{"id":538,"name":"MARIDA","description":"A marine debris-oriented dataset on Sentinel-2 satellite images.","url":"https://github.com/marine-debris/marine-debris.github.io","last_synced_at":"2026-04-28T00:30:38.707Z","repository":{"id":43085945,"uuid":"391733217","full_name":"marine-debris/marine-debris.github.io","owner":"marine-debris","description":"Quick Start Guide for MARIDA (Marine Debris Archive)","archived":false,"fork":false,"pushed_at":"2023-12-28T16:41:19.000Z","size":10514,"stargazers_count":80,"open_issues_count":2,"forks_count":18,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-04-06T14:04:02.541Z","etag":null,"topics":["classification","deep-learning","marine-litter","semantic-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/marine-debris.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,"governance":null,"roadmap":null,"authors":null}},"created_at":"2021-08-01T20:38:30.000Z","updated_at":"2026-03-30T23:42:30.000Z","dependencies_parsed_at":"2024-01-08T00:52:45.432Z","dependency_job_id":"818b7a8c-c65f-4843-a522-ac29191c8b16","html_url":"https://github.com/marine-debris/marine-debris.github.io","commit_stats":{"total_commits":23,"total_committers":2,"mean_commits":11.5,"dds":0.04347826086956519,"last_synced_commit":"8de83a3394edfbe867d9fa825439666369ec6282"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/marine-debris/marine-debris.github.io","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marine-debris%2Fmarine-debris.github.io","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marine-debris%2Fmarine-debris.github.io/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marine-debris%2Fmarine-debris.github.io/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marine-debris%2Fmarine-debris.github.io/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/marine-debris","download_url":"https://codeload.github.com/marine-debris/marine-debris.github.io/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marine-debris%2Fmarine-debris.github.io/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31560476,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-08T14:31:17.711Z","status":"ssl_error","status_checked_at":"2026-04-08T14:31:17.202Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":null,"packages":[],"commits":{"id":1254242,"full_name":"marine-debris/marine-debris.github.io","default_branch":"main","total_commits":23,"total_committers":2,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":11.5,"dds":0.04347826086956519,"past_year_total_commits":0,"past_year_total_committers":0,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":0.0,"past_year_dds":0.0,"last_synced_at":"2026-04-06T14:02:46.417Z","last_synced_commit":"8de83a3394edfbe867d9fa825439666369ec6282","created_at":"2023-03-27T11:00:59.504Z","updated_at":"2026-04-06T14:02:45.093Z","committers":[{"name":"Ioannis Kakogeorgiou","email":"gkakogeorgiou@gmail.com","login":"gkakogeorgiou","count":22},{"name":"Kendall Smith","email":"smith.kendall.lee@gmail.com","login":"KennSmithDS","count":1}],"past_year_committers":[],"commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/marine-debris%2Fmarine-debris.github.io/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-04-08T00:00:24.542Z","repositories_count":6212203,"commits_count":914906080,"contributors_count":35345446,"owners_count":1143114,"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":"marine-debris/marine-debris.github.io","html_url":"https://github.com/marine-debris/marine-debris.github.io","last_synced_at":"2025-09-16T17:37:38.593Z","status":"active","issues_count":8,"pull_requests_count":1,"avg_time_to_close_issue":4614589.666666667,"avg_time_to_close_pull_request":229708.0,"issues_closed_count":6,"pull_requests_closed_count":1,"pull_request_authors_count":1,"issue_authors_count":7,"avg_comments_per_issue":2.625,"avg_comments_per_pull_request":1.0,"merged_pull_requests_count":1,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":2,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":2,"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":"2023-05-09T10:35:44.240Z","updated_at":"2025-09-16T17:37:38.593Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/marine-debris%2Fmarine-debris.github.io","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/marine-debris%2Fmarine-debris.github.io/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":8},"pull_request_author_associations_count":{"CONTRIBUTOR":1},"issue_authors":{"EmanuelCastanho":2,"giustiandrea91":1,"mohammadali-67":1,"ipereira-uib":1,"QasimKhan5x":1,"Zhanarik":1,"MahitNandan":1},"pull_request_authors":{"KennSmithDS":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-04-08T00:00:09.900Z","repositories_count":14147583,"issues_count":34546263,"pull_requests_count":112868491