Local interpretation of machine learning models in remote sensing with SHAP

Data-driven models using machine learning have been widely used in remote-sensing applications such as the retrieval of biophysical variables and land cover classification. However, these models behave as a 'black box', meaning that the relationships between the input and predicted variabl...

Descripción completa

Detalles Bibliográficos
Autores: Descals, Adrià|||0000-0003-1644-3036, Verger, Aleixandre|||0000-0001-9374-1745, Yin, Gaofei|||0000-0002-9828-7139, Filella, Iolanda|||0000-0001-6262-5733, Peñuelas, Josep|||0000-0002-7215-0150
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:287444
Acceso en línea:https://ddd.uab.cat/record/287444
https://dx.doi.org/urn:doi:10.1080/01431161.2023.2217982
Access Level:acceso abierto
Palabra clave:SHapley Additive exPlanations
Explainable machine learning
Local interpretation
Sun-induced fluorescence
Vegetation phenology
Climate constraints
Photosynthesis dynamics
id ES_eb327f41fcdd8ca82e415d848c1e41bf
oai_identifier_str oai:ddd.uab.cat:287444
network_acronym_str ES
network_name_str España
repository_id_str
spelling Local interpretation of machine learning models in remote sensing with SHAPthe case of global climate constraints on photosynthesis phenologyDescals, Adrià|||0000-0003-1644-3036Verger, Aleixandre|||0000-0001-9374-1745Yin, Gaofei|||0000-0002-9828-7139Filella, Iolanda|||0000-0001-6262-5733Peñuelas, Josep|||0000-0002-7215-0150SHapley Additive exPlanationsExplainable machine learningLocal interpretationSun-induced fluorescenceVegetation phenologyClimate constraintsPhotosynthesis dynamicsData-driven models using machine learning have been widely used in remote-sensing applications such as the retrieval of biophysical variables and land cover classification. However, these models behave as a 'black box', meaning that the relationships between the input and predicted variables are hard to interpret. Recent regression models that downscale sun-induced fluorescence (SIF) with MODIS and weather variables are an example. The impact of weather variables on the predicted SIF in these models is unknown. The explanation of such weather-SIF relationships would aid in the understanding of climate-related constraints on photosynthesis phenology since SIF is a proxy of gross primary productivity. Here, we used SHapley Additive exPlanations (SHAP) - a novel technique based on game theory - for explaining the contribution of input variables to the individual predictions in a machine learning model. We explored the capabilities of this technique with a weather-SIF model. The regression model predicted ESA-TROPOSIF measurements from ERA5-Land air temperature, shortwave radiation, and vapour-pressure-deficit (VPD) data. The SHAP values of the model were estimated at the start and end of the growing season for the entire globe. These values depicted the global constraints of the three climate variables on the photosynthetically active season and confirmed existing knowledge on the limiting factors of terrestrial photosynthesis with unprecedented spatial detail. Radiation was the limiting factor in tropical rainforest and VPD constrained the start and end of the growing season in tropical dryland ecosystems. In extra-tropical regions, temperature was the main limiting factor during the start of the growing season, but both temperature and radiation constrained photosynthesis at the end of the growing season. This technique may help future remote sensing studies that require the use of non-interpretable machine-learning regression models and explain how input variables contribute to the model prediction in a spatiotemporally explicit manner. 22023-01-0120232023-01-01Articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://ddd.uab.cat/record/287444https://dx.doi.org/urn:doi:10.1080/01431161.2023.2217982reponame:Dipòsit Digital de Documents de la UABinstname:Universitat Autònoma de BarcelonaInglésengMinisterio de Ciencia e Innovación https://doi.org/10.13039/501100004837 TED2021-132627B-I00Agència de Gestió d'Ajuts Universitaris i de Recerca https://doi.org/10.13039/501100003030 2021/SGR-1333open accesshttp://purl.org/coar/access_right/c_abf2Aquest material està protegit per drets d'autor i/o drets afins. Podeu utilitzar aquest material en funció del que permet la legislació de drets d'autor i drets afins d'aplicació al vostre cas. Per a d'altres usos heu d'obtenir permís del(s) titular(s) de drets.https://rightsstatements.org/vocab/InC/1.0/info:eu-repo/semantics/openAccessoai:ddd.uab.cat:2874442026-06-06T12:50:31Z
dc.title.none.fl_str_mv Local interpretation of machine learning models in remote sensing with SHAP
the case of global climate constraints on photosynthesis phenology
title Local interpretation of machine learning models in remote sensing with SHAP
spellingShingle Local interpretation of machine learning models in remote sensing with SHAP
