Data Augmentation in Earth Observation: A Diffusion Model Approach
Open Access
- 22 January 2025
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 16 (2) , 81
Abstract
High-quality Earth Observation (EO) imagery is essential for accurate analysis and informed decision making across sectors. However, data scarcity caused by atmospheric conditions, seasonal variations, and limited geographical coverage hinders the effective application of Artificial Intelligence (AI) in EO. Traditional data augmentation techniques, which rely on basic parameterized image transformations, often fail to introduce sufficient diversity across key semantic axes. These axes include natural changes such as snow and floods, human impacts like urbanization and roads, and disasters such as wildfires and storms, which limits the accuracy of AI models in EO applications. To address this, we propose a four-stage data augmentation approach that integrates diffusion models to enhance semantic diversity. Our method employs meta-prompts for instruction generation, vision–language models for rich captioning, EO-specific diffusion model fine-tuning, and iterative data augmentation. Extensive experiments using four augmentation techniques demonstrate that our approach consistently outperforms established methods, generating semantically diverse EO images and improving AI model performance.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- RSDiff: remote sensing image generation from text using diffusion modelNeural Computing and Applications, 2024
- Label Freedom: Stable Diffusion for Remote Sensing Image Semantic Segmentation Data Generation2023
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- A review on remote sensing imagery augmentation using deep learningMaterials Today: Proceedings, 2022
- AutoAugment: Learning Augmentation Strategies From Data2019
- A review of applications of satellite earth observation data for global societal benefit and stewardship of planet earthSpace Policy, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- The role of satellite remote sensing in climate change studiesNature Climate Change, 2013
- Remote Sensing and Global Environmental Change2011