[](https://doi.org/10.1109/JSTARS.2024.3480520) [](https://github.com/spaceml-org/DTACSNet/releases) [](https://pypi.org/project/dtacs/) [](https://pypi.org/project/dtacs/) [](https://github.com/spaceml-org/DTACSNet/blob/main/LICENSE) [](https://spaceml-org.github.io/DTACSNet/)
# [DTACSNet: Onboard Cloud Detection and Atmospheric Correction With Efficient Deep Learning Models](https://ieeexplore.ieee.org/document/10716772)
*Cesar Aybar*<sup>§</sup>, *Gonzalo Mateo-GarcĂa*<sup>§</sup>, *Giacomo Acciarini*<sup>§</sup>, *Vit Ruzicka*, *Gabriele Meoni*, *Nicolas Longepe*, *Luis GĂłmez-Chova* <sub><sup>*§ development contribution*</sup></sub>
[10.1109/JSTARS.2024.3480520](https://ieeexplore.ieee.org/document/10716772)
This repo contains an open implementation to run inference with DTACSNet models for atmospheric correction. **This repo and trained models are released under a** [Creative Commons non-commercial licence](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt)
<img src="https://mirrors.creativecommons.org/presskit/buttons/88x31/png/by-nc.png" alt="licence" width="60"/>
Install ⚙️:
```bash
pip install dtacs
```
Run:
```python
from dtacs.model_wrapper import ACModel
model_atmospheric_correction = ACModel(model_name="CNN_corrector_phisat2")
model_atmospheric_correction.load_weights()
ac_output = model_atmospheric_correction.predict(l1c_toa_s2)
```
<img src="assets/example_ac.png" alt="awesome atmospheric correction" width="100%">
The figure above shows a sample of Sentinel-2 level 1C, DTACSNet model output and Sentinel-2 level 2A in the RGB (first row) and in the SWIR, NIR, Red (last row) composites.
See the [inference tutorial](https://spaceml-org.github.io/DTACSNet/tutorials/inference_Sentinel-2.html) for a complete example.
## Citation
If you find this work useful for your research, please consider citing [our work](https://ieeexplore.ieee.org/document/10716772):
```bibtex
@article{aybar_onboard_2024,
title = {Onboard {Cloud} {Detection} and {Atmospheric} {Correction} {With} {Efficient} {Deep} {Learning} {Models}},
volume = {17},
issn = {2151-1535},
url = {https://ieeexplore.ieee.org/abstract/document/10716772},
doi = {10.1109/JSTARS.2024.3480520},
urldate = {2024-11-12},
journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
author = {Aybar, Cesar and Mateo-GarcĂa, Gonzalo and Acciarini, Giacomo and RĹŻĹľiÄŤka, VĂt and Meoni, Gabriele and LongĂ©pĂ©, Nicolas and GĂłmez-Chova, Luis},
year = {2024},
note = {Conference Name: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
pages = {19518--19529}
}
```
## Acknowledgments
DTACSNet has been developed by Trillium Technologies. It has been funded by ESA Cognitive Cloud Computing in Space initiative project number D-TACS I-2022-00380.
## More Cloud Detection Viz
 Thick cloud
 Thin cloud
 Cloud shadow
## More Atmospheric Correction Viz
Raw data
{
"_id": null,
"home_page": "https://github.com/spaceml-org/DTACSNet",
"name": "dtacs",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Gonzalo Mateo-Garc\u00eda",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/a7/45/ad85a284469479a1ee02ff7a11918ab5853cf3b38afc60c983c857eb3c0b/dtacs-1.0.1.tar.gz",
"platform": null,
"description": "[](https://doi.org/10.1109/JSTARS.2024.3480520) [](https://github.com/spaceml-org/DTACSNet/releases) [](https://pypi.org/project/dtacs/) [](https://pypi.org/project/dtacs/) [](https://github.com/spaceml-org/DTACSNet/blob/main/LICENSE) [](https://spaceml-org.github.io/DTACSNet/)\n\n# [DTACSNet: Onboard Cloud Detection and Atmospheric Correction With Efficient Deep Learning Models](https://ieeexplore.ieee.org/document/10716772)\n\n*Cesar Aybar*<sup>\u00a7</sup>, *Gonzalo Mateo-Garc\u00eda*<sup>\u00a7</sup>, *Giacomo Acciarini*<sup>\u00a7</sup>, *Vit Ruzicka*, *Gabriele Meoni*, *Nicolas Longepe*, *Luis G\u00f3mez-Chova* <sub><sup>*\u00a7 development contribution*</sup></sub>\n\n[10.1109/JSTARS.2024.3480520](https://ieeexplore.ieee.org/document/10716772)\n\nThis repo contains an open implementation to run inference with DTACSNet models for atmospheric correction. **This repo and trained models are released under