Saved in:
Bibliographic Details
Main Authors: Imtiaz, Syed Usama, Azadani, Mitra Nasr, Alamdari, Nasrin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.22097
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917456145022976
author Imtiaz, Syed Usama
Azadani, Mitra Nasr
Alamdari, Nasrin
author_facet Imtiaz, Syed Usama
Azadani, Mitra Nasr
Alamdari, Nasrin
contents Foundation models are now increasingly being developed for Earth observation (EO), yet they often rely on stochastic masking that do not explicitly enforce physics constraints; a critical trustworthiness limitation, in particular for predictive models that guide public health decisions. In this work, we propose SpecTM (Spectral Targeted Masking), a physics-informed masking design that encourages the reconstruction of targeted bands from cross-spectral context during pretraining. To achieve this, we developed an adaptable multi-task (band reconstruction, bio-optical index inference, and 8-day-ahead temporal prediction) self-supervised learning (SSL) framework that encodes spectrally intrinsic representations via joint optimization, and evaluated it on a downstream microcystin concentration regression model using NASA PACE hyperspectral imagery over Lake Erie. SpecTM achieves R^2 = 0.695 (current week) and R^2 = 0.620 (8-day-ahead) predictions surpassing all baseline models by (+34% (0.51 Ridge) and +99% (SVR 0.31)) respectively. Our ablation experiments show targeted masking improves predictions by +0.037 R^2 over random masking. Furthermore, it outperforms strong baselines with 2.2x superior label efficiency under extreme scarcity. SpecTM enables physics-informed representation learning across EO domains and improves the interpretability of foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22097
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SpecTM: Spectral Targeted Masking for Trustworthy Foundation Models
Imtiaz, Syed Usama
Azadani, Mitra Nasr
Alamdari, Nasrin
Artificial Intelligence
Machine Learning
Foundation models are now increasingly being developed for Earth observation (EO), yet they often rely on stochastic masking that do not explicitly enforce physics constraints; a critical trustworthiness limitation, in particular for predictive models that guide public health decisions. In this work, we propose SpecTM (Spectral Targeted Masking), a physics-informed masking design that encourages the reconstruction of targeted bands from cross-spectral context during pretraining. To achieve this, we developed an adaptable multi-task (band reconstruction, bio-optical index inference, and 8-day-ahead temporal prediction) self-supervised learning (SSL) framework that encodes spectrally intrinsic representations via joint optimization, and evaluated it on a downstream microcystin concentration regression model using NASA PACE hyperspectral imagery over Lake Erie. SpecTM achieves R^2 = 0.695 (current week) and R^2 = 0.620 (8-day-ahead) predictions surpassing all baseline models by (+34% (0.51 Ridge) and +99% (SVR 0.31)) respectively. Our ablation experiments show targeted masking improves predictions by +0.037 R^2 over random masking. Furthermore, it outperforms strong baselines with 2.2x superior label efficiency under extreme scarcity. SpecTM enables physics-informed representation learning across EO domains and improves the interpretability of foundation models.
title SpecTM: Spectral Targeted Masking for Trustworthy Foundation Models
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.22097