Faster Annotation for Elevation-Guided Flood Extent Mapping by Consistency-Enhanced Active Learning

Adhikari, Saugat; Yan, Da; Wang, Tianyang; Dyken, Landon; Kumar, Sidharth; Yuan, Lyuheng; Ahmad, Akhlaque; Han, Jiao; Zhou, Yang; Petruzza, Steve

doi:10.24963/ijcai.2025/1057

Faster Annotation for Elevation-Guided Flood Extent Mapping by Consistency-Enhanced Active Learning

Saugat Adhikari, Da Yan, Tianyang Wang, Landon Dyken, Sidharth Kumar, Lyuheng Yuan, Akhlaque Ahmad, Jiao Han, Yang Zhou, Steve Petruzza

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 9511-9519.

https://doi.org/10.24963/ijcai.2025/1057

Keywords

Computer Vision: General
Machine Learning: General

Abstract

Flood extent mapping is crucial for disaster response and damage assessment. While Earth imagery and terrain data (in the form of DEM) are now readily available, there are few flood annotation data for training machine learning models, which hinders the automated mapping of flooded areas. We propose ALFA, an interactive active-learning-based approach to minimize the annotators' efforts when preparing the ground-truth flood map in a satellite image. ALFA calibrates the prediction consistency of a segmentation model (1) across training cycles and (2) for various data augmentations. The two consistencies are integrated into the design of both the acquisition function and the loss function to enhance the robustness of active learning with limited annotation inputs. ALFA recommends those superpixels that the underlying model is most uncertain about, and users can annotate their pixels with minimal clicks with the help of elevation guidance. Extensive experiments on various regions hit by flooding show that we can improve the annotation time from hours to around 20 minutes. ALFA is open sourced at https://github.com/saugatadhikari/alfa.

Saugat Adhikari, Da Yan, Tianyang Wang, Landon Dyken, Sidharth Kumar, Lyuheng Yuan, Akhlaque Ahmad, Jiao Han, Yang Zhou, and Steve Petruzza. 2025. Faster Annotation for Elevation-Guided Flood Extent Mapping by Consistency-Enhanced Active Learning. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 9511–9519. https://doi.org/10.24963/ijcai.2025/1057

@inproceedings{ijcai2025p1057,
  title     = {Faster Annotation for Elevation-Guided Flood Extent Mapping by Consistency-Enhanced Active Learning},
  author    = {Adhikari, Saugat and Yan, Da and Wang, Tianyang and Dyken, Landon and Kumar, Sidharth and Yuan, Lyuheng and Ahmad, Akhlaque and Han, Jiao and Zhou, Yang and Petruzza, Steve},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {9511--9519},
  year      = {2025},
  month     = {8},
  note      = {AI and Social Good},
  doi       = {10.24963/ijcai.2025/1057},
  url       = {https://doi.org/10.24963/ijcai.2025/1057},
}

TY  - CPAPER
TI  - Faster Annotation for Elevation-Guided Flood Extent Mapping by Consistency-Enhanced Active Learning
AU  - Adhikari, Saugat
AU  - Yan, Da
AU  - Wang, Tianyang
AU  - Dyken, Landon
AU  - Kumar, Sidharth
AU  - Yuan, Lyuheng
AU  - Ahmad, Akhlaque
AU  - Han, Jiao
AU  - Zhou, Yang
AU  - Petruzza, Steve
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 9511
EP  - 9519
DO  - 10.24963/ijcai.2025/1057
UR  - https://doi.org/10.24963/ijcai.2025/1057
ER  -