a** [Creative Commons non-commercial licence](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) \n<img src=\"https://mirrors.creativecommons.org/presskit/buttons/88x31/png/by-nc.png\" alt=\"licence\" width=\"60\"/>\n\nInstall \u2699\ufe0f:\n```bash\npip install dtacs\n```\n\nRun:\n\n```python\nfrom dtacs.model_wrapper import ACModel\nmodel_atmospheric_correction = ACModel(model_name=\"CNN_corrector_phisat2\")\nmodel_atmospheric_correction.load_weights()\n\nac_output = model_atmospheric_correction.predict(l1c_toa_s2)\n```\n\n<img src=\"assets/example_ac.png\" alt=\"awesome atmospheric correction\" width=\"100%\">\nThe figure above shows a sample of Sentinel-2 level 1C, DTACSNet model output and Sentinel-2 level 2A in the RGB (first row) and in the SWIR, NIR, Red (last row) composites.\n\nSee the [inference tutorial](https://spaceml-org.github.io/DTACSNet/tutorials/inference_Sentinel-2.html) for a complete example.\n\n\n## Citation\n\nIf you find this work useful for your research, please consider citing [our work](https://ieeexplore.ieee.org/document/10716772):\n\n```bibtex\n@article{aybar_onboard_2024,\n\ttitle = {Onboard {Cloud} {Detection} and {Atmospheric} {Correction} {With} {Efficient} {Deep} {Learning} {Models}},\n\tvolume = {17},\n\tissn = {2151-1535},\n\turl = {https://ieeexplore.ieee.org/abstract/document/10716772},\n\tdoi = {10.1109/JSTARS.2024.3480520},\n\turldate = {2024-11-12},\n\tjournal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},\n\tauthor = {Aybar, Cesar and Mateo-Garc\u00eda, Gonzalo and Acciarini, Giacomo and R\u016f\u017ei\u010dka, V\u00edt and Meoni, Gabriele and Long\u00e9p\u00e9, Nicolas and G\u00f3mez-Chova, Luis},\n\tyear = {2024},\n\tnote = {Conference Name: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},\n\tpages = {19518--19529}\n}\n```\n\n## Acknowledgments\n\nDTACSNet has been developed by Trillium Technologies. It has been funded by ESA Cognitive Cloud Computing in Space initiative project number D-TACS I-2022-00380.\n\n## More Cloud Detection Viz\n\n Thick cloud\n Thin cloud \n Cloud shadow\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n## More Atmospheric Correction Viz\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"bugtrack_url": null,
"license": "\tGPL-3.0",
"summary": "\ud83d\udef0\ufe0f Cloud Detection and Atmospheric Correction With Efficient Deep Learning Models",
"version": "1.0.1",
"project_urls": {
"Documentation": "https://spaceml-org.github.io/DTACSNet/",
"Homepage": "https://github.com/spaceml-org/DTACSNet",
"Repository": "https://github.com/spaceml-org/DTACSNet"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "74a8b903a51fd9191b30a91aa3faadce30bf817e51bd769576e62a32f705a968",
"md5": "fdcf252109f2fe4c8448a53f5f45e002",
"sha256": "6c64d8dad2f9de167f85e9ac0eee9d6cc6cb28174786af67d163ed20cc0676d9"
},
"downloads": -1,
"filename": "dtacs-1.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "fdcf252109f2fe4c8448a53f5f45e002",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 21405,
"upload_time": "2024-12-04T06:05:58",
"upload_time_iso_8601": "2024-12-04T06:05:58.245229Z",
"url": "https://files.pythonhosted.org/packages/74/a8/b903a51fd9191b30a91aa3faadce30bf817e51bd769576e62a32f705a968/dtacs-1.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "a745ad85a284469479a1ee02ff7a11918ab5853cf3b38afc60c983c857eb3c0b",
"md5": "f6d4cbad246058ee8dbc628af3d77e5f",
"sha256": "ace7c31f8829c2a21e8c58bb96598c9b780cd52bbc61b5126915b173bafd9742"
},
"downloads": -1,
"filename": "dtacs-1.0.1.tar.gz",
"has_sig": false,
"md5_digest": "f6d4cbad246058ee8dbc628af3d77e5f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 22892,
"upload_time": "2024-12-04T06:06:00",
"upload_time_iso_8601": "2024-12-04T06:06:00.196942Z",
"url": "https://files.pythonhosted.org/packages/a7/45/ad85a284469479a1ee02ff7a11918ab5853cf3b38afc60c983c857eb3c0b/dtacs-1.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-04 06:06:00",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "spaceml-org",
"github_project": "DTACSNet",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"tox": true,
"lcname": "dtacs"
}
JSON
