libraries, the workflow utilizes the following libraries included in the User-Defined Function (UDF):

* Biopar: The `biopar` package retrieves biophysical parameters like FAPAR, FCOVER, and more, that were passed as the S2_collection. The biopar package is a Python package that calculates biophysical parameters from Sentinel-2 satellite images as described [here](https://step.esa.int/docs/extra/ATBD_S2ToolBox_L2B_V1.1.pdf). The `fusets_mogpr` udp directly uses the biopar udp shared in the APEX Algorithms repository.

* FuseTS: The `fusets` library was developed to facilitate data fusion and time-series analytics using AI/ML to extract insights about land environments. It functions as a Time Series & Data Fusion toolbox integrated with openEO. For additional information, please refer to the [FuseTS documentation](https://open-eo.github.io/FuseTS/installation.html).



## Output

This User-Defined-Process (UDP) produces a datacube that contains a gap-filled time series for all pixels within the specified temporal and spatial range. This datacube can be seamlessly integrated with other openEO processes.
Loading