,"authors_count":11230090,"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":{"ipereira-uib":1},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"ForkEvent":6,"WatchEvent":31,"IssueCommentEvent":1},"last_year":{"ForkEvent":1,"WatchEvent":9,"IssueCommentEvent":1}},"keywords":["classification","deep-learning","marine-litter","semantic-segmentation"],"dependencies":[{"ecosystem":"pypi","filepath":"environment.yml","sha":null,"kind":"manifest","created_at":"2024-01-08T00:52:44.080Z","updated_at":"2024-01-08T00:52:44.080Z","repository_link":"https://github.com/marine-debris/marine-debris.github.io/blob/main/environment.yml","dependencies":[]}],"score":5.099866427824199,"created_at":"2023-09-11T11:54:35.044Z","updated_at":"2026-04-28T00:30:38.712Z","avatar_url":"https://github.com/marine-debris.png","language":"Python","category":"Industrial Ecology","sub_category":"Circular Economy and Waste","monthly_downloads":0,"total_dependent_repos":0,"total_dependent_packages":0,"readme":"![Marine Debris Archive Logo](./docs/marida_trans.png)\r\n\r\nMarine Debris Archive (MARIDA) is a marine debris-oriented dataset on Sentinel-2 satellite images. \r\nIt also includes various sea features that co-exist.\r\nMARIDA is primarily focused on the weakly supervised pixel-level semantic segmentation task.\r\nThis repository hosts the basic tools for the extraction of spectral signatures\r\n as well as the code for the reproduction of the baseline models.\r\n \r\nIf you find this repository useful, please consider giving a star :star: and citation:\r\n \u003e Kikaki K, Kakogeorgiou I, Mikeli P, Raitsos DE, Karantzalos K (2022) MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data. PLoS ONE 17(1): e0262247. https://doi.org/10.1371/journal.pone.0262247\r\n\r\nIn order to download MARIDA go to https://doi.org/10.5281/zenodo.5151941.\r\n\r\nAlternatively, MARIDA can be downloaded from the [Radiant MLHub](https://mlhub.earth/data/marida_v1). The `tar.gz` archive file downloaded from this source includes the STAC catalog associated with this dataset.\r\n\r\n\r\n## Contents\r\n\r\n- [Installation](#installation)\r\n\t- [Installation Requirements](#installation-requirements)\r\n\t- [Installation Guide](#installation-guide)\r\n- [Getting Started](#getting-started)\r\n\t- [Dataset Structure](#dataset-structure)\r\n\t- [Spectral Signatures Extraction](#spectral-signatures-extraction)\r\n\t- [Weakly Supervised Pixel-Level Semantic Segmentation](#weakly-supervised-pixel-Level-semantic-segmentation)\r\n\t\t- [Unet](#unet)\r\n\t\t- [Random Forest](#random-forest)\r\n\t- [Multi-label Classification](#multi-label-classification)\r\n\t\t- [ResNet](#resnet)\r\n- [MARIDA - Exploratory Analysis](https://marine-debris.github.io/)\r\n- [Talks and Papers](#talks-and-papers)\r\n\r\n\r\n## Installation\r\n\r\n### Installation Requirements\r\n- python == 3.7.10\r\n- pytorch == 1.7 \r\n- cudatoolkit == 11.0 (For GPU usage, compute capability \u003e= 3.5)\r\n- gdal == 2.3.3\r\n- rasterio == 1.0.21\r\n- scikit-learn == 0.24.2\r\n- numpy == 1.20.2\r\n- tensorboard == 1.15\r\n- torchvision == 0.8.0\r\n- scikit-image == 0.18.1\r\n- pandas == 1.2.4\r\n- pytables == 3.6.1\r\n- tqdm == 4.59.0\r\n\r\n\r\n### Installation Guide\r\n\r\nThe requirements are easily installed via\r\n[Anaconda](https://www.anaconda.com/distribution/#download-section) (recommended):\r\n```bash\r\nconda env create -f environment.yml\r\n```\r\n\u003e If the following error occurred: InvalidVersionSpecError: Invalid version spec: =2.7 \r\n\u003e\r\n\u003e Run: conda update conda\r\n\r\nAfter the installation is completed, activate the environment:\r\n```bash\r\nconda activate marida\r\n```\r\n\r\n## Getting Started\r\n\r\n### Dataset Structure\r\n\r\nIn order to train or test the models, download [MARIDA](https://doi.org/10.5281/zenodo.5151941)\r\nand extract it in the `data/` folder. The final structure should be:\r\n\r\n    .\r\n    ├── ...\r\n    ├── data                                     # Main Dataset folder\r\n    │   ├── patches                              # Folder with patches Structured by Unique Dates and S2 Tiles  \r\n\t│   │    ├── S2_DATE_TILE                    # Unique Date\r\n\t│   │    │    ├── S2_DATE_TILE_CROP.tif      # Unique 256 x 256 Patch \r\n\t│   │    │    ├── S2_DATE_TILE_CROP_cl.tif   # 256 x 256 Classification Mask for Semantic Segmentation Task\r\n\t│   │    │    └── S2_DATE_TILE_CROP_conf.tif # 256 x 256 Annotator Confidence Level Mask\r\n\t│   │    └──  ...                        \r\n    │   ├── splits                               # Train/Val/Test split Folder (train_X.txt, val_X.txt, test_X.txt) \r\n    │   └── labels_mapping.txt                   # Mapping between Unique 256 x 256 Patch and labels for Multi-label Classification Task\r\n\r\n\r\nThe mapping in S2_DATA_TILE_CROP_cl between Digital Numbers and Classes is:\r\n\r\n```yaml\r\n1: 'Marine Debris',\r\n2: 'Dense Sargassum',\r\n3: 'Sparse Sargassum',\r\n4: 'Natural Organic Material',\r\n5: 'Ship',\r\n6: 'Clouds',\r\n7: 'Marine Water',\r\n8: 'Sediment-Laden Water',\r\n9: 'Foam',\r\n10: 'Turbid Water',\r\n11: 'Shallow Water',\r\n12: 'Waves',\r\n13: 'Cloud Shadows',\r\n14: 'Wakes',\r\n15: 'Mixed Water'\r\n```\r\n\r\nFor the confidence level mask or other usefull mappings go to utils/assets.py\r\n\r\nAlso, in order to easily visualize the RGB composite of the S2_DATE_TILE_CROP patches via [QGIS](https://qgis.org/en/site/index.html),\r\nyou can use the `utils/qgis_color_patch_rgb.qml` file.\r\n\r\n### Spectral Signatures Extraction\r\n\r\nFor the extraction of the spectal signature of each annotated pixel and\r\nits storage in a HDF5 Table file (DataFrame-like processing) run the following commands below. \r\nThe output `data/dataset.h5` can be used for the spectral analysis of the dataset.\r\nAlso, this stage is required for the Random Forest training (press [here](#random-forest)). \r\nNote that this is not required for the Unet training. This procedure lasts approximately ~10 minutes.\r\n\r\n```bash\r\npython utils/spectral_extraction.py\r\n```\r\n\r\nAlternatively, you can download the `dataset.h5` file from [here](https://pithos.okeanos.grnet.gr/public/sbT8ASX0HINAdx4tmKCg27) and put it in the `data` folder.\r\nFinally, in order to load the `dataset.h5` with Pandas, run in a python cell the following:\r\n\r\n```python\r\nimport pandas as pd\r\n\r\nhdf = pd.HDFStore('./data/dataset.h5', mode = 'r')\r\n\r\ndf_train = hdf.select('train')\r\ndf_val = hdf.select('val')\r\ndf_test = hdf.select('test')\r\n\r\nhdf.close()\r\n```\r\n\r\n### Weakly Supervised Pixel-Level Semantic Segmentation\r\n\r\n#### Unet\r\n\r\n**Unet training**\r\n\r\nSpectral Signatures Extraction in not required for this procedure.\r\nFor training in the \"train\" set and evaluation in \"val\" set with the proposed parameters, run:\r\n\r\n```bash\r\ncd semantic_segmentation/unet\r\npython train.py\r\n```\r\n\r\nWhile training, in order to see the loss status and various metrics via tensorboard, run in a different terminal \r\nthe following command and then go to `localhost:6006` with your browser:\r\n\r\n```bash\r\ntensorboard --logdir logs/tsboard_segm\r\n```\r\n\r\nThe `train.py` also supports the following argument flags:\r\n\r\n```bash\r\n    # Basic parameters\r\n    --agg_to_water \"Aggregate Mixed Water, Wakes, Cloud Shadows, Waves with Marine Water (True or False)\"\r\n    --mode \"Select between 'train' or 'test'\"\r\n    --epochs \"Number of epochs to run\"\r\n    --batch \"Batch size\"\r\n    --resume_from_epoch \"Load model from previous epoch (To continue the training)\"\r\n    \r\n    # Unet\r\n    --input_channels \"The number of input bands\"\r\n    --output_channels \"The number of output classes\"\r\n    --hidden_channels \"The number of hidden features\"\r\n\r\n    # Optimization\r\n    --weight_param \"Weighting parameter for Loss Function\"\r\n    --lr \"Learning rate for adam\"\r\n    --decay \"Learning rate decay for adam\"\r\n    --reduce_lr_on_plateau \"Reduce learning rate when val loss no decrease (0 or 1)\"\r\n    --lr_steps \"Specify the steps that the lr will be reduced\"\r\n\r\n    # Evaluation/Checkpointing\r\n    --checkpoint_path \"The folder to save checkpoints into.\"\r\n    --eval_every \"How frequently to run evaluation (epochs)\"\r\n\r\n    # misc\r\n    --num_workers \"How many cpus for loading data (0 is the main process)\"\r\n    --pin_memory \"Use pinned memory or not\"\r\n    --prefetch_factor \"Number of sample loaded in advance by each worker\"\r\n    --persistent_workers \"This allows to maintain the workers Dataset instances alive\"\r\n    --tensorboard \"Name for tensorboard run\"\r\n```\r\n\r\n**Unet evaluation**\r\n\r\nRun the following commands in order to produce the Confusion Matrix in stdout and `logs/evaluation_unet.log`,\r\n as well as to produce the predicted masks from the test set in `data/predicted_unet/` folder:\r\n\r\n```bash\r\ncd semantic_segmentation/unet\r\npython evaluation.py\r\n```\r\n\r\nIn order to easily visualize the predicted masks via [QGIS](https://qgis.org/en/site/index.html),\r\nyou can use the `utils/qgis_color_mask_mapping.qml` file.\r\n\r\nTo download the pretrained Unet model on MARIDA press [here](https://pithos.okeanos.grnet.gr/public/lxh8hL4zvuSKds2BdVnMd2). \r\nThen, you should put these items in the `semantic_segmentation/unet/trained_models/` folder.\r\n\r\n#### Random Forest\r\n\r\nIn our baseline setup we trained a random forest classifier on Spectral Signatures,\r\nproduced Spectral Indices (SI) and extracted Gray-Level Co-occurrence Matrix (GLCM) texture features.