{"id":20763147,"url":"https://github.com/dymaxionlabs/burned-area-detection","last_synced_at":"2025-04-30T07:47:57.704Z","repository":{"id":48782281,"uuid":"366733824","full_name":"dymaxionlabs/burned-area-detection","owner":"dymaxionlabs","description":"Detection of burned areas using deep learning from satellite images","archived":false,"fork":false,"pushed_at":"2022-02-07T19:09:36.000Z","size":7462,"stargazers_count":12,"open_issues_count":2,"forks_count":8,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-04-24T12:14:09.106Z","etag":null,"topics":["burned-area","machine-learning","satellite-imagery","unet"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dymaxionlabs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-05-12T13:56:11.000Z","updated_at":"2024-03-23T03:20:43.000Z","dependencies_parsed_at":"2022-09-04T18:11:23.442Z","dependency_job_id":null,"html_url":"https://github.com/dymaxionlabs/burned-area-detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dymaxionlabs%2Fburned-area-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dymaxionlabs%2Fburned-area-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dymaxionlabs%2Fburned-area-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dymaxionlabs%2Fburned-area-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dymaxionlabs","download_url":"https://codeload.github.com/dymaxionlabs/burned-area-detection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225029151,"owners_count":17409613,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["burned-area","machine-learning","satellite-imagery","unet"],"created_at":"2024-11-17T10:42:59.266Z","updated_at":"2024-11-17T10:42:59.857Z","avatar_url":"https://github.com/dymaxionlabs.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"*This digital tool is part of the catalog of tools of the **Inter-American Development Bank**. You can learn more about the IDB initiative at [code.iadb.org](https://code.iadb.org/en)*\n\n\u003cp align=\"center\"\u003e\n  \u003cimg height=\"200\" src=\"img/logo.png\"\u003e\n\u003c/p\u003e\n\n  # \u003cimg height=\"30\" src=\"https://img.icons8.com/flat-round/64/000000/fire-element.png\"/\u003e burned-area-detection  \n  \n\n[![License](https://img.shields.io/badge/license-Apache%202.0-blue)](https://github.com/dymaxionlabs/burned-area-detection/blob/master/LICENSE.txt)\n\n\n\n\u003cbr\u003e\n\u003cp align=\"center\"\u003eDetection of burned areas using deep learning from satellite images.\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg height=\"300\" widht=\"500\" src=\"img/burn.jpg\"\u003e\n\u003c/p\u003e\n\n\u003cp  align=\"center\"\u003e\n• \u003ca  href=\"#-description\"\u003eDescription\u003c/a\u003e •\n\u003ca  href=\"#notebook-notebooks\"\u003eNotebooks\u003c/a\u003e •\n\u003ca  href=\"#-about-dymaxion-labs\"\u003eAbout Dymaxion Labs\u003c/a\u003e •\n\u003ca  href=\"#handshake-contributing\"\u003eContributing\u003c/a\u003e •\n\u003ca  href=\"#page_facing_up-license\"\u003eLicense\u003c/a\u003e •\n\u003c/p\u003e\n\n## \u003cimg height=\"25\" src=\"https://code.iadb.org/sites/default/files/2019-04/31227283.png\"/\u003e Description\n\nThe burned-area-detection project aims to identify and analyze the affected\nareas after a fire incident. It allows us to understand incident behavior to\ntake action shortly.\n\nThe number of uncontrolled fires has increased significantly in the last few\nyears. This kind of environmental catastrophe affects habitat and community on\nseveral levels. The impact on our environment can be evidenced in a short time\nby measuring the wellness and the evacuation process of the different\ncommunities living in affected areas. But we are also able to notice its\neffects in the long term due to the impact on nature and local economies. Some\nof the project's principal goals are measuring these affected areas. \n\nThis project uses Sentinel-2 public satellite images. Sentinel-2 has high\ncadence at no cost, allowing the study of the affected area's evolution across\ntime. These images can be download from Google Earth Engine. There are several\nreflectance bands available to use, besides a combination of them can be more\nsensitive to detect burn areas.\n\n### Normalized Burn Ratio (NBR)\n\nThe Normalized Burn Ratio (NBR) is an index that highlights burnt areas in\nlarge fire zones. The formula combines the near-infrared (NIR) and shortwave\ninfrared (SWIR) wavelengths.\n\nHealthy vegetation shows a very high reflectance in the NIR, and low\nreflectance in the SWIR portion of the spectrum, (see figure below). The\ncontrary happens for areas destroyed by fire; recently burnt areas show a low\nreflectance in the NIR and high reflectance in the SWIR. Therefore, the\nnormalized difference between the NIR and the SWIR is a good discriminant for\nthis kind of phenomenon.\n\u003cp align=\"center\"\u003e\n  \u003cimg widht=\"500\" src=\"img/Spectral_responses.jpg\"\u003e\n\u003c/p\u003e\n\n\n### Burn Severity\n\nThe difference between the pre-fire and post-fire NBR obtained from the images\nis used to calculate the delta NBR. A higher value of dNBR indicates more\nsevere damage, while areas with negative dNBR values may indicate regrowth\nfollowing a fire.\n\nUses [satproc](https://github.com/dymaxionlabs/satproc) and\n[unetseg](https://github.com/dymaxionlabs/unetseg) Python packages.\n\n\n## \t:notebook: Notebooks\n\nThis repository contains a set of Jupyter Notebooks describing the steps for\nbuilding a semantic segmentation model based on the U-Net architecture for\ndetecting burned areas from fires from optical satellite imagery.\n\n1. [Pre-process](1_Pre-process.ipynb): Image and ground truth data preprocessing and dataset generation\n2. [Training](2_Training.ipynb): Model training and evaluation\n3. [Prediction](3_Prediction.ipynb): Prediction\n4. [Post-process](4_Post-process.ipynb): Post-processing of prediction results\n\n## \u003cimg height=\"25\" src=\"https://code.iadb.org/sites/default/files/2019-04/31227283.png\"/\u003e About Dymaxion Labs\n[Dymaxion Labs](https://dymaxionlabs.com/) leverages AI and Computer Vision to analyze petabytes of geospatial data to understand the physical world. These include optical, SAR and aerial imagery, climate data, and IoT sensors.\nWith our grounded, data science based methodology, private companies and the public sector accelerate strategic data-driven decisions from their remote targets.\n### :man_technologist: Authors\n* María Roberta Devesa \u003cro.devesa@dymaxionlabs.com\u003e\n* Damián Silvani \u003cdamian@dymaxionlabs.com\u003e\n\n\n\n## :handshake: Contributing\n\nBug reports and pull requests are welcome on GitHub at the [issues\npage](https://github.com/dymaxionlabs/burned-area-detection). This project is\nintended to be a safe, welcoming space for collaboration, and contributors are\nexpected to adhere to the [Contributor\nCovenant](http://contributor-covenant.org) code of conduct.\n\n## :page_facing_up: License\n\nThis project is licensed under Apache 2.0. Refer to [LICENSE.txt](LICENSE.txt).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdymaxionlabs%2Fburned-area-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdymaxionlabs%2Fburned-area-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdymaxionlabs%2Fburned-area-detection/lists"}