Tensor Network Machine Learning for Wildfire Susceptibility Mapping: from Grokking Dynamics to Quantum Mixedness of Class Representations

Domenico Pomarico; Alessandra Costantino; Gabriel Ramirez Sanchez; Loredana Bellantuono; Davide D' Alò; Mario Elia; Alessandro Fania; Francesco Giordano

physics.soc-phJul 21, 2026

Tensor Network Machine Learning for Wildfire Susceptibility Mapping: from Grokking Dynamics to Quantum Mixedness of Class Representations

Authors: Domenico Pomarico, Alessandra Costantino, Gabriel Ramirez Sanchez, Loredana Bellantuono, Davide D' Alò, Mario Elia, Alessandro Fania, Francesco Giordano, +7 more

Organizations: 1Dipartimento Interuniversitario di Fisica, Universit`a degli Studi di Bari Aldo Moro, Bari, I-70126, Italy · 2Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, I-70126, Italy · 3Dipartimento di Biomedicina Traslazionale e Neuroscienze (DiBraiN), Universit`a degli Studi di Bari Aldo Moro, Bari, I-70124, Italy · 4Dipartimento Di Scienze Del Suolo, Della Pianta e Degli Alimenti (DISSPA), Universit`a degli Studi di Bari Aldo Moro, Bari, I-70125, Italy · 5Dipartimento di Farmacia-Scienze del Farmaco, Universit`a degli Studi di Bari Aldo Moro, Bari, I-70125, Italy

Abstract

A quantum-inspired tensor network framework for wildfire susceptibility classification in the Gargano region is introduced, leveraging AlphaEarth embeddings and Matrix Product State models. The approach combines scalable geospatial representations with an interpretable quantum mask, enabling both binary and multiclass classification of wildfire susceptibility. Beyond predictive performance, the study reveals a pronounced grokking transition in the binary case and provides a detailed analysis of inter-class confusion in the multiclass setting. By introducing level-resolved mixedness diagnostics based on reduced density matrices, we show that the MPS classifier naturally encodes a hierarchy of class distinguishability, with non-adjacent categories becoming more separable than neighboring ones. These results demonstrate that tensor network models not only achieve competitive classification accuracy but also offer a physically grounded framework to quantify and interpret class separability in complex environmental datasets.

Explore similar work

Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping
Aug 12, 2026Yuan Zhuang, Sanaa Hobeichi, Peng Shi +1Wildfire Prediction Geospatial Foundation Models
Quantum-Grassmann-Plucker Token Mixing for Deep Learning-Based Post-Disaster Damage Assessment
Aug 31, 2026Kooroush Farahkhah, Umut Lagap, Taha Rezaei +1Post-Disaster Damage Assessment Image Classification
Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction
May 4, 2026Jonas V. FunkWildfire Prediction Wildfire Spread

Aug 12, 2026 · stat.APJ/K move · Enter open · S save

Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping

Yuan Zhuang, Sanaa Hobeichi, Peng Shi, Fei Huang

1UNSW Sydney, School of Risk and Actuarial Studies, New South Wales, Australia · 2ARC Centre of Excellence for the Weather of the 21st Century, Australia · 3Climate Change Research Centre, University of New South Wales, Sydney, New South Wales, Australia · 4UNSW AI Institute, New South Wales, Australia · Department of Risk and Insurance, Wisconsin School of Business, University of Wisconsin–Madison, Madison, Wisconsin 53706, USA

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.

Wildfire Prediction Geospatial Foundation Models Landslides Medregion-Ct

Open paper Ask about it PDF

Abstract

Explore similar work

Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping

Quantum-Grassmann-Plucker Token Mixing for Deep Learning-Based Post-Disaster Damage Assessment

Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction