Ten deep learning techniques to address small data problems with remote sensing

This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: https://doi.org/10.1016/j.jag.2023.103569. This is version 3 of this Preprint.

Add a Comment

You must log in to post a comment.


There are no comments or no comments have been made public for this article.


Download Preprint


Anastasiia Safonova, Gohar Ghazaryan, Stefan Stiller, Magdalena Main-Knorn, Claas Nendel, Masahiro Ryo


Researchers and engineers have increasingly used Deep Learning (DL) for a variety of Remote Sensing (RS) tasks. However, data from local observations or via ground truth is often quite limited for training DL models, especially when these models represent key socio-environmental problems, such as the monitoring of extreme, destructive climate events, biodiversity, and sudden changes in ecosystem states. Such cases, also known as small data problems, pose significant methodological challenges. This review summarises these challenges in the RS domain and the possibility of using emerging DL techniques to overcome them. We show that the small data problem is a common challenge across disciplines and scales that results in poor model generalisability and transferability. We then introduce an overview of ten promising DL techniques: transfer learning, self-supervised learning, semi-supervised learning, few-shot learning, zero-shot learning, active learning, weakly supervised learning, multitask learning, process-aware learning, and ensemble learning; we also include a validation technique known as spatial k-fold cross validation. Our particular contribution was to develop a flowchart that helps DL users select which technique to use given by answering a few questions. We hope that our review article facilitate DL applications to tackle societally important environmental problems with limited reference data.




Artificial Intelligence and Robotics, Other Earth Sciences


remote sensing, Cross Validation, Ensemble Learning, multi-task learning, Weakly Supervised Learning, active learning, Semi-Supervised Learning, transfer learning, Process-Aware AI, Self-Supervised Learning, Zero-Shot Learning, Few-Shot Learning, UAV Imagery, Deep learning, machine learning, Data Sparsity, Limited Annotated Data, Limited Labeled Data, Limited Sample Size, Process-Aware AI, Self-Supervised Learning, Zero-Shot Learning, Few-Shot Learning, UAV Imagery, Deep Learning, machine learning, Remote Sensing, Limited Annotated Data, Limited Labeled Data, Limited Sample Size


Published: 2023-06-09 14:39

Last Updated: 2023-09-08 19:26

Older Versions

CC BY Attribution 4.0 International

Additional Metadata

Conflict of interest statement:
The authors declare no competing interests.

Data Availability (Reason not available):
Not applicable.