{"id":139790,"name":"STARCOP","description":"Semantic Segmentation of Methane Plumes with Hyperspectral Machine Learning models.","url":"https://github.com/spaceml-org/starcop","last_synced_at":"2026-04-13T17:01:14.766Z","repository":{"id":207754749,"uuid":"632550611","full_name":"spaceml-org/STARCOP","owner":"spaceml-org","description":"Official code for STARCOP: Semantic Segmentation of Methane Plumes with Hyperspectral Machine Learning models :rainbow::artificial_satellite:","archived":false,"fork":false,"pushed_at":"2025-07-24T11:24:52.000Z","size":10865,"stargazers_count":69,"open_issues_count":1,"forks_count":14,"subscribers_count":6,"default_branch":"main","last_synced_at":"2026-04-11T16:02:35.470Z","etag":null,"topics":["aviris","aviris-ng","emit","hyperspectral","hyperspectral-datasets","machine-learning","methane","methane-detection"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/spaceml-org.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-04-25T16:32:03.000Z","updated_at":"2026-03-23T15:26:36.000Z","dependencies_parsed_at":"2024-03-18T05:00:44.626Z","dependency_job_id":"6fcc1cf1-dd4f-452c-b816-19d4f2d82788","html_url":"https://github.com/spaceml-org/STARCOP","commit_stats":{"total_commits":19,"total_committers":3,"mean_commits":6.333333333333333,"dds":0.368421052631579,"last_synced_commit":"41e85377842ad30c1b57d079a51146f8c3503ce1"},"previous_names":["spaceml-org/starcop"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/spaceml-org/STARCOP","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spaceml-org%2FSTARCOP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spaceml-org%2FSTARCOP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spaceml-org%2FSTARCOP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spaceml-org%2FSTARCOP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/spaceml-org","download_url":"https://codeload.github.com/spaceml-org/STARCOP/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spaceml-org%2FSTARCOP/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31761996,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T15:25:13.801Z","status":"ssl_error","status_checked_at":"2026-04-13T15:25:09.162Z","response_time":93,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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"}},"owner":{"login":"spaceml-org","name":"SpaceML","uuid":"75035593","kind":"organization","description":"","email":null,"website":"spaceml.org","location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/75035593?v=4","repositories_count":19,"last_synced_at":"2023-03-08T22:00:19.530Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/spaceml-org","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-18T11:56:35.287Z","updated_at":"2023-03-08T22:00:19.563Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/spaceml-org","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/spaceml-org/repositories"},"packages":[],"commits":{"id":1449999,"full_name":"spaceml-org/starcop","default_branch":"main","total_commits":26,"total_committers":3,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":8.666666666666666,"dds":0.42307692307692313,"past_year_total_commits":2,"past_year_total_committers":1,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":2.0,"past_year_dds":0.0,"last_synced_at":"2026-04-11T16:01:22.077Z","last_synced_commit":"c4789268a3fa0395f92357429052f6f5fc748acb","created_at":"2023-11-19T00:07:37.264Z","updated_at":"2026-04-11T16:01:18.503Z","committers":[{"name":"Vit Ruzicka","email":"previtus@gmail.com","login":"previtus","count":15},{"name":"Gonzalo Mateo Garcia","email":"gonzalo.mateogarcia@un.org","login":null,"count":7},{"name":"Gonzalo Mateo García","email":"gonzmg88@gmail.com","login":"gonzmg88","count":4}],"past_year_committers":[{"name":"Gonzalo Mateo Garcia","email":"gonzalo.mateogarcia@un.org","login":null,"count":2}],"commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/spaceml-org%2Fstarcop/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-04-13T00:00:06.408Z","repositories_count":6212933,"commits_count":903846857,"contributors_count":34933085,"owners_count":1144075,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"spaceml-org/starcop","html_url":"https://github.com/spaceml-org/starcop","last_synced_at":"2026-04-01T11:00:25.009Z","status":"error","issues_count":7,"pull_requests_count":1,"avg_time_to_close_issue":2917777.6,"avg_time_to_close_pull_request":490440.0,"issues_closed_count":5,"pull_requests_closed_count":1,"pull_request_authors_count":1,"issue_authors_count":6,"avg_comments_per_issue":0.8571428571428571,"avg_comments_per_pull_request":0.0,"merged_pull_requests_count":1,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":3,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":4084.0,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":1,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":3,"past_year_avg_comments_per_issue":0.0,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2023-11-19T00:07:37.548Z","updated_at":"2026-04-01T11:00:25.010Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/spaceml-