# Physics-Informed Spectral Modeling for Hyperspectral Imaging

arXiv: https://arxiv.org/abs/2508.21618 · HTML: https://mlsanity.com/paper/2508.21618/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 40 references that are in the map.
- First posted on arXiv 29 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers](https://mlsanity.com/paper/2107.02988/) (2021)
- [Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning](https://mlsanity.com/paper/1905.06088/) (2019)
- [Incorporating Domain Knowledge into Deep Neural Networks](https://mlsanity.com/paper/2103.00180/) (2021)
- [shapiq: Shapley Interactions for Machine Learning](https://mlsanity.com/paper/2410.01649/) (2024)
- [Validating Hyperspectral Image Segmentation](https://mlsanity.com/paper/1811.03707/) (2018)
- [Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution](https://mlsanity.com/paper/2110.11591/) (2021)
- [BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification](https://mlsanity.com/paper/1612.00144/) (2016)
- [Physics-informed Machine Learning for Battery Pack Thermal Management](https://mlsanity.com/paper/2411.09915/) (2024)
- [Tobler's First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection Under Weak Supervision](https://mlsanity.com/paper/2508.03745/) (2025)

## Built on by (most cited first, 2 of 2)

- [Scalable and Trustworthy Earth Observation Foundation Models](https://mlsanity.com/paper/2607.07758/) (2026)
- [DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification](https://mlsanity.com/paper/2607.15128/) (2026)

## Abstract (arXiv)

We present PhISM, a physics-informed deep learning architecture that learns without supervision to explicitly disentangle hyperspectral observations and model them with continuous basis functions. PhISM outperforms prior methods on several classification and regression benchmarks, requires limited labeled data, and provides additional insights thanks to interpretable latent representation.