Enhancing Reproducibility and Replicability in Remote Sensing Deep Learning Research and Practice
Many issues can reduce the reproducibility and replicability of deep learning (DL) research and application in remote sensing, including the complexity and customizability of architectures, variable model training and assessment processes and practice, inability to fully control random components of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/22/5760 |
| _version_ | 1797464116406779904 |
|---|---|
| author | Aaron E. Maxwell Michelle S. Bester Christopher A. Ramezan |
| author_facet | Aaron E. Maxwell Michelle S. Bester Christopher A. Ramezan |
| author_sort | Aaron E. Maxwell |
| collection | DOAJ |
| description | Many issues can reduce the reproducibility and replicability of deep learning (DL) research and application in remote sensing, including the complexity and customizability of architectures, variable model training and assessment processes and practice, inability to fully control random components of the modeling workflow, data leakage, computational demands, and the inherent nature of the process, which is complex, difficult to perform systematically, and challenging to fully document. This communication discusses key issues associated with convolutional neural network (CNN)-based DL in remote sensing for undertaking semantic segmentation, object detection, and instance segmentation tasks and offers suggestions for best practices for enhancing reproducibility and replicability and the subsequent utility of research results, proposed workflows, and generated data. We also highlight lingering issues and challenges facing researchers as they attempt to improve the reproducibility and replicability of their experiments. |
| first_indexed | 2024-03-09T18:02:23Z |
| format | Article |
| id | doaj.art-cc1a9532fd304f2295a00d7dee890304 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:02:23Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-cc1a9532fd304f2295a00d7dee8903042023-11-24T09:50:01ZengMDPI AGRemote Sensing2072-42922022-11-011422576010.3390/rs14225760Enhancing Reproducibility and Replicability in Remote Sensing Deep Learning Research and PracticeAaron E. Maxwell0Michelle S. Bester1Christopher A. Ramezan2Department of Geology and Geography, West Virginia University, Morgantown, WV 26505, USADepartment of Geology and Geography, West Virginia University, Morgantown, WV 26505, USAJohn Chambers College of Business and Economics, West Virginia University, Morgantown, WV 26505, USAMany issues can reduce the reproducibility and replicability of deep learning (DL) research and application in remote sensing, including the complexity and customizability of architectures, variable model training and assessment processes and practice, inability to fully control random components of the modeling workflow, data leakage, computational demands, and the inherent nature of the process, which is complex, difficult to perform systematically, and challenging to fully document. This communication discusses key issues associated with convolutional neural network (CNN)-based DL in remote sensing for undertaking semantic segmentation, object detection, and instance segmentation tasks and offers suggestions for best practices for enhancing reproducibility and replicability and the subsequent utility of research results, proposed workflows, and generated data. We also highlight lingering issues and challenges facing researchers as they attempt to improve the reproducibility and replicability of their experiments.https://www.mdpi.com/2072-4292/14/22/5760deep learningreplicabilityreproducibilitysemantic segmentationobject detection |
| spellingShingle | Aaron E. Maxwell Michelle S. Bester Christopher A. Ramezan Enhancing Reproducibility and Replicability in Remote Sensing Deep Learning Research and Practice Remote Sensing deep learning replicability reproducibility semantic segmentation object detection |
| title | Enhancing Reproducibility and Replicability in Remote Sensing Deep Learning Research and Practice |
| title_full | Enhancing Reproducibility and Replicability in Remote Sensing Deep Learning Research and Practice |
| title_fullStr | Enhancing Reproducibility and Replicability in Remote Sensing Deep Learning Research and Practice |
| title_full_unstemmed | Enhancing Reproducibility and Replicability in Remote Sensing Deep Learning Research and Practice |
| title_short | Enhancing Reproducibility and Replicability in Remote Sensing Deep Learning Research and Practice |
| title_sort | enhancing reproducibility and replicability in remote sensing deep learning research and practice |
| topic | deep learning replicability reproducibility semantic segmentation object detection |
| url | https://www.mdpi.com/2072-4292/14/22/5760 |
| work_keys_str_mv | AT aaronemaxwell enhancingreproducibilityandreplicabilityinremotesensingdeeplearningresearchandpractice AT michellesbester enhancingreproducibilityandreplicabilityinremotesensingdeeplearningresearchandpractice AT christopheraramezan enhancingreproducibilityandreplicabilityinremotesensingdeeplearningresearchandpractice |