Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping

• URL: http://arxiv.org/abs/2608.12663v1
• Date: Wed, 12 Aug 2026 23:52:37 GMT
• Title: Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping
• Abstract summary: We show that AEF embeddings can reconstruct commonly used variables in wildfire susceptibility analysis with high accuracy.<n>In downstream susceptibility models trained on satellite-derived fire occurrence data, embedding-based susceptibility models achieve ROC-AUC values above 0.92.<n>Key feature of AEF embeddings is their strong near-region transferability within climatically similar regions.
• Score: 34.48698163135379
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Wildfire susceptibility mapping typically relies on physical variables assembled from multiple remote-sensing, climate, and geospatial products. AlphaEarth Foundations (AEF) provides analysis-ready geospatial embeddings that may reduce this dependence on heavy harmonisation and task-specific feature engineering, but their value for wildfire susceptibility mapping has not been systematically evaluated. Using Victoria, Australia (2017-2025), as a case study, we show that AEF embeddings can reconstruct commonly used variables in wildfire susceptibility analysis with high accuracy. In downstream susceptibility models trained on satellite-derived fire occurrence data, embedding-based susceptibility models achieve ROC-AUC values above 0.92 and consistently identify high wildfire susceptibility across eastern Victoria, particularly Gippsland and the north-eastern uplands, with additional localized hotspots in central and northwestern Victoria. A key feature of AEF embeddings is their strong near-region transferability within climatically similar regions. When embedding-based models trained in Victoria are applied to Canberra and Western Sydney-Blue Mountains, ROC-AUC improves by around 4% at Canberra and declines by around 2% at Western Sydney-Blue Mountains, compared with a mean decrease of approximately 25% for physical-variable models. These findings provide practical guidance for using AEF embeddings and lay a foundation for scalable wildfire susceptibility mapping workflows for downstream users such as government agencies and (re)insurers.

Related papers

• A Nationwide Benchmark for Wildfire Initial Attack Failure Prediction with Public Environmental Data [62.031815260604056]
  We present the first U.S. national-scale benchmark for initial attack (IA) failure prediction from environmental and contextual data available at fire discovery time.<n> WILDFIREIA aligns 38,128 naturally caused FPA-FOD wildfire events with FIRMS/VIIRS thermal detections, gridMET weather and fire-danger variables, LANDFIRE vegetation, fuel, and topography.<n>Results show that public discovery-time data provides useful but incomplete signal for IA failure prediction.
  arXiv  Detail & Related papers  (2026-06-14T01:03:13Z)
• Low-Rank Adaptation of Geospatial Foundation Models for Wildfire Mapping Using Sentinel-2 Data [0.9558392439655014]
  This study evaluates three state-of-the-art Geospatial Foundation Models (GFMs) for burned-area mapping across the United States and Canada using Sentinel-2 data.<n>We compare full fine-tuning, decoder-only fine-tuning, and Low-Rank Adaptation (LoRA) for adapting each model.<n> Prithvi-v2 with LoRA achieves the highest overall accuracy and the largest improvement compared to full fine-tuning.
  arXiv  Detail & Related papers  (2026-05-06T14:47:01Z)
• From Landslide Conditioning Factors to Satellite Embeddings: Evaluating the Utilisation of Google AlphaEarth for Landslide Susceptibility Mapping using Deep Learning [1.6571781613404601]
  This study evaluated the potential of Google AlphaEarth embeddings as alternative predictors for landslide susceptibility mapping.<n>AE-based models consistently outperformed LCFs across all regions and models, yielding higher F1-scores, AUC values, and more stable error distributions.
  arXiv  Detail & Related papers  (2026-01-12T07:17:43Z)
• FireScope: Wildfire Risk Prediction with a Chain-of-Thought Oracle [69.84129020970477]
  Existing methods lack the causal reasoning and understanding required for reliable generalization.<n>We introduce $textbfFireScope-Bench, a dataset and benchmark that couples Sentinel-2 imagery and climate data with expert-defined risks.<n>When trained in the USA and tested in Europe, $textbfFireScope$ achieves substantial performance gains.<n>Our findings demonstrate that reasoning can ground prediction models, improving both generalization and interpretability.
  arXiv  Detail & Related papers  (2025-11-21T11:45:22Z)
• Probabilistic Wildfire Susceptibility from Remote Sensing Using Random Forests and SHAP [0.0]
  Wildfires pose a significant global threat to ecosystems worldwide.<n>This study aims to develop a comprehensive wildfire risk map for California by applying the random forest algorithm.
  arXiv  Detail & Related papers  (2025-11-12T06:05:41Z)
• CanadaFireSat: Toward high-resolution wildfire forecasting with multiple modalities [13.151866497852211]
  Canada experienced one of the most severe wildfire seasons in recent history in 2023.<n>This extreme wildfire season is symptomatic of a climate-change-induced increase in the length and severity of the fire season that affects the boreal ecosystem.<n>It is critical to empower wildfire management in boreal communities with better mitigation solutions.
  arXiv  Detail & Related papers  (2025-06-10T10:58:43Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• Deep graphical regression for jointly moderate and extreme Australian wildfires [0.7864304771129751]
  Recent wildfires in Australia have led to considerable economic loss and property destruction. There is increasing concern that climate change may exacerbate their intensity, duration, and frequency. It is imperative to develop robust statistical methods to reliably model the full distribution of wildfire spread.
  arXiv  Detail & Related papers  (2023-08-28T13:04:52Z)
• Country-wide Retrieval of Forest Structure From Optical and SAR Satellite Imagery With Bayesian Deep Learning [74.94436509364554]
  We propose a Bayesian deep learning approach to densely estimate forest structure variables at country-scale with 10-meter resolution. Our method jointly transforms Sentinel-2 optical images and Sentinel-1 synthetic aperture radar images into maps of five different forest structure variables. We train and test our model on reference data from 41 airborne laser scanning missions across Norway.
  arXiv  Detail & Related papers  (2021-11-25T16:21:28Z)
• From Static to Dynamic Prediction: Wildfire Risk Assessment Based on Multiple Environmental Factors [69.9674326582747]
  Wildfire is one of the biggest disasters that frequently occurs on the west coast of the United States. We propose static and dynamic prediction models to analyze and assess the areas with high wildfire risks in California.
  arXiv  Detail & Related papers  (2021-03-14T17:56:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.