\r\nThus, this process requires the Spectral Signatures Extraction i.e., the `data/dataset.h5` [file](#spectral-signatures-extraction). Also, it requires the `dataset_si.h5` and `dataset_glcm.h5` for SI and GLCM features,\r\nrespectively.\r\n\r\n1) For the extraction of stacked SI patches (in `data/indices/`) run:\r\n\r\n```bash\r\ncd semantic_segmentation/random_forest\r\npython engineering_patches.py\r\n```\r\n\r\nThen, in order to produce the `dataset_si.h5` run:\r\n\r\n```bash\r\npython utils/spectral_extraction.py --type indices\r\n```\r\n\r\n2) For the stacked GLCM patches (in `data/texture/`) run (approximately ~ 110 mins):\r\n\r\n```bash\r\npython engineering_patches.py --type texture\r\n```\r\n\r\nSimilarly, in order to produce the `dataset_glcm.h5` run:\r\n\r\n```bash\r\npython utils/spectral_extraction.py --type texture\r\n```\r\n\r\n Alternatively, you can download the `indices/` and `texture/` folders as well as the `dataset_si.h5` and `dataset_glcm.h5` files from [here](https://pithos.okeanos.grnet.gr/public/7Xm6x2uSBHTknNv7vaqgS6). \r\nThen, you should put these items in the `data` folder.\r\n\r\n**Random Forest training and evaluation**\r\n\r\nFor training in \"train\" set and final evaluation in \"test\" set, run the following commands.\r\nNote that the results will appear in stdout and `logs/evaluation_rf.log`, and the predicted \r\nmasks in `data/predicted_rf/` folder.\r\n\r\n```bash\r\ncd semantic_segmentation\\random_forest\r\npython train_eval.py\r\n```\r\n\r\nThe `train_eval.py` supports the `--agg_to_water` argument for \r\nthe aggregation of various classes to form the Water Super Class (The default setup):\r\n\r\n```bash\r\npython train_eval.py --agg_to_water ['\"Mixed Water\"','\"Wakes\"','\"Cloud Shadows\"','\"Waves\"']\r\n```\r\n\r\n### Multi-label Classification\r\n\r\nThe weakly-supervised multi-label classification task is an incomplete multi-label\r\nassignment problem. Specifically, the assigned labels are definitely positive (assigned as 1),\r\n while the absent labels (assigned as 0) are not necessarily negative. The assigned labels\r\n per patch can be found in `data/labels_mapping.txt`\r\n\r\n#### ResNet\r\n\r\n**ResNet training**\r\n\r\nFor training in \"train\" set and evaluation in \"val\" set, run:\r\n\r\n```bash\r\ncd multi-label/resnet\r\npython train.py\r\n```\r\n\r\nSimilarly to U-Net training, you can use tensorboard thought `localhost:6006` \r\nto visualize the training process:\r\n\r\n```\r\ntensorboard --logdir logs/tsboard_multilabel\r\n```\r\n\r\n**ResNet evaluation**\r\n\r\nRun the following commands in order to produce the accuracy scores and the Confusion Matrix in stdout \r\nand `logs/evaluation_resnet.log`, as well as to produce the predictions for each patch from the test \r\nset in `data/predicted_labels_mapping.txt`:\r\n\r\n```bash\r\npython evaluation.py\r\n```\r\n\r\nTo download the pretrained ResNet model on MARIDA press [here](https://pithos.okeanos.grnet.gr/public/lxh8hL4zvuSKds2BdVnMd2). \r\nThen, you should put these items in the `multi-label/resnet/trained_models/` folder.\r\n\r\n## Presentations\r\n[Kikaki A, Kakogeorgiou I, Mikeli P, Raitsos DE, Karantzalos K. Detecting and Classifying Marine Plastic Debris from high-resolution multispectral satellite data.](https://doi.org/10.5194/egusphere-egu21-15243)\r\n\r\n## License\r\nThis project is licensed under the MIT License.\r\n","funding_links":[],"readme_doi_urls":["https://doi.org/10.1371/journal.pone.0262247","https://doi.org/10.5281/zenodo.5151941","https://doi.org/10.5194/egusphere-egu21-15243"],"works":{"https://doi.org/10.1371/journal.pone.0262247":{"id":"https://openalex.org/W4205835860","doi":"https://doi.org/10.1371/journal.pone.0262247","title":"MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data","display_name":"MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data","publication_year":2022,"publication_date":"2022-01-07","ids":{"openalex":"https://openalex.org/W4205835860","doi":"https://doi.org/10.1371/journal.pone.0262247","pmid":"https://pubmed.ncbi.nlm.nih.gov/34995337"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0262247","pdf_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0262247\u0026type=printable","source":{"id":"https://openalex.org/S202381698","display_name":"PLOS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0262247\u0026type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019605722","display_name":"Aikaterini Kikaki","orcid":"https://orcid.org/0000-0002-2618-3074"},"institutions":[{"id":"https://openalex.org/I4210131924","display_name":"Hellenic Centre for Marine Research","ror":"https://ror.org/038kffh84","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210131924"]},{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Katerina