Bioclimatic inference based on mammal community using machine learning regression models: perspectives for paleoecological studies
Climate has played a significant role in shaping the distribution of mammal species across the world. Mammal community composition can therefore be used for inferring modern and past climatic conditions. Here, we develop a novel approach for bioclimatic inference using machine learning (ML) algorith...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Ecology and Evolution |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fevo.2023.1178379/full |
| _version_ | 1797791814162317312 |
|---|---|
| author | Pierre Linchamps Pierre Linchamps Emmanuelle Stoetzel François Robinet Raphaël Hanon Raphaël Hanon Pierre Latouche Pierre Latouche Raphaël Cornette |
| author_facet | Pierre Linchamps Pierre Linchamps Emmanuelle Stoetzel François Robinet Raphaël Hanon Raphaël Hanon Pierre Latouche Pierre Latouche Raphaël Cornette |
| author_sort | Pierre Linchamps |
| collection | DOAJ |
| description | Climate has played a significant role in shaping the distribution of mammal species across the world. Mammal community composition can therefore be used for inferring modern and past climatic conditions. Here, we develop a novel approach for bioclimatic inference using machine learning (ML) algorithms, which allows for accurate prediction of a set of climate variables based on the composition of the faunal community. The automated dataset construction process aggregates bioclimatic variables with modern species distribution maps, and includes multiple taxonomic ranks as explanatory variables for the predictions. This yields a large dataset that can be used to produce highly accurate predictions. Various ML algorithms that perform regression have been examined. To account for spatial dependence in our data, we employed a geographical block validation approach for model validation and selection. The random forest (RF) outperformed the other evaluated algorithms. Ultimately, we used unseen modern mammal surveys to assess the high predictive performances and extrapolation abilities achieved by our trained models. This contribution introduces a framework and methodology to construct models for developing models based on neo-ecological data, which could be utilized for paleoclimate applications in the future. The study aimed to satisfy specific criteria for interpreting both modern and paleo faunal assemblages, including the ability to generate reliable climate predictions from faunal lists with varying taxonomic resolutions, without the need for published wildlife inventory data from the study area. This method demonstrates the versatility of ML techniques in climate modeling and highlights their promising potential for applications in the fields of archaeology and paleontology. |
| first_indexed | 2024-03-13T02:24:08Z |
| format | Article |
| id | doaj.art-726166fc63c4495ba398e7891488c4ff |
| institution | Directory Open Access Journal |
| issn | 2296-701X |
| language | English |
| last_indexed | 2024-03-13T02:24:08Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Ecology and Evolution |
| spelling | doaj.art-726166fc63c4495ba398e7891488c4ff2023-06-30T05:53:40ZengFrontiers Media S.A.Frontiers in Ecology and Evolution2296-701X2023-06-011110.3389/fevo.2023.11783791178379Bioclimatic inference based on mammal community using machine learning regression models: perspectives for paleoecological studiesPierre Linchamps0Pierre Linchamps1Emmanuelle Stoetzel2François Robinet3Raphaël Hanon4Raphaël Hanon5Pierre Latouche6Pierre Latouche7Raphaël Cornette8Institut de Systématique, Évolution, Biodiversité (ISYEB) UMR 7205, CNRS/Muséum National d’Histoire Naturelle/Université Pierre et Marie Curie (UPMC)/École Pratique des Hautes Études (EPHE)/Sorbonne Universités, Paris, FranceHistoire Naturelle de l'Homme Préhistorique (HNHP) UMR 7194, CNRS/Muséum National d’Histoire Naturelle/Université de Perpignan Via Domitia (UPVD)/Sorbonne Universités, Paris, FranceHistoire Naturelle de l'Homme Préhistorique (HNHP) UMR 7194, CNRS/Muséum National d’Histoire Naturelle/Université de Perpignan Via Domitia (UPVD)/Sorbonne Universités, Paris, FranceInterdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg, LuxembourgHistoire Naturelle de l'Homme Préhistorique (HNHP) UMR 7194, CNRS/Muséum National d’Histoire Naturelle/Université de Perpignan Via Domitia (UPVD)/Sorbonne Universités, Paris, FranceEvolutionary Studies Institute, University of the Witwatersrand, Johannesburg, South AfricaLMBP UMR 6620, Université Clermont Auvergne/CNRS, Aubière, FranceMathématiques Appliquées à Paris 5 (MAP5) UMR 8145, Université Paris Cité/CNRS, Paris, FranceInstitut de Systématique, Évolution, Biodiversité (ISYEB) UMR 7205, CNRS/Muséum National d’Histoire Naturelle/Université