org%2Fstarcop","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/spaceml-org%2Fstarcop/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":7},"pull_request_author_associations_count":{"CONTRIBUTOR":1},"issue_authors":{"yaoyuan10475":2,"heyref":1,"1750585724":1,"klaraklycke":1,"shreeyut1905":1,"huang-2":1},"pull_request_authors":{"gonzmg88":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-04-09T00:00:10.509Z","repositories_count":14207162,"issues_count":34660469,"pull_requests_count":113258760,"authors_count":11232439,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{"NONE":1},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{"shreeyut1905":1},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"ForkEvent":7,"IssuesEvent":5,"WatchEvent":19,"IssueCommentEvent":1,"PushEvent":4},"last_year":{"ForkEvent":4,"IssuesEvent":1,"WatchEvent":10,"PushEvent":2}},"keywords":["aviris","aviris-ng","emit","hyperspectral","hyperspectral-datasets","machine-learning","methane","methane-detection"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2023-11-17T12:50:34.926Z","updated_at":"2023-11-17T12:50:34.926Z","repository_link":"https://github.com/spaceml-org/STARCOP/blob/main/requirements.txt","dependencies":[{"id":14556698234,"package_name":"fsspec","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698235,"package_name":"gcsfs","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698236,"package_name":"torch","ecosystem":"pypi","requirements":"==1.13.1","direct":true,"kind":"runtime","optional":false},{"id":14556698237,"package_name":"pytorch-lightning","ecosystem":"pypi","requirements":"==1.6.4","direct":true,"kind":"runtime","optional":false},{"id":14556698238,"package_name":"torchmetrics","ecosystem":"pypi","requirements":"==0.10.0","direct":true,"kind":"runtime","optional":false},{"id":14556698239,"package_name":"omegaconf","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698240,"package_name":"kornia","ecosystem":"pypi","requirements":"==0.6.7","direct":true,"kind":"runtime","optional":false},{"id":14556698241,"package_name":"wandb","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698242,"package_name":"segmentation_models_pytorch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698243,"package_name":"hydra-core","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698244,"package_name":"ipython","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698246,"package_name":"rasterio","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698248,"package_name":"geopandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698251,"package_name":"ipykernel","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698253,"package_name":"matplotlib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698256,"package_name":"scikit-image","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698257,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14556698258,"package_name":"wandb","ecosystem":"pypi","requirements":"==0.13.3","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements_package.txt","sha":null,"kind":"manifest","created_at":"2023-12-11T10:40:56.357Z","updated_at":"2023-12-11T10:40:56.357Z","repository_link":"https://github.com/spaceml-org/STARCOP/blob/main/requirements_package.txt","dependencies":[{"id":15024329097,"package_name":"fsspec","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329098,"package_name":"gcsfs","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329099,"package_name":"torch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329100,"package_name":"pytorch-lightning","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329101,"package_name":"torchmetrics","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329102,"package_name":"omegaconf","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329103,"package_name":"kornia","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329104,"package_name":"wandb","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329105,"package_name":"segmentation_models_pytorch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329106,"package_name":"hydra-core","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329107,"package_name":"ipython","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329108,"package_name":"rasterio","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329109,"package_name":"geopandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329110,"package_name":"ipykernel","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329111,"package_name":"matplotlib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329112,"package_name":"scikit-image","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329113,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":15024329114,"package_name":"georeader-spaceml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2023-12-11T10:40:57.867Z","updated_at":"2023-12-11T10:40:57.867Z","repository_link":"https://github.com/spaceml-org/STARCOP/blob/main/setup.py","dependencies":[]}],"score":5.347107530717469,"created_at":"2023-11-19T00:06:05.652Z","updated_at":"2026-04-13T17:01:14.769Z","avatar_url":"https://github.com/spaceml-org.png","language":"Jupyter