Kikaki","raw_affiliation_string":"Institute of Oceanography, Hellenic Centre for Marine Research, Athens, Anavyssos, Greece; Remote Sensing Laboratory, National Technical University of Athens, Athens, Zografou, Greece","raw_affiliation_strings":["Institute of Oceanography, Hellenic Centre for Marine Research, Athens, Anavyssos, Greece","Remote Sensing Laboratory, National Technical University of Athens, Athens, Zografou, Greece"]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038352333","display_name":"Ioannis Kakogeorgiou","orcid":"https://orcid.org/0000-0001-5200-2620"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioannis Kakogeorgiou","raw_affiliation_string":"Remote Sensing Laboratory, National Technical University of Athens, Athens, Zografou, Greece","raw_affiliation_strings":["Remote Sensing Laboratory, National Technical University of Athens, Athens, Zografou, Greece"]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089042649","display_name":"Paraskevi Mikeli","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Paraskevi Mikeli","raw_affiliation_string":"Remote Sensing Laboratory, National Technical University of Athens, Athens, Zografou, Greece","raw_affiliation_strings":["Remote Sensing Laboratory, National Technical University of Athens, Athens, Zografou, Greece"]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082977120","display_name":"Dionysios Ε. Raitsos","orcid":"https://orcid.org/0000-0002-6714-2180"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dionysios E. Raitsos","raw_affiliation_string":"Department of Biology, National and Kapodistrian University of Athens, Athens, Zografou, Greece","raw_affiliation_strings":["Department of Biology, National and Kapodistrian University of Athens, Athens, Zografou, Greece"]},{"author_position":"last","author":{"id":"https://openalex.org/A5064461457","display_name":"Κωνσταντίνος Καράντζαλος","orcid":"https://orcid.org/0000-0001-8730-6245"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication \u0026 Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Karantzalos","raw_affiliation_string":"Athena Research Center, Athens, Greece; Remote Sensing Laboratory, National Technical University of Athens, Athens, Zografou, Greece","raw_affiliation_strings":["Athena Research Center, Athens, Greece","Remote Sensing Laboratory, National Technical University of Athens, Athens, Zografou, Greece"]}],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019605722"],"corresponding_institution_ids":["https://openalex.org/I4210131924","https://openalex.org/I174458059"],"apc_list":{"value":1805,"currency":"USD","value_usd":1805,"provenance":"doaj"},"apc_paid":{"value":1805,"currency":"USD","value_usd":1805,"provenance":"doaj"},"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":27,"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"17","issue":"1","first_page":"e0262247","last_page":"e0262247"},"is_retracted":false,"is_paratext":false,"keywords":[{"keyword":"marine debris detection","score":0.7174},{"keyword":"remote sensing","score":0.4759},{"keyword":"benchmark","score":0.3133}],"concepts":[{"id":"https://openalex.org/C173163844","wikidata":"https://www.wikidata.org/wiki/Q1761440","display_name":"Multispectral image","level":2,"score":0.7774938},{"id":"https://openalex.org/C2776023875","wikidata":"https://www.wikidata.org/wiki/Q637703","display_name":"Debris","level":2,"score":0.68453014},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.67993253},{"id":"https://openalex.org/C5457282","wikidata":"https://www.wikidata.org/wiki/Q7907352","display_name":"VNIR","level":3,"score":0.5771365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.56207836},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5388261},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.48770866},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.46917444},{"id":"https://openalex.org/C2778102629","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite imagery","level":2,"score":0.4522588},{"id":"https://openalex.org/C62329434","wikidata":"https://www.wikidata.org/wiki/Q463960","display_name":"Marine debris","level":3,"score":0.41030118},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.24205565},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.22211927},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.19380644},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1610362},{"id":"https://openalex.org/C159078339","wikidata":"https://www.wikidata.org/wiki/Q959005","display_name":"Hyperspectral imaging","level":2,"score":0.13612553},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07478434},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004784","descriptor_name":"Environmental Monitoring","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019015","descriptor_name":"Geologic Sediments","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D058998","descriptor_name":"Remote Sensing Technology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014866","descriptor_name":"Waste Products","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D004784","descriptor_name":"Environmental Monitoring","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019015","descriptor_name":"Geologic Sediments","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058998","descriptor_name":"Remote Sensing Technology","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012621","descriptor_name":"Seasons","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014866","descriptor_name":"Waste Products","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0262247","pdf_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0262247\u0026type=printable","source":{"id":"https://openalex.org/S202381698","display_name":"PLOS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://doaj.org/article/96c11bdde6fc47588d45e62c40056158","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8740969","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34995337","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0262247","pdf_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0262247\u0026type=printable","source":{"id":"https://openalex.org/S202381698","display_name":"PLOS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.87}],"grants":[{"funder":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020","award_id":"863448"}],"referenced_works_count":55,"referenced_works":["https://openalex.org/W2003059629","https://openalex.org/W2010319424","https://openalex.org/W2030724333","https://openalex.org/W2037227137","https://openalex.org/W2037600639","https://openalex.org/W2044465660","https://openalex.org/W2136758825","https://openalex.org/W2194775991","https://openalex.org/W2216742482","https://openalex.org/W2422823951","https://openalex.org/W2604316091","https://openalex.org/W2746791238","https://openalex.org/W2762862468","https://openalex.org/W2767653890","https://openalex.org/W2775157412","https://openalex.org/W2786644902","https://openalex.org/W2802213413","https://openalex.org/W2810550100","https://openalex.org/W2884226222","https://openalex.org/W2889468980","https://openalex.org/W2892976510","https://openalex.org/W2895805893","https://openalex.org/W2909460473","https://openalex.org/W2911964244","https://openalex.org/W2923133959","https://openalex.org/W2953172836","https://openalex.org/W2963351448","https://openalex.org/W2969832099","https://openalex.org/W2973873733","https://openalex.org/W2981569413","https://openalex.org/W2995930197","https://openalex.org/W3001953785","https://openalex.org/W3003984144","https://openalex.org/W3017204974","https://openalex.org/W3018351936","https://openalex.org/W3024533279","https://openalex.org/W3031158544","https://openalex.org/W3037870660","https://openalex.org/W3045509105","https://openalex.org/W3055327921","https://openalex.org/W3082975392","https://openalex.org/W3091414454","https://openalex.org/W3093066926","https://openalex.org/W3094176698","https://openalex.org/W3094670705","https://openalex.org/W3094962286","https://openalex.org/W3120546273","https://openalex.org/W3123775691","https://openalex.org/W3125889112","https://openalex.org/W3134343497","https://openalex.org/W3134347438","https://openalex.org/W3147644407","https://openalex.org/W3155690422","https://openalex.org/W3170311479","https://openalex.org/W3172537970"],"related_works":["https://openalex.org/W2007071609","https://openalex.org/W2322660418","https://openalex.org/W2607562548","https://openalex.org/W2160330414","https://openalex.org/W3154225647","https://openalex.org/W2053629703","https://openalex.org/W2552044454","https://openalex.org/W2937037279","https://openalex.org/W2134877526","https://openalex.org/W3016105964"],"ngrams_url":"https://api.openalex.org/works/W4205835860/ngrams","abstract_inverted_index":{"Currently,":[0],"a":[1,30,36],"significant":[2],"amount":[3],"of":[4,48,128,163],"research":[5,156],"is":[6,53,132,149],"focused":[7],"on":[8,58,182],"detecting":[9,49],"Marine":[10,31,50,67,177],"Debris":[11,32,68,178],"and":[12,41,96,118,125,144,170,175,185],"assessing":[13],"its":[14],"spectral":[15,124,161],"behaviour":[16,162],"via":[17],"remote":[18],"sensing,":[19],"ultimately":[20],"aiming":[21],"at":[22],"new":[23],"operational":[24],"monitoring":[25],"solutions.":[26],"Here,":[27],"we":[28],"introduce":[29],"Archive":[33],"(MARIDA),":[34],"as":[35,189,191],"benchmark":[37],"dataset":[38,56,131,152],"for":[39,139],"developing":[40],"evaluating":[42],"Machine":[43],"Learning":[44],"(ML)":[45],"algorithms":[46],"capable":[47],"Debris.":