https://github.com/google-research/skai
SKAI is a machine learning based tool for performing automatic building damage assessments on aerial imagery of disaster sites.
Science Score: 36.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.9%) to scientific vocabulary
Keywords from Contributors
Repository
SKAI is a machine learning based tool for performing automatic building damage assessments on aerial imagery of disaster sites.
Basic Info
Statistics
- Stars: 139
- Watchers: 15
- Forks: 21
- Open Issues: 15
- Releases: 4
Metadata Files
docs/README.md
SKAI
SKAI is a machine learning based tool for performing automatic building damage assessments on aerial imagery of disaster sites.
If you are working in the disaster response space and/or are interested in using SKAI, please reach out to the developers at skai-developers@googlegroups.com.
Background
A humanitarian disaster such as an earthquake, hurricane, or wildfire is a highly disruptive event that affects a region and people in complex ways. Disaster assessment is the process of understanding, quantifying, and locating these harmful effects, in order to provide crisis responders with situation awareness and help them plan rescue and recovery activities.
One predominant type of disaster assessment is identifying all buildings that were damaged or destroyed in a disaster. This helps estimate how much of the population is unsheltered or possibly trapped in rubble, or how much it will cost to rebuild a neighborhood.
SKAI uses machine learning and aerial imagery to automatically identify the locations of damaged buildings in a disaster region. This significantly speeds up damage assessment turn-around times and lowers labor costs. Model-generated assessments match expert generated assessments on between 85% and 98% of buildings assessed in many past disasters ranging from hurricanes to wildfires.
For more information, please refer to our NeurIPS workshop paper and our blog post.
Setup
Please see detailed setup instructions here.
Using SKAI
Please see detailed instructions here.
Acknowledgments
This software was developed in collaboration with the following organizations:
United Nations World Food Program (WFP) Innovation Accelerator
The WFP Innovation Accelerator identifies, supports and scales high potential solutions to hunger worldwide. The Innovation Accelerator supports WFP innovators and external start-ups and companies through financial support, access to a network of experts and a global field reach.
InstaDeep AI for Social Good (AI4SG) team
InstaDeep's AI for Social Good (AI4SG) team utilizes the company's expertise in AI research and engineering to create technologies aimed at improving human welfare and enhancing global well-being.
Owner
- Name: Google Research
- Login: google-research
- Kind: organization
- Location: Earth
- Website: https://research.google
- Repositories: 226
- Profile: https://github.com/google-research
GitHub Events
Total
- Release event: 4
- Watch event: 25
- Delete event: 83
- Issue comment event: 1
- Push event: 337
- Pull request review comment event: 6
- Pull request review event: 8
- Pull request event: 185
- Fork event: 6
- Create event: 99
Last Year
- Release event: 4
- Watch event: 25
- Delete event: 83
- Issue comment event: 1
- Push event: 337
- Pull request review comment event: 6
- Pull request review event: 8
- Pull request event: 185
- Fork event: 6
- Create event: 99
Committers
Last synced: 11 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Joseph Xu | j****u@g****m | 239 |
| panford | p****y@g****m | 129 |
| ambaha1 | b****e@h****r | 78 |
| Boris Lami Fonyuy | f****y@g****m | 25 |
| Mohamedelfatih Mohamedkhair | m****h@g****m | 20 |
| Ibrahim Salihu Yusuf | i****f@i****m | 15 |
| Jihyeon Lee | j****e@g****m | 15 |
| Skai team | n****y@g****m | 13 |
| rsadiq | r****q@w****g | 6 |
| Mohamedelfatih Mohamedkhair | m****h@g****m | 6 |
| dependabot[bot] | 4****] | 5 |
| Ryan Wang | j****g@g****m | 4 |
| Jun Takahashi | j****i@g****m | 4 |
| Luke Granger-Brown | l****b@g****m | 2 |
| Kurt Schwehr | s****r@g****m | 1 |
| Lily Hu | r****u@g****m | 1 |
| Rebecca Chen | r****n@g****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 7 months ago
All Time
- Total issues: 3
- Total pull requests: 513
- Average time to close issues: 5 days
- Average time to close pull requests: 8 days
- Total issue authors: 2
- Total pull request authors: 9
- Average comments per issue: 0.33
- Average comments per pull request: 0.08
- Merged pull requests: 321
- Bot issues: 2
- Bot pull requests: 462
Past Year
- Issues: 1
- Pull requests: 197
- Average time to close issues: N/A
- Average time to close pull requests: 5 days
- Issue authors: 1
- Pull request authors: 3
- Average comments per issue: 0.0
- Average comments per pull request: 0.02
- Merged pull requests: 146
- Bot issues: 1
- Bot pull requests: 196
Top Authors
Issue Authors
- copybara-service[bot] (2)
- BioGeek (1)
Pull Request Authors
- copybara-service[bot] (445)
- dependabot[bot] (17)
- ambaha1 (16)
- jzxu (13)
- panford (13)
- rsadiq (6)
- erikaguti (1)
- rajveer43 (1)
- Alikerin (1)
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- absl-py >=0.12.0
- apache_beam *
- earthengine-api *
- geopandas *
- google-cloud-aiplatform *
- google-cloud-bigquery-storage *
- google_apitools *
- numpy *
- opencv-python *
- pandas *
- pillow *
- pyproj *
- pytest *
- rasterio *
- requests *
- rio-cogeo *
- shapely *
- sklearn *
- tensorflow *
- tensorflow-addons *
- tensorflow_probability *
- tqdm *
- actions/checkout v3 composite
- actions/setup-python v3 composite