Notebook","category":"Emissions","sub_category":"Emission Observation and Modeling","monthly_downloads":0,"total_dependent_repos":0,"total_dependent_packages":0,"readme":"# STARCOP\n\n\u003ctable\u003e\n\u003ctr\u003e\n  \u003ctd width=\"100%\"\u003e\u003cimg src=\"_illustrations/STARCOP_banner.jpg\" alt=\"STARCOP banner\" width=\"100%\"\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n  \u003ctd\u003e\n    \u003cb\u003eThe STARCOP system\u003c/b\u003e\u003cbr\u003e\n    \u003cem\u003eWe introduce the STARCOP system, a lightweight model for methane plume detection in hyperspectral (AVIRIS-NG and EMIT) and multispectral (WorldView-3) data. We show that the proposed methods outperforms baseline approaches (ratio products for multispectral and matched filter approaches for hyperspectral data). Finally we release the full annotated training and evaluation dataset of methane plume events events. Project conducted as part of the ESA Cognitive Cloud Computing in Space (3CS) initiative with \u003ca href=\"https://trillium.tech/starcop\"\u003eTrillium Technologies\u003c/a\u003e.\n    \u003c/em\u003e\n\u003c/td\u003e  \n\u003c/tr\u003e\u003c/table\u003e\n\n\u003cp align=\"center\"\u003e\n    \n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://www.nature.com/articles/s41598-023-44918-6\"\u003eNature Scientific Reports Paper 2023\u003c/a\u003e •\n  \u003ca href=\"https://www.cs.ox.ac.uk/news/2218-full.html\"\u003eOxford Department of Computer Science news\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://events.ecmwf.int/event/304/contributions/3628/attachments/2152/3811/ECMWf-ESA-ML_Ruzicka.pdf\"\u003eslides \u003c/a\u003e \u0026\n  \u003ca href=\"https://vimeo.com/771105606/c1cddccabb\"\u003evideo\u003c/a\u003e from ECMWF–ESA workshop 2022 •\n  \u003ca href=\"https://colab.research.google.com/github/spaceml-org/STARCOP/blob/master/notebooks/model_demos_AVIRIS.ipynb\"\u003eQuick Demo with AVIRIS \u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" height=16px\u003e\u003c/a\u003e •\n  \u003ca href=\"https://huggingface.co/isp-uv-es/starcop\"\u003e Trained models🤗 \u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n## Semantic Segmentation of Methane Plumes with Hyperspectral ML Models\n\n\u003cdetails\u003e\n  \u003csummary\u003e\u003cb\u003eAbstract\u003c/b\u003e\u003c/summary\u003e\nMethane is the second most important greenhouse gas contributor to climate change; at the same time its reduction has been denoted as one of the fastest pathways to preventing temperature growth due to its short atmospheric lifetime. In particular, the mitigation of active point-sources associated with the fossil fuel industry has a strong and cost-effective mitigation potential. Detection of methane plumes in remote sensing data is possible, but the existing approaches exhibit high false positive rates and need manual intervention. Machine learning research in this area is limited due to the lack of large real-world annotated datasets. In this work, we are publicly releasing a machine learning ready dataset with manually refined annotation of methane plumes. We present labelled hyperspectral data from the AVIRIS-NG sensor and provide simulated multispectral WorldView-3 views of the same data to allow for model benchmarking across hyperspectral and multispectral sensors. We propose sensor agnostic machine learning architectures, using classical methane enhancement products as input features. Our HyperSTARCOP model outperforms strong matched filter baseline by over 25% in F1 score, while reducing its false positive rate per classified tile by over 41.83%. Additionally, we demonstrate zero-shot generalisation of our trained model on data from the EMIT hyperspectral instrument, despite the differences in the spectral and spatial resolution between the two sensors: in an annotated subset of EMIT images HyperSTARCOP achieves a 40% gain in F1 score over the baseline.\n\u003c/details\u003e\n\n\n\n### Dataset\n\nThe full annotated dataset used for training and evaluation is \u003ca href=\"https://doi.org/10.5281/zenodo.7863343\"\u003ehosted on Zenodo\u003c/a\u003e. For easier access to the data for the demos, a smaller subsets are also hosted on Google Drive: \u003ca href=\"https://drive.google.com/uc?id=1TwtSVpbvGd-lWfIjQrw0i4LqkiX2EuHq\"\u003eevaluation dataset\u003c/a\u003e and \u003ca href=\"https://drive.google.com/uc?id=1C4ZHvT1ZPKVMFGmqcV12Aozs8Uv_DIxD\"\u003esubset of the training dataset, including only strong plumes\u003c/a\u003e. \nWe provide selected AVIRIS-NG hyperspectral bands, computed methane enhancement products and simulated multispectral views of the data from WorldView-3. For more details see the paper.\n\n**All bands:** If you'd like to use more AVIRIS-NG bands, please contact us for instructions on downloading the full data (a preview of the formatting in a mini dataset is also available \u003ca href=\"https://huggingface.co/datasets/previtus/starcop_allbands_mini\"\u003ehere\u003c/a\u003e).