BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography
Aim: Functional traits of organisms are key to understanding and predicting biodiversity and ecological change, which motivates continuous collection of traits and their integration into global databases. Such trait matrices are inherently sparse, severely limiting their usefulness for further analy...
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Published: |
Wiley
2015
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/47674/ |
| _version_ | 1848797603121070080 |
|---|---|
| author | Schrodt, Franziska Kattge, Jens Shan, Hanhuai Fazayeli, Farideh Joswig, Julia Banerjee, Arindam Reichstein, Markus Bönisch, Gerhard Diaz, Sandra Dickie, John Gillison, Andy Karpatne, Anuj Lavorel, Sandra Leadley, Paul Wirth, Christian B. Wright, Ian J. Wright, S. Joseph Reich, Peter B. |
| author_facet | Schrodt, Franziska Kattge, Jens Shan, Hanhuai Fazayeli, Farideh Joswig, Julia Banerjee, Arindam Reichstein, Markus Bönisch, Gerhard Diaz, Sandra Dickie, John Gillison, Andy Karpatne, Anuj Lavorel, Sandra Leadley, Paul Wirth, Christian B. Wright, Ian J. Wright, S. Joseph Reich, Peter B. |
| author_sort | Schrodt, Franziska |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Aim: Functional traits of organisms are key to understanding and predicting biodiversity and ecological change, which motivates continuous collection of traits and their integration into global databases. Such trait matrices are inherently sparse, severely limiting their usefulness for further analyses. On the other hand, traits are characterized by the phylogenetic trait signal, trait–trait correlations and environmental constraints, all of which provide information that could be used to statistically fill gaps. We propose the application of probabilistic models which, for the first time, utilize all three characteristics to fill gaps in trait databases and predict trait values at larger spatial scales.
Innovation: For this purpose we introduce BHPMF, a ierarchical Bayesian extension of probