# Semantic Segmentation in Satellite Hyperspectral Imagery by Deep Learning

arXiv: https://arxiv.org/abs/2310.16210 · HTML: https://mlsanity.com/paper/2310.16210/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 64 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 7 of 7)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [The Final Frontier: Deep Learning in Space](https://mlsanity.com/paper/2001.10362/) (2020)
- [An Open Hyperspectral Dataset with Sea-Land-Cloud Ground-Truth from the HYPSO-1 Satellite](https://mlsanity.com/paper/2308.13679/) (2023)
- [Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data](https://mlsanity.com/paper/1901.04846/) (2019)
- [Self-Configuring nnU-Nets Detect Clouds in Satellite Images](https://mlsanity.com/paper/2210.13659/) (2022)
- [Squeezing nnU-Nets with Knowledge Distillation for On-Board Cloud Detection](https://mlsanity.com/paper/2306.09886/) (2023)

## Built on by (most cited first, 5 of 5)

- [Data-Efficient Spectral Classification of Hyperspectral Data Using MiniROCKET and HDC-MiniROCKET](https://mlsanity.com/paper/2509.13809/) (2025)
- [Lightweight Cloud Masking Models for On-Board Inference in Hyperspectral Imaging](https://mlsanity.com/paper/2507.08052/) (2025)
- [Curriculum Multi-Task Self-Supervision Improves Lightweight Architectures for Onboard Satellite Hyperspectral Image Segmentation](https://mlsanity.com/paper/2509.13229/) (2025)
- [AI-enabled Satellite Edge Computing: A Single-Pixel Feature based Shallow Classification Model for Hyperspectral Imaging](https://mlsanity.com/paper/2601.18560/) (2026)
- [Cross-Domain Transfer of Hyperspectral Foundation Models](https://mlsanity.com/paper/2604.26478/) (2026)

## Abstract (arXiv)

Satellites are increasingly adopting on-board AI to optimize operations and increase autonomy through in-orbit inference. The use of Deep Learning (DL) models for segmentation in hyperspectral imagery offers advantages for remote sensing applications. In this work, we train and test 20 models for multi-class segmentation in hyperspectral imagery, selected for their potential in future space deployment. These models include 1D and 2D Convolutional Neural Networks (CNNs) and the latest vision transformers (ViTs). We propose a lightweight 1D-CNN model, 1D-Justo-LiuNet, which outperforms state-of-the-art models in the hypespectral domain. 1D-Justo-LiuNet exceeds the performance of 2D-CNN UNets and outperforms Apple's lightweight vision transformers designed for mobile inference. 1D-Justo-LiuNet achieves the highest accuracy (0.93) with the smallest model size (4,563 parameters) among all tested models, while maintaining fast inference. Unlike 2D-CNNs and ViTs, which encode both spectral and spatial information, 1D-Justo-LiuNet focuses solely on the rich spectral features in hyperspectral data, benefitting from the high-dimensional feature space. Our findings are validated across various satellite datasets, with the HYPSO-1 mission serving as the primary case study for sea, land, and cloud segmentation. We further confirm our conclusions through generalization tests on other hyperspectral missions, such as NASA's EO-1. Based on its superior performance and compact size, we conclude that 1D-Justo-LiuNet is highly suitable for in-orbit deployment, providing an effective solution for optimizing and automating satellite operations at edge.