WEKO3
アイテム
{"_buckets": {"deposit": "f4ecd6ca-c30d-47dd-9999-a3e005147551"}, "_deposit": {"created_by": 30, "id": "1876", "owners": [30], "pid": {"revision_id": 0, "type": "depid", "value": "1876"}, "status": "published"}, "_oai": {"id": "oai:oist.repo.nii.ac.jp:00001876", "sets": ["27"]}, "author_link": ["12002", "12006", "12004", "12001", "12003", "12005"], "item_10001_biblio_info_7": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2020-11-17", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "2", "bibliographicPageEnd": "205", "bibliographicPageStart": "199", "bibliographicVolumeNumber": "44", "bibliographic_titles": [{}, {"bibliographic_title": "Ecography", "bibliographic_titleLang": "en"}]}]}, "item_10001_creator_3": {"attribute_name": "Author", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Ryo, Masahiro"}], "nameIdentifiers": [{"nameIdentifier": "12001", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Angelov, Boyan"}], "nameIdentifiers": [{"nameIdentifier": "12002", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Mammola, Stefano"}], "nameIdentifiers": [{"nameIdentifier": "12003", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Kass, Jamie M."}], "nameIdentifiers": [{"nameIdentifier": "12004", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Benito, Blas M."}], "nameIdentifiers": [{"nameIdentifier": "12005", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Hartig, Florian"}], "nameIdentifiers": [{"nameIdentifier": "12006", "nameIdentifierScheme": "WEKO"}]}]}, "item_10001_description_5": {"attribute_name": "Abstract", "attribute_value_mlt": [{"subitem_description": "Species distribution models (SDMs) are widely used in ecology, biogeography and conservation biology to estimate relationships between environmental variables and species occurrence data and make predictions of how their distributions vary in space and time. During the past two decades, the field has increasingly made use of machine learning approaches for constructing and validating SDMs. Model accuracy has steadily increased as a result, but the interpretability of the fitted models, for example the relative importance of predictor variables or their causal effects on focal species, has not always kept pace. Here we draw attention to an emerging subdiscipline of artificial intelligence, explainable AI (xAI), as a toolbox for better interpreting SDMs. xAI aims at deciphering the behavior of complex statistical or machine learning models (e.g. neural networks, random forests, boosted regression trees), and can produce more transparent and understandable SDM predictions. We describe the rationale behind xAI and provide a list of tools that can be used to help ecological modelers better understand complex model behavior at different scales. As an example, we perform a reproducible SDM analysis in R on the African elephant and showcase some xAI tools such as local interpretable model-agnostic explanation (LIME) to help interpret local-scale behavior of the model. We conclude with what we see as the benefits and caveats of these techniques and advocate for their use to improve the interpretability of machine learning SDMs.", "subitem_description_type": "Other"}]}, "item_10001_publisher_8": {"attribute_name": "Publisher", "attribute_value_mlt": [{"subitem_publisher": "John Wiley \u0026 Sons Ltd on behalf of Nordic Society Oikos"}]}, "item_10001_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:doi/10.1111/ecog.05360", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_17": {"attribute_name": "Related site", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://onlinelibrary.wiley.com/doi/10.1111/ecog.05360", "subitem_relation_type_select": "URI"}}]}, "item_10001_rights_15": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_rights": "© 2020 The Author(s). "}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "0906-7590", "subitem_source_identifier_type": "ISSN"}, {"subitem_source_identifier": "1600-0587", "subitem_source_identifier_type": "ISSN"}]}, "item_10001_version_type_20": {"attribute_name": "Author\u0027s flag", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2021-02-05"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "ecog.05360(1).pdf", "filesize": [{"value": "2.0 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_6", "mimetype": "application/pdf", "size": 2000000.0, "url": {"label": "ecog.05360(1)", "url": "https://oist.repo.nii.ac.jp/record/1876/files/ecog.05360(1).pdf"}, "version_id": "79e4e3fc-8aff-444e-a32f-15ce45428ae8"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "ecological modeling", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "explainable artificial intelligence", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "habitat suitability modeling", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "interpretable machine learning", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "species distribution model", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "xAI", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Explainable artificial intelligence enhances the ecological interpretability of black‐box species distribution models", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Explainable artificial intelligence enhances the ecological interpretability of black‐box species distribution models", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "30", "path": ["27"], "permalink_uri": "https://oist.repo.nii.ac.jp/records/1876", "pubdate": {"attribute_name": "公開日", "attribute_value": "2021-01-15"}, "publish_date": "2021-01-15", "publish_status": "0", "recid": "1876", "relation": {}, "relation_version_is_last": true, "title": ["Explainable artificial intelligence enhances the ecological interpretability of black‐box species distribution models"], "weko_shared_id": 30}
Explainable artificial intelligence enhances the ecological interpretability of black‐box species distribution models
https://oist.repo.nii.ac.jp/records/1876
https://oist.repo.nii.ac.jp/records/187685916722-85ed-40b4-b713-70e8f597b8ee
名前 / ファイル | ライセンス | アクション |
---|---|---|
ecog.05360(1) (2.0 MB)
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2021-01-15 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Explainable artificial intelligence enhances the ecological interpretability of black‐box species distribution models | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | ecological modeling | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | explainable artificial intelligence | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | habitat suitability modeling | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | interpretable machine learning | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | species distribution model | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | xAI | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | journal article | |||||
著者(英) |
Ryo, Masahiro
× Ryo, Masahiro× Angelov, Boyan× Mammola, Stefano× Kass, Jamie M.× Benito, Blas M.× Hartig, Florian |
|||||
書誌情報 |
en : Ecography 巻 44, 号 2, p. 199-205, 発行日 2020-11-17 |
|||||
抄録 | ||||||
内容記述タイプ | Other | |||||
内容記述 | Species distribution models (SDMs) are widely used in ecology, biogeography and conservation biology to estimate relationships between environmental variables and species occurrence data and make predictions of how their distributions vary in space and time. During the past two decades, the field has increasingly made use of machine learning approaches for constructing and validating SDMs. Model accuracy has steadily increased as a result, but the interpretability of the fitted models, for example the relative importance of predictor variables or their causal effects on focal species, has not always kept pace. Here we draw attention to an emerging subdiscipline of artificial intelligence, explainable AI (xAI), as a toolbox for better interpreting SDMs. xAI aims at deciphering the behavior of complex statistical or machine learning models (e.g. neural networks, random forests, boosted regression trees), and can produce more transparent and understandable SDM predictions. We describe the rationale behind xAI and provide a list of tools that can be used to help ecological modelers better understand complex model behavior at different scales. As an example, we perform a reproducible SDM analysis in R on the African elephant and showcase some xAI tools such as local interpretable model-agnostic explanation (LIME) to help interpret local-scale behavior of the model. We conclude with what we see as the benefits and caveats of these techniques and advocate for their use to improve the interpretability of machine learning SDMs. | |||||
出版者 | ||||||
出版者 | John Wiley & Sons Ltd on behalf of Nordic Society Oikos | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 0906-7590 | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1600-0587 | |||||
DOI | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.1111/ecog.05360 | |||||
権利 | ||||||
権利情報 | © 2020 The Author(s). | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | https://onlinelibrary.wiley.com/doi/10.1111/ecog.05360 | |||||
著者版フラグ | ||||||
出版タイプ | VoR | |||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 |