cs.LGNov 18, 2026

Synthesizing hyperspectral Data using generative Models to train spectral Unmixing Methods for low-cost Crop Residue Cover Mapping

Authors: Ege Artan, Shuo Chen, Andrew Peng, Sammuel Aldrich Karya, Kyaw Thiha

Organizations: University of Toronto Scarborough, Univ. of Toronto, 1265 Military Trail, Toronto, ON M1C 1A4, Canada · Space Systems, University of Toronto Aerospace Team, 10 King’s College Road, B740 Sandford Fleming Building, Toronto, ON M5S 3G8, Canada · Faculty of Arts and Science, University of Toronto, 100 St. George Street, Toronto, ON M5S 3G3, Canada

Abstract

The spectral range of the Field Imaging Nanosatellite for Crop residue Hyperspectral Mapping (FINCH), developed by the University of Toronto Aerospace Team's Space System Division, poses significant challenges for hyperspectral unmixing to determine crop residue cover fractional abundances. The severe lack of standard indices necessitates the use of complex, data-driven unmixing models. Complex unmixing models require dense, well-distributed manifolds, whereas ground-truth datasets are sparse and expensive. To better leverage the information content in existing ground-truth datasets, this study presents a framework that decouples interpolation and abundance-mapping estimation via an intermediary conditional data generator, contrasting with traditional single-model unmixing pipelines. This decoupling enables the inclusion of physical prior knowledge about spectra, which is not natively accessible to unmixing models, thereby artificially expanding the dataset to serve as a Monte Carlo approximation of the population risk. To test this hypothesis, we have proposed two generator models: a 1D Conditional U-Net with Conformer Layers (GD-Streamline) and a Dual-Path Transformer Conditional Variational AutoEncoder (TCVAE), and two unmixing models: Multi-Layered Perceptrons (MLP) and Fourier Neural Operators (FNO). The results of the study indicate a need for rigorous integration and introduction of spectral priors within the scope of the proposed decoupling framework to prevent domain and mode collapse and hallucination by the generator models; otherwise, this leads to falsely approximated data manifolds, ultimately resulting in unsatisfactory and out-of-distribution unmixing performance.

Figures & tables

Explore similar work

CardsList
  1. Looking into a Pixel by Nonlinear Unmixing -- A Generative Approach

    Apr 1, 2026Maofeng Tang, Hairong QiSpectral UnmixingHyperspectral Unmixing

  2. Benchmarking Hyperspectral Foundation Models for Hyperspectral Unmixing

    Sep 23, 2026Edgard Dabier, Christophe Kervazo, Pietro Gori +1Hyperspectral ImagingHyperspectral Unmixing

  3. Agentic Multimodal Models for Environmental Hyperspectral Unmixing

    Sep 1, 2026Michał Cholewa, Luca Ciampi, Nicola Messina +2Hyperspectral ImagingHyperspectral Unmixing