Combining environmental DNA and remote sensing variables to model fish biodiversity in tropical river ecosystems

Tropical river ecosystems face substantial threats, leading to a sharp decline in their biodiversity. High-resolution data on the spatial distribution of biodiversity is essential for devising effective conservation strategies. However, biodiversity information is limited because traditional assessm...

Full description

Saved in:
Bibliographic Details
Main Authors: Robin Bauknecht, Loïc Pellissier, Sébastien Brosse, Vincent Prié, Manuel Lopes-Lima, Pedro Beja, Monika K. Goralczyk, Andrea Polanco Fernandez, Jorge A. Moreno-Tilano, Rafik Neme, Mailyn A. Gonzalez, Shuo Zong
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125002602
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233618664161280
author Robin Bauknecht
Loïc Pellissier
Sébastien Brosse
Vincent Prié
Manuel Lopes-Lima
Pedro Beja
Monika K. Goralczyk
Andrea Polanco Fernandez
Jorge A. Moreno-Tilano
Rafik Neme
Mailyn A. Gonzalez
Shuo Zong
author_facet Robin Bauknecht
Loïc Pellissier
Sébastien Brosse
Vincent Prié
Manuel Lopes-Lima
Pedro Beja
Monika K. Goralczyk
Andrea Polanco Fernandez
Jorge A. Moreno-Tilano
Rafik Neme
Mailyn A. Gonzalez
Shuo Zong
author_sort Robin Bauknecht
collection DOAJ
description Tropical river ecosystems face substantial threats, leading to a sharp decline in their biodiversity. High-resolution data on the spatial distribution of biodiversity is essential for devising effective conservation strategies. However, biodiversity information is limited because traditional assessment methods often face challenges in these vast, inaccessible environments. Here, we aim to assess whether combining large-scale environmental DNA (eDNA) data with environmental variables generated from remote sensing images in machine learning models can overcome this limitation. We used a fish eDNA dataset of 264 samples collected from major tropical rivers—the Casamance, Cuando, Cunene, Okavango, and Zambezi (Africa); the Magdalena, Maroni, and Oyapock (South America); and the Kinabatangan (Southeast Asia)—together with aquatic and terrestrial variables derived from remote sensing imagery. Based on this data, we constructed both river-specific and multi-river Random Forest models to predict fish species richness and the Shannon diversity index. The models exhibited a good fit to the data, indicating the suitability of variables in capturing the determinants of fish biodiversity in these rivers. Moreover, the models effectively predicted the metrics during cross-validation, underscoring their utility in generating biodiversity maps along large tropical rivers. Although predictions for unencountered rivers remain challenging, the models are able to capture large-scale patterns. With further refinement and expansion through additional data, this integrated approach holds promise for generating biodiversity insights without extensive on-site sampling requirements. Our study highlights the potential of combining eDNA with remote sensing variables to model biodiversity patterns in tropical river ecosystems.
format Article
id doaj-art-e10a524f639e4e918f07184fb13e71ee
institution Kabale University
issn 1574-9541
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-e10a524f639e4e918f07184fb13e71ee2025-08-20T05:05:20ZengElsevierEcological Informatics1574-95412025-12-019010325110.1016/j.ecoinf.2025.103251Combining environmental DNA and remote sensing variables to model fish biodiversity in tropical river ecosystemsRobin Bauknecht0Loïc Pellissier1Sébastien Brosse2Vincent Prié3Manuel Lopes-Lima4Pedro Beja5Monika K. Goralczyk6Andrea Polanco Fernandez7Jorge A. Moreno-Tilano8Rafik Neme9Mailyn A. Gonzalez10Shuo Zong11Ecosystems and Landscape Evolution, Institute of Terrestrial Ecosystems, Department of Environmental Systems Science, ETH Zürich, Zürich, Switzerland; Corresponding author.Ecosystems and Landscape Evolution, Institute of Terrestrial Ecosystems, Department of Environmental Systems Science, ETH Zürich, Zürich, Switzerland; Land Change Science Research Unit, Swiss Federal Institute for Forest, Snow and Landscape Research, WSL Birmensdorf, SwitzerlandCentre de Recherches sur la Biodiversité et l’Environnement, CRBE UMR5300, Université Paul Sabatier, IRD, CNRS, INP 118 route de Narbonne, 31062 Toulouse, FranceCIBIO, Centro de Investigação em Biodiversidade e Recursos Genéticos, InBIO Laboratório Associado, Campus de Vairão, Universidade do Porto, Vairão, Portugal; BIOPOLIS Program in Genomics, Biodiversity and Land Planning, CIBIO, Vairão, Portugal; SPYGEN, 17, rue du Lac Saint-André - CS 20274, 73375 Le Bourget-du-Lac, FranceCIBIO, Centro de Investigação em Biodiversidade e Recursos Genéticos, InBIO Laboratório Associado, Campus de Vairão, Universidade do Porto, Vairão, Portugal; BIOPOLIS Program in Genomics, Biodiversity and Land Planning, CIBIO, Vairão, PortugalCIBIO, Centro de Investigação em Biodiversidade e Recursos Genéticos, InBIO Laboratório Associado, Campus de Vairão, Universidade do Porto, Vairão, Portugal; CIBIO, Centro de Investigação em Biodiversidade e Recursos Genéticos, InBIO Laboratório Associado, Instituto Superior de Agronomia, Universidade de Lisboa, Lisboa, Portugal; BIOPOLIS Program in Genomics, Biodiversity and Land Planning, CIBIO, Vairão, PortugalEcosystems and Landscape Evolution, Institute of Terrestrial Ecosystems, Department of Environmental Systems Science, ETH Zürich, Zürich, Switzerland; Land