QGIS plugin · Satellite embeddings · Guide

02EarthEmbeddings — Earth Embeddings Lab

Mapping with the Google AlphaEarth Foundations Satellite Embedding dataset (annual 2017 to 2025, 10 m, 64 channels, CC BY 4.0) in QGIS. The plugin reads the public Cloud-Optimised GeoTIFFs without an Earth Engine account, turns the bottom-up, quantised tiles into a north-up cube of unit vectors across UTM zones, and carries a study to similarity search, label-free clustering, few-label classification, design-based accuracy and area estimates, multi-year change, polygon embeddings and an HTML report.

Version: 0.1.0 QGIS: 3.28+ / 4.x Licence: GPL-2.0-or-later Developer: Geophilo Language: English
01 · Overview

What 02EarthEmbeddings does

Mapping with the Google AlphaEarth Foundations Satellite Embedding dataset (annual 2017 to 2025, 10 m, 64 channels, CC BY 4.0) in QGIS. The plugin reads the public Cloud-Optimised GeoTIFFs without an Earth Engine account, turns the bottom-up, quantised tiles into a north-up cube of unit vectors across UTM zones, and carries a study to similarity search, label-free clustering, few-label classification, design-based accuracy and area estimates, multi-year change, polygon embeddings and an HTML report.

Reading

Correct cube from public tiles

Tiles are flipped north-up, de-quantised as x=sign⁡(q) (q/127.5)2x = \operatorname{sign}(q)\,(q/127.5)^2 with −128-128 as nodata, normalised to unit length and mosaicked across UTM zones; an estimate of pixels, download size and tiles comes before any fetch.

Mapping

Similarity, clusters, classes

Mean prototype, nearest example or contrast search with Otsu, top-percent or fixed thresholds; spherical kk-means with model-selection curves; kk-NN, nearest prototype and logistic regression in NumPy with spatial block and random cross-validation side by side.

Accuracy and change

Estimates you can report

Stratified random samples and Olofsson et al. (2014) area estimates with 95 % confidence intervals for area, OA, UA and PA; change distance d=1−xt⋅xt+1d = 1 - \mathbf{x}_t \cdot \mathbf{x}_{t+1} with Otsu, MAD or stable-reference thresholds; polygon embeddings with coherence RR.

02 · Install and quick start

Install, then run the demo

In QGIS, open Plugins › Manage and Install Plugins, search for 02EarthEmbeddings and install it, or install a release zip with Install from ZIP.

QGIS 3.28 or later (QGIS 4 included). GDAL and NumPy ship with QGIS. Optional: scikit-learn (random forest) and pyarrow (a second reader for the Parquet tile index). One area of interest holds at most 25 million pixels per year at the chosen pixel size (about 50×50 km50 \times 50\,\mathrm{km} at 10 m). Annual embeddings show that change happened, not when within the year.

Open the lab

Click the 02EarthEmbeddings toolbar button; the lab opens as a dock on the right.

Load the demo cube

On Data, press Load demo cube (synthetic): a 400×300400 \times 300 pixel cube at 10 m in EPSG:32635 for 2022 to 2024 with five planted classes, one novel class and a 24 ha block that changes class in 2024. Every layer is marked SYNTHETIC - not AlphaEarth data.

Cluster and classify

On Clusters, Find k (the silhouette peaks at k=5k = 5), then Run clustering. On Classify, use the demo training points (field class) with 500 m blocks and compare OA (blocks) with OA (random); the AOA layer flags the novel class.

Change and report

On Change, years 2022 to 2024 with Otsu: the changed area is 24 ha and the change year 2024. On Report, write the HTML report.

03 · The dock

The lab dock, page by page

The lab is a dock on the right of the QGIS window with an icon rail of eight pages and Help. Long steps run as QGIS background tasks with a progress bar and a Cancel button.

PageWhat it holds
1. DataArea of interest, year chips 2017 to 2025, pixel size 10 to 80 m, source (Google Cloud, Source Cooperative mirror, a local folder or raster layers), Check connection, an estimate card, Fetch cube and Load demo cube (synthetic); a PCA colour composite is added.
2. SimilarPositive and negative examples from map clicks or layers, scoring rule, threshold on a live histogram, minimum mapping unit and a ranked region list.
3. ClustersFind k draws the silhouette, Calinski-Harabasz and Davies-Bouldin curves; spherical kk-means; renamable cluster cards with share, area and coherence.
4. ClassifyTraining layer or quick labels; OA from spatial blocks and from random folds, macro-F1, quantity and allocation disagreement, a confusion matrix, probability, margin, dissimilarity-index and area-of-applicability layers.
5. AccuracyStratified random sample design sized for a target standard error, a labelling helper that writes ref_class, and Olofsson area estimates with confidence intervals, also as CSV.
6. ChangeDistance between years, thresholds, change year, change regions and a before/after PCA pair.
7. ZonesPolygon embeddings (e00 to e63), coherence, similarity to a reference zone and a CSV similarity matrix.
8. ReportOne self-contained HTML file with provenance, attribution, formulas, KPIs, tables and references; an export of all rasters and a GeoPackage of the vectors.
Clusters page of the 02EarthEmbeddings dock with the silhouette, Calinski-Harabasz and Davies-Bouldin curves
Clusters page of the 02EarthEmbeddings dock with the silhouette, Calinski-Harabasz and Davies-Bouldin curves.
Classify page with training data, classifier and spatial block validation settings
Classify page with training data, classifier and spatial block validation settings.
Accuracy page with the sample design, labelling helper and area estimates
Accuracy page with the sample design, labelling helper and area estimates.
Change page with the distance histogram, threshold and changed area
Change page with the distance histogram, threshold and changed area.
04 · Processing

Processing provider

The plugin registers a 02EarthEmbeddings provider with 13 algorithms in the Processing Toolbox, usable in models, batch mode and scripts.

GroupAlgorithm
DataSynthetic demo cube
DataEstimate download (AlphaEarth tiles)
DataFetch AlphaEarth embeddings
DataPCA colour composite
SimilaritySimilarity search (from examples)
ClustersChoose the number of clusters
ClustersLabel-free clusters (spherical k-means)
ClassificationFew-label classification
Accuracy and areaAccuracy sample (stratified random)
Accuracy and areaArea estimate and accuracy (Olofsson)
ChangeChange between years
ZonesPolygon embeddings (zones)
WorkflowEarth Embeddings Lab (full workflow and report)
05 · Manual

Full manual

06 · Credits

Citation and licence

Name02EarthEmbeddings - Earth Embeddings Lab
Packagezero2earthembeddings
Version0.1.0
QGIS3.28 or newer; QGIS 4 supported
LicenceGPL-2.0-or-later (LICENSE)
DeveloperGeophilo · Yusuf Eminoğlu (ORCID 0009-0005-6000-2934)
Sourcegitlab.com/geophilo1/zero2earthembeddings
Issuesgitlab.com/geophilo1/zero2earthembeddings/-/work_items
Hubplugins.qgis.org search: zero2earthembeddings (listing pending)
RevisionNovember 2026
Eminoğlu, Y. (2026). 02EarthEmbeddings - Earth Embeddings Lab (version 0.1.0) [QGIS plugin]. https://gitlab.com/geophilo1/zero2earthembeddings