Home Publications

Publications

Papers, preprints, code repositories, and datasets from our research programme.

Featured Paper

2026 Preprint

Geospatial foundation models enable data-efficient tree species mapping in temperate montane forests

James GC Ball, Jana Annika Wicklein, Zhengpeng Feng, Jovana Knezevic, Clement Atzberger, Michele Dalponte, David Coomes

We evaluate two geospatial foundation-model embeddings, AlphaEarth and Tessera, for tree species classification in the Trentino region of northern Italy, using parcel-level forest inventories as reference data (18 species and species groups). Foundation-model embeddings substantially outperform composite-based multispectral satellite baselines, achieving higher accuracy with far fewer training labels and preserving ecologically meaningful structure aligned with functional and taxonomic groupings.

Code & Data

trentino-trees

Complete species classification pipeline: soft-label training, model training, evaluation, and visualisation. Python, scikit-learn, PyTorch.

github.com/PatBall1/trentino-trees

Data on Zenodo

Processed labels, evaluation results, and model outputs. Available upon publication.

DOI forthcoming

Related & Background Work

Feng et al., 2025

Tessera: Geospatial Foundation Model

The Tessera geospatial foundation model providing 128-dimensional embeddings from multi-sensor seasonal composites at 10 m resolution.

Brown et al., 2025

AlphaEarth (AEF)

Google’s AlphaEarth Foundations geospatial foundation model providing multi-source Earth surface representations.

Ball et al., 2024

Foundation Models for Ecological Monitoring

Prior work on the role of foundation models in reducing labelling bottlenecks for ecological remote sensing applications.

Jung, 2017

A Global Map of Terrestrial Habitat Types (IUCN)

The first global, spatially explicit characterisation of terrestrial habitat types at 100 m resolution following the IUCN habitat classification scheme.