\n\nFor dataset inspection use the prepared \u003ca href=\"https://colab.research.google.com/github/spaceml-org/STARCOP/blob/master/notebooks/dataset_exploration.ipynb\"\u003eColab Dataset Exploration demo \u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" height=16px\u003e\u003c/a\u003e.\n\n\n### Code examples\n\n**Install**\n\n```bash\nconda create -c conda-forge -n starcop_env python=3.10 mamba\nconda activate starcop_env\n\npip install git+https://github.com/spaceml-org/STARCOP.git\n```\n\n**Inference**\n\nTo start using our model for inference, you can check the demo with AVIRIS data in \u003ca href=\"https://colab.research.google.com/github/spaceml-org/STARCOP/blob/master/notebooks/model_demos_AVIRIS.ipynb\"\u003e Colab Inference on AVIRIS \u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" height=16px\u003e\u003c/a\u003e, or with EMIT data in \u003ca href=\"https://colab.research.google.com/github/spaceml-org/STARCOP/blob/master/notebooks/inference_on_raw_EMIT_nc_file.ipynb\"\u003e Colab Inference on EMIT \u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" height=16px\u003e\u003c/a\u003e. These download our annotated datasets and demonstrate the performance of our pre-trained models.\n\n\u003ctable\u003e\n\u003ctr\u003e\n  \u003ctd width=\"100%\"\u003e\u003cimg src=\"_illustrations/Figure1_EMIT.jpg\" alt=\"Detections in EMIT\" width=\"100%\"\u003e\u003cbr\u003e\n  Selected predictions of our model detecting methane leaks using the data from the EMIT sensor deployed on board of the International Space Station. Showing detections from around the world with data from 2022-2023. Image credit: Open source EMIT data (NASA) processed by Vít Růžička.\n  \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n  \u003ctd width=\"100%\"\u003e\u003cimg src=\"_illustrations/Figure2_AVIRIS.jpg\" alt=\"Detections in AVIRIS\" width=\"100%\"\u003e\u003cbr\u003e\n  Selected predictions of our model detecting methane leaks using the data from the AVIRIS aerial mission flown above the Four Corners area in the USA in 2019. Plume emission rates are used from the source annotations. Image credit: Open source AVIRIS data (NASA) processed by Vít Růžička.\n  \u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\nOur trained models are stored in Hugging Face🤗 at [isp-uv-es/starcop](https://huggingface.co/isp-uv-es/starcop).\n\n**Training**\n\nTo reproduce the same training process as reported in the paper, you will need to download the whole STARCOP dataset from Zenodo first, and prepare the coding environment.\n\n```bash\n# Check possible parameters with:\n!python3 -m scripts.train --help\n\n# Or run the prepared training script used for the paper models (remember to download and adjust the paths to the training datasets)\n./bash/bash_train_example.sh\n```\n\n**Minimal training example**\n\nIf you install the environment using the commands above, this should work as a minimal training example (which includes first getting the data):\n\n```bash\ngdown https://drive.google.com/uc?id=1Qw96Drmk2jzBYSED0YPEUyuc2DnBechl -O STARCOP_mini.zip\nunzip -q STARCOP_mini.zip\n# The train script will expect the test dataset in the \"test.csv\" - so here in this small demo we just place the small subset there instead:\ncp STARCOP_mini/test_mini10.csv STARCOP_mini/test.csv\n\npython -m scripts.train dataset.input_products=[\"mag1c\",\"TOA_AVIRIS_640nm\",\"TOA_AVIRIS_550nm\",\"TOA_AVIRIS_460nm\"] model.model_type='unet_semseg' model.pos_weight=1 experiment_name=\"HyperSTARCOP_magic_rgb_DEMO\" dataloader.num_workers=4 dataset.use_weight_loss=True training.val_check_interval=0.5 training.max_epochs=5 products_plot=[\"rgb_aviris\",\"mag1c\",\"label\",\"pred\",\"differences\"] dataset.weight_sampling=True dataset.train_csv=\"train_mini10.csv\" dataset.root_folder=PATH_TO/STARCOP_mini wandb.wandb_entity=\"YOUR_ENTITY\" wandb.wandb_project=\"starcop_project\"\n```\n\n## Citation\nIf you find the STARCOP models or dataset useful in your research, please consider citing our work. \n\n```\n@article{ruzicka_starcop_2023,\n\ttitle = {Semantic segmentation of methane plumes with hyperspectral machine learning models},\n\tvolume = {13},\n\tissn = {2045-2322},\n\turl = {https://www.nature.com/articles/s41598-023-44918-6},\n\tdoi = {10.1038/s41598-023-44918-6},\n\tnumber = {1},\n\tjournal = {Scientific Reports},\n        author={Růžička, Vít and Mateo-Garcia, Gonzalo and G{\\'o}mez-Chova, Luis and Vaughan, Anna and Guanter, Luis and Markham, Andrew},\n\tmonth = nov,\n\tyear = {2023},\n\tpages = {19999}\n}\n```\n## Acknowledgments\n\nThis research has been funded by ESA Cognitive Cloud Computing in Space initiative project number STARCOP I-2022-00380. It has been supported by the DEEPCLOUD project (PID2019-109026RB-I00) funded by the Spanish Ministry of Science and Innovation (MCIN/AEI/10.13039/501100011033) and the European Union (NextGenerationEU).\n","funding_links":[],"readme_doi_urls":["https://doi.org/10.5281/zenodo.7863343"],"works":{"https://doi.org/10.5281/zenodo.7863343":null},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://ost.ecosyste.ms/api/v1/projects/139790","html_url":"https://ost.ecosyste.ms/projects/139790"}