Earth observation embeddings convert discrete biome maps into continuous representations that better predict species occurrence
Researchers used satellite image embeddings from an Earth observation foundation model to convert discrete biome maps into continuous probabilistic representations of ecological zones. The study tested the approach across six Brazilian biomes using 1.3 million embeddings and over 10,000 forest inventory plots covering nearly 5,000 plant species. The continuous representation outperformed traditional categorical biome labels for predicting species occurrence, offering a more ecologically accurate tool for biodiversity research.
A study posted to arXiv proposes using dense embeddings from the Clay v1.5 Earth observation foundation model to replace rigid, categorical biome classifications with continuous probability vectors that better reflect ecological gradients. The researchers trained a linear classifier on satellite image embeddings to predict biome labels, then used the softmax output as a graded, multi-dimensional representation of biome membership. Evaluated across six Brazilian biomes with 1.3 million embeddings and 10,015 withheld forest inventory plots spanning 4,672 plant species, the continuous representation achieved a mean per-species AUC of 0.618 compared to 0.570 for discrete biome labels across ten spatial cross-validation folds. The improvement was attributed specifically to the graded probability output rather than to any reclassification of biome labels, and the gain held consistently across all distances from biome boundaries—not just at ecotones. The raw 1,024-dimensional embedding performed best overall (AUC 0.646), but the continuous biome representation recovered most of the gap between embeddings and discrete labels while retaining interpretable, named biome dimensions. The authors argue this approach offers a practical, probabilistic upgrade to categorical map labels for ecological modeling.
What's missing
The approach is validated only in Brazil; generalizability to other regions with different biome structures or data availability is untested. The study does not compare against other continuous or fuzzy classification methods beyond discrete labels and raw embeddings.
What different sources said
- arXiv q-bioCenter
Continuous biome representations from Earth observation embeddings
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.