[51],"MARIDA":[52,130,148],"the":[54,59,129,155,160],"first":[55],"based":[57,181],"multispectral":[60],"Sentinel-2":[61],"(S2)":[62],"satellite":[63,192],"data,":[64],"which":[65,153],"distinguishes":[66],"from":[69,104],"various":[70],"marine":[71],"features":[72,169],"that":[73],"co-exist,":[74],"including":[75],"Sargassum":[76],"macroalgae,":[77],"Ships,":[78],"Natural":[79],"Organic":[80],"Material,":[81],"Waves,":[82],"Wakes,":[83],"Foam,":[84],"dissimilar":[85],"water":[86,171],"types":[87],"(i.e.,":[88],"Clear,":[89],"Turbid":[90],"Water,":[91,93],"Sediment-Laden":[92],"Shallow":[94],"Water),":[95],"Clouds.":[97],"We":[98],"provide":[99],"annotations":[100],"(georeferenced":[101],"polygons/":[102],"pixels)":[103],"verified":[105],"plastic":[106],"debris":[107],"events":[108],"in":[109],"several":[110],"geographical":[111],"regions":[112],"globally,":[113],"during":[114],"different":[115],"seasons,":[116],"years":[117],"sea":[119,167],"state":[120,168],"conditions.":[121],"A":[122],"detailed":[123],"statistical":[126],"analysis":[127],"presented":[133],"along":[134],"with":[135],"well-established":[136],"ML":[137],"baselines":[138],"weakly":[140],"supervised":[141],"semantic":[142],"segmentation":[143],"multi-label":[145],"classification":[146],"tasks.":[147],"an":[150],"open-access":[151],"enables":[154],"community":[157],"to":[158,173],"explore":[159],"certain":[164],"floating":[165],"materials,":[166],"types,":[172],"develop":[174],"evaluate":[176],"detection":[179],"solutions":[180],"artificial":[183],"intelligence":[184],"deep":[186],"learning":[187],"architectures,":[188],"well":[190],"pre-processing":[193],"pipelines.":[194]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4205835860","counts_by_year":[{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":8}],"updated_date":"2023-12-18T05:38:57.368588","created_date":"2022-01-25"},"https://doi.org/10.5281/zenodo.5151941":null,"https://doi.org/10.5194/egusphere-egu21-15243":{"id":"https://openalex.org/W3176688224","doi":"https://doi.org/10.5194/egusphere-egu21-15243","title":"Detecting and Classifying Marine Plastic Debris from high-resolution multispectral satellite data","display_name":"Detecting and Classifying Marine Plastic Debris from high-resolution multispectral satellite data","publication_year":2021,"publication_date":"2021-03-04","ids":{"openalex":"https://openalex.org/W3176688224","doi":"https://doi.org/10.5194/egusphere-egu21-15243","mag":"3176688224"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.5194/egusphere-egu21-15243","pdf_url":null,"source":null,"license":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"article","type_crossref":"posted-content","open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019605722","display_name":"Aikaterini Kikaki","orcid":"https://orcid.org/0000-0002-2618-3074"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aikaterini Kikaki","raw_affiliation_string":"","raw_affiliation_strings":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038352333","display_name":"Ioannis Kakogeorgiou","orcid":"https://orcid.org/0000-0001-5200-2620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ioannis Kakogeorgiou","raw_affiliation_string":"","raw_affiliation_strings":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089042649","display_name":"Paraskevi Mikeli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paraskevi Mikeli","raw_affiliation_string":"","raw_affiliation_strings":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082977120","display_name":"Dionysios Ε. Raitsos","orcid":"https://orcid.org/0000-0002-6714-2180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dionysios E. Raitsos","raw_affiliation_string":"","raw_affiliation_strings":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064461457","display_name":"Κωνσταντίνος Καράντζαλος","orcid":"https://orcid.org/0000-0001-8730-6245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantinos Karantzalos","raw_affiliation_string":"","raw_affiliation_strings":[]}],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"has_fulltext":false,"cited_by_count":0,"cited_by_percentile_year":{"min":0,"max":66},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"keywords":[{"keyword":"classifying marine plastic debris","score":0.7998},{"keyword":"satellite","score":0.2596},{"keyword":"high-resolution","score":0.25}],"concepts":[{"id":"https://openalex.org/C2776023875","wikidata":"https://www.wikidata.org/wiki/Q637703","display_name":"Debris","level":2,"score":0.78736687},{"id":"https://openalex.org/C173163844","wikidata":"https://www.wikidata.org/wiki/Q1761440","display_name":"Multispectral image","level":2,"score":0.7218791},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.66286826},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.6294401},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.5839623},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.57694703},{"id":"https://openalex.org/C62329434","wikidata":"https://www.wikidata.org/wiki/Q463960","display_name":"Marine debris","level":3,"score":0.5539217},{"id":"https://openalex.org/C2778102629","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite imagery","level":2,"score":0.48050606},{"id":"https://openalex.org/C134097258","wikidata":"https://www.wikidata.org/wiki/Q1507383","display_name":"Sea surface temperature","level":2,"score":0.43807963},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.35580617},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.33319318},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2607},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.18293089},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06629652},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.5194/egusphere-egu21-15243","pdf_url":null,"source":null,"license":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.87}],"grants":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2007071609","https://openalex.org/W3016105964","https://openalex.org/W2053629703","https://openalex.org/W2552044454","https://openalex.org/W2937037279","https://openalex.org/W2322660418","https://openalex.org/W2134877526","https://openalex.org/W2607562548","https://openalex.org/W2160330414","https://openalex.org/W2939407732"],"ngrams_url":"https://api.openalex.org/works/W3176688224/ngrams","abstract_inverted_index":{"\u0026amp;lt;p\u0026amp;gt;Plastic":[0],"debris":[1,48,59,113,137,162],"in":[2,135],"the":[3,98,102,217],"global":[4],"ocean":[5],"is":[6,22,88,126],"considered":[7],"an":[8,56,127],"essential":[9],"issue":[10],"with":[11,144],"severe":[12],"implications":[13],"for":[14,26,41,45,70,97,160],"human":[15],"health":[16],"and":[17,28,38,66,79,115,148,170,202,213,220],"marine":[18,30,46,161,223],"ecosystems.":[19],"Remote":[20],"sensing":[21],"a":[23,153],"useful":[24],"tool":[25],"detecting":[27],"identifying":[29],"pollution;":[31],"however,":[32],"there":[33],"are":[34],"still":[35],"few":[36],"studies":[37],"benchmark":[39,207],"datasets":[40],"developing":[42],"monitoring":[43,142,221],"solutions":[44],"plastic":[47,58,112,136,189,224],"detection":[49,163,219],"from":[50,61],"high-resolution":[51,91,165],"satellite":[52,93,132,166],"data.\u0026amp;lt;/p\u0026amp;gt;\u0026amp;lt;p\u0026amp;gt;Here,":[53],"we":[54],"present":[55,152],"annotated":[57],"dataset":[60,87],"different":[62,181],"geographical":[63],"regions,":[64],"seasons,":[65],"years,":[67],"including":[68],"annotations":[69],"sea":[71,145],"surface":[72,146],"features":[73],"(e.g.,":[74,77],"foam),":[75],"objects":[76],"ship)":[78],"floating":[80],"macroalgae":[81,117],"species":[82],"such":[83],"as":[84,139,141,187,192,194],"Sargassum.":[85],"Our":[86],"based":[89],"on":[90,164],"multispectral":[92],"observations":[94],"collected":[95],"mainly":[96],"period":[99],"2014-2020":[100],"over":[101],"Gulf":[103],"of":[104,155,222],"Honduras":[105],"(Caribbean":[106],"Sea).":[107],"Over":[108],"this":[109],"region,":[110],"large":[111],"masses":[114],"Sargassum":[116],"blooms":[118],"have":[119,184],"been":[120,185],"frequently":[121],"reported,":[122],"suggesting":[123],"that":[124,183],"it":[125],"ideal":[128],"region":[129],"to":[130,199],"examine":[131],"sensors'":[133],"effectiveness":[134],"identification,":[138],"well":[140,193],"along":[143],"circulation":[147],"meteorological":[149],"data.\u0026amp;lt;/p\u0026amp;gt;\u0026amp;lt;p\u0026amp;gt;We":[150],"also":[151],"set":[154],"machine":[156],"learning":[157],"classification":[158],"frameworks":[159],"imagery,":[167],"comparing":[168],"qualitatively":[169],"quantitatively":[171],"their":[172,195],"overall":[173],"performance.":[174],"The":[175],"new":[176,203],"algorithms":[177],"were":[178],"validated":[179],"against":[180],"regions":[182],"reported":[186],"major":[188],"polluted":[190],"areas,":[191],"performance":[196],"was":[197],"compared":[198],"well-established":[200],"FAI":[201],"promising":[204],"FDI.":[205],"This":[206],"study":[208],"can":[209],"trigger":[210],"more":[211],"research":[212],"developement":[214],"efforts":[215],"towards":[216],"systematic":[218],"pollution.\u0026amp;lt;/p\u0026amp;gt;":[225]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3176688224","counts_by_year":[],"updated_date":"2023-12-11T06:05:32.350156","created_date":"2021-07-05"}},"citation_counts":{"https://doi.org/10.1371/journal.pone.0262247":27,"https://doi.org/10.5194/egusphere-egu21-15243":0},"total_citations":27,"keywords_from_contributors":[],"project_url":"https://ost.ecosyste.ms/api/v1/projects/538","html_url":"https://ost.ecosyste.ms/projects/538"}