Descals, Adrià|||0000-0003-1644-3036
SHapley Additive exPlanations
Explainable machine learning
Local interpretation
Sun-induced fluorescence
Vegetation phenology
Climate constraints
Photosynthesis dynamics
title_short Local interpretation of machine learning models in remote sensing with SHAP
title_full Local interpretation of machine learning models in remote sensing with SHAP
title_fullStr Local interpretation of machine learning models in remote sensing with SHAP
title_full_unstemmed Local interpretation of machine learning models in remote sensing with SHAP
title_sort Local interpretation of machine learning models in remote sensing with SHAP
dc.creator.none.fl_str_mv Descals, Adrià|||0000-0003-1644-3036
Verger, Aleixandre|||0000-0001-9374-1745
Yin, Gaofei|||0000-0002-9828-7139
Filella, Iolanda|||0000-0001-6262-5733
Peñuelas, Josep|||0000-0002-7215-0150
author Descals, Adrià|||0000-0003-1644-3036
author_facet Descals, Adrià|||0000-0003-1644-3036
Verger, Aleixandre|||0000-0001-9374-1745
Yin, Gaofei|||0000-0002-9828-7139
Filella, Iolanda|||0000-0001-6262-5733
Peñuelas, Josep|||0000-0002-7215-0150
author_role author
author2 Verger, Aleixandre|||0000-0001-9374-1745
Yin, Gaofei|||0000-0002-9828-7139
Filella, Iolanda|||0000-0001-6262-5733
Peñuelas, Josep|||0000-0002-7215-0150
author2_role author
author
author
author
dc.subject.none.fl_str_mv SHapley Additive exPlanations
Explainable machine learning
Local interpretation
Sun-induced fluorescence
Vegetation phenology
Climate constraints
Photosynthesis dynamics
topic SHapley Additive exPlanations
Explainable machine learning
Local interpretation
Sun-induced fluorescence
Vegetation phenology
Climate constraints
Photosynthesis dynamics
description Data-driven models using machine learning have been widely used in remote-sensing applications such as the retrieval of biophysical variables and land cover classification. However, these models behave as a 'black box', meaning that the relationships between the input and predicted variables are hard to interpret. Recent regression models that downscale sun-induced fluorescence (SIF) with MODIS and weather variables are an example. The impact of weather variables on the predicted SIF in these models is unknown. The explanation of such weather-SIF relationships would aid in the understanding of climate-related constraints on photosynthesis phenology since SIF is a proxy of gross primary productivity. Here, we used SHapley Additive exPlanations (SHAP) - a novel technique based on game theory - for explaining the contribution of input variables to the individual predictions in a machine learning model. We explored the capabilities of this technique with a weather-SIF model. The regression model predicted ESA-TROPOSIF measurements from ERA5-Land air temperature, shortwave radiation, and vapour-pressure-deficit (VPD) data. The SHAP values of the model were estimated at the start and end of the growing season for the entire globe. These values depicted the global constraints of the three climate variables on the photosynthetically active season and confirmed existing knowledge on the limiting factors of terrestrial photosynthesis with unprecedented spatial detail. Radiation was the limiting factor in tropical rainforest and VPD constrained the start and end of the growing season in tropical dryland ecosystems. In extra-tropical regions, temperature was the main limiting factor during the start of the growing season, but both temperature and radiation constrained photosynthesis at the end of the growing season. This technique may help future remote sensing studies that require the use of non-interpretable machine-learning regression models and explain how input variables contribute to the model prediction in a spatiotemporally explicit manner.
publishDate 2023
dc.date.none.fl_str_mv 2
2023-01-01
2023
2023-01-01
dc.type.none.fl_str_mv Article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://ddd.uab.cat/record/287444
https://dx.doi.org/urn:doi:10.1080/01431161.2023.2217982
url https://ddd.uab.cat/record/287444
https://dx.doi.org/urn:doi:10.1080/01431161.2023.2217982
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Ministerio de Ciencia e Innovación https://doi.org/10.13039/501100004837 TED2021-132627B-I00
Agència de Gestió d'Ajuts Universitaris i de Recerca https://doi.org/10.13039/501100003030 2021/SGR-1333
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://rightsstatements.org/vocab/InC/1.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://rightsstatements.org/vocab/InC/1.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Dipòsit Digital de Documents de la UAB
instname:Universitat Autònoma de Barcelona
instname_str Universitat Autònoma de Barcelona
reponame_str Dipòsit Digital de Documents de la UAB
collection Dipòsit Digital de Documents de la UAB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869423206612336640
score 15,300719

Similares en LA Referencia