Change Science Research Unit, Swiss Federal Institute for Forest, Snow and Landscape Research, WSL Birmensdorf, SwitzerlandFundacion Biodiversa Colombia, Bogota, ColombiaDepartment of Chemistry and Biology, Universidad del Norte, Barranquilla, Colombia; Max Planck Partner Group for Genomics and Biodiversity of the Colombian Caribbean, ColombiaDepartment of Chemistry and Biology, Universidad del Norte, Barranquilla, Colombia; Max Planck Partner Group for Genomics and Biodiversity of the Colombian Caribbean, ColombiaInstituto de Investigación de Recursos Biológicos Alexander von Humboldt, Bogotá, ColombiaEcosystems and Landscape Evolution, Institute of Terrestrial Ecosystems, Department of Environmental Systems Science, ETH Zürich, Zürich, Switzerland; Land Change Science Research Unit, Swiss Federal Institute for Forest, Snow and Landscape Research, WSL Birmensdorf, Switzerland; Corresponding author at: Ecosystems and Landscape Evolution, Institute of Terrestrial Ecosystems, Department of Environmental Systems Science, ETH Zürich, Zürich, Switzerland.Tropical river ecosystems face substantial threats, leading to a sharp decline in their biodiversity. High-resolution data on the spatial distribution of biodiversity is essential for devising effective conservation strategies. However, biodiversity information is limited because traditional assessment methods often face challenges in these vast, inaccessible environments. Here, we aim to assess whether combining large-scale environmental DNA (eDNA) data with environmental variables generated from remote sensing images in machine learning models can overcome this limitation. We used a fish eDNA dataset of 264 samples collected from major tropical rivers—the Casamance, Cuando, Cunene, Okavango, and Zambezi (Africa); the Magdalena, Maroni, and Oyapock (South America); and the Kinabatangan (Southeast Asia)—together with aquatic and terrestrial variables derived from remote sensing imagery. Based on this data, we constructed both river-specific and multi-river Random Forest models to predict fish species richness and the Shannon diversity index. The models exhibited a good fit to the data, indicating the suitability of variables in capturing the determinants of fish biodiversity in these rivers. Moreover, the models effectively predicted the metrics during cross-validation, underscoring their utility in generating biodiversity maps along large tropical rivers. Although predictions for unencountered rivers remain challenging, the models are able to capture large-scale patterns. With further refinement and expansion through additional data, this integrated approach holds promise for generating biodiversity insights without extensive on-site sampling requirements. Our study highlights the potential of combining eDNA with remote sensing variables to model biodiversity patterns in tropical river ecosystems.http://www.sciencedirect.com/science/article/pii/S1574954125002602Environmental DNARemote sensingEcological modelingBiodiversity monitoringAquatic species detectionTropical river ecosystems
spellingShingle Robin Bauknecht
Loïc Pellissier
Sébastien Brosse
Vincent Prié
Manuel Lopes-Lima
Pedro Beja
Monika K. Goralczyk
Andrea Polanco Fernandez
Jorge A. Moreno-Tilano
Rafik Neme
Mailyn A. Gonzalez
Shuo Zong
Combining environmental DNA and remote sensing variables to model fish biodiversity in tropical river ecosystems
Ecological Informatics
Environmental DNA
Remote sensing
Ecological modeling
Biodiversity monitoring
Aquatic species detection
Tropical river ecosystems
title Combining environmental DNA and remote sensing variables to model fish biodiversity in tropical river ecosystems
title_full Combining environmental DNA and remote sensing variables to model fish biodiversity in tropical river ecosystems
title_fullStr Combining environmental DNA and remote sensing variables to model fish biodiversity in tropical river ecosystems
title_full_unstemmed Combining environmental DNA and remote sensing variables to model fish biodiversity in tropical river ecosystems
title_short Combining environmental DNA and remote sensing variables to model fish biodiversity in tropical river ecosystems
title_sort combining environmental dna and remote sensing variables to model fish biodiversity in tropical river ecosystems
topic Environmental DNA
Remote sensing
Ecological modeling
Biodiversity monitoring
Aquatic species detection
Tropical river ecosystems
url http://www.sciencedirect.com/science/article/pii/S1574954125002602
work_keys_str_mv AT robinbauknecht combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT loicpellissier combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT sebastienbrosse combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT vincentprie combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT manuellopeslima combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT pedrobeja combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT monikakgoralczyk combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT andreapolancofernandez combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT jorgeamorenotilano combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT rafikneme combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT mailynagonzalez combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems
AT shuozong combiningenvironmentaldnaandremotesensingvariablestomodelfishbiodiversityintropicalriverecosystems