Pierre et Marie Curie (UPMC)/École Pratique des Hautes Études (EPHE)/Sorbonne Universités, Paris, FranceClimate has played a significant role in shaping the distribution of mammal species across the world. Mammal community composition can therefore be used for inferring modern and past climatic conditions. Here, we develop a novel approach for bioclimatic inference using machine learning (ML) algorithms, which allows for accurate prediction of a set of climate variables based on the composition of the faunal community. The automated dataset construction process aggregates bioclimatic variables with modern species distribution maps, and includes multiple taxonomic ranks as explanatory variables for the predictions. This yields a large dataset that can be used to produce highly accurate predictions. Various ML algorithms that perform regression have been examined. To account for spatial dependence in our data, we employed a geographical block validation approach for model validation and selection. The random forest (RF) outperformed the other evaluated algorithms. Ultimately, we used unseen modern mammal surveys to assess the high predictive performances and extrapolation abilities achieved by our trained models. This contribution introduces a framework and methodology to construct models for developing models based on neo-ecological data, which could be utilized for paleoclimate applications in the future. The study aimed to satisfy specific criteria for interpreting both modern and paleo faunal assemblages, including the ability to generate reliable climate predictions from faunal lists with varying taxonomic resolutions, without the need for published wildlife inventory data from the study area. This method demonstrates the versatility of ML techniques in climate modeling and highlights their promising potential for applications in the fields of archaeology and paleontology.https://www.frontiersin.org/articles/10.3389/fevo.2023.1178379/fullmachine learningclimate modelingecological inferencemammal communitiesmethodologypalaeoclimates |
| spellingShingle | Pierre Linchamps Pierre Linchamps Emmanuelle Stoetzel François Robinet Raphaël Hanon Raphaël Hanon Pierre Latouche Pierre Latouche Raphaël Cornette Bioclimatic inference based on mammal community using machine learning regression models: perspectives for paleoecological studies Frontiers in Ecology and Evolution machine learning climate modeling ecological inference mammal communities methodology palaeoclimates |
| title | Bioclimatic inference based on mammal community using machine learning regression models: perspectives for paleoecological studies |
| title_full | Bioclimatic inference based on mammal community using machine learning regression models: perspectives for paleoecological studies |
| title_fullStr | Bioclimatic inference based on mammal community using machine learning regression models: perspectives for paleoecological studies |
| title_full_unstemmed | Bioclimatic inference based on mammal community using machine learning regression models: perspectives for paleoecological studies |
| title_short | Bioclimatic inference based on mammal community using machine learning regression models: perspectives for paleoecological studies |
| title_sort | bioclimatic inference based on mammal community using machine learning regression models perspectives for paleoecological studies |
| topic | machine learning climate modeling ecological inference mammal communities methodology palaeoclimates |
| url | https://www.frontiersin.org/articles/10.3389/fevo.2023.1178379/full |
| work_keys_str_mv | AT pierrelinchamps bioclimaticinferencebasedonmammalcommunityusingmachinelearningregressionmodelsperspectivesforpaleoecologicalstudies AT pierrelinchamps bioclimaticinferencebasedonmammalcommunityusingmachinelearningregressionmodelsperspectivesforpaleoecologicalstudies AT emmanuellestoetzel bioclimaticinferencebasedonmammalcommunityusingmachinelearningregressionmodelsperspectivesforpaleoecologicalstudies AT francoisrobinet bioclimaticinferencebasedonmammalcommunityusingmachinelearningregressionmodelsperspectivesforpaleoecologicalstudies AT raphaelhanon bioclimaticinferencebasedonmammalcommunityusingmachinelearningregressionmodelsperspectivesforpaleoecologicalstudies AT raphaelhanon bioclimaticinferencebasedonmammalcommunityusingmachinelearningregressionmodelsperspectivesforpaleoecologicalstudies AT pierrelatouche bioclimaticinferencebasedonmammalcommunityusingmachinelearningregressionmodelsperspectivesforpaleoecologicalstudies AT pierrelatouche bioclimaticinferencebasedonmammalcommunityusingmachinelearningregressionmodelsperspectivesforpaleoecologicalstudies AT raphaelcornette bioclimaticinferencebasedonmammalcommunityusingmachinelearningregressionmodelsperspectivesforpaleoecologicalstudies |