# A Novel Graph-Regulated Disentangling Mamba Model with Sparse Tokens for Enhanced Tree Species Classification from MODIS Time Series

arXiv: https://arxiv.org/abs/2605.05549 · HTML: https://mlsanity.com/paper/2605.05549/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Hyperspectral image analysis with Mamba, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 4 of its 8 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Hyperspectral image analysis with Mamba](https://mlsanity.com/ssm/hyperspectral-image-analysis-with-mamba/)

## Builds on (most cited first, 4 of 4)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Graph Convolutional Networks for Hyperspectral Image Classification](https://mlsanity.com/paper/2008.02457/) (2020)
- [SITSMamba for Crop Classification based on Satellite Image Time Series](https://mlsanity.com/paper/2409.09673/) (2024)
- [Sparse Deformable Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2504.09446/) (2025)

## Abstract (arXiv)

Although tree species classification from Moderate Resolution Imaging Spectroradiometer (MODIS) time series data is critical for supporting various environmental applications, it is a challenging task due to several key difficulties: the subtle signature differences among tree species, strong spatial-spectral-temporal information coupling, and the difficulty of modeling large-scale topological context information. To better address these challenges, this paper presents a novel Graph-regulated Disentangled Sparse Mamba model (GDS-Mamba) for enhanced tree species classification, with the following contributions. (1) First, to improve large-scale context modeling, we design a mini-batch graph-regulated approach that explicitly explores topological correlation effects among input images. (2) Second, to disentangle the high-dimensional spatial-spectral-temporal information coupling for improved feature extraction, we propose a novel disentangling Mamba architecture tailored for capturing independent spatial patterns, spectral signatures, and temporal phenology behaviors in MODIS time series. (3) Third, to improve efficiency and subtle feature learning, we design novel sparse token approaches that adaptively learn the optimum subset of tokens to better address the correlation decay problem that bottlenecks standard Mamba models. Extensive experiments using large-scale annual MOD13Q1 data across two Canadian provinces (i.e., Alberta and Saskatchewan) achieved an overall accuracy of 93.94% in Alberta and 80.19% in cross-provincial evaluations, outperforming twelve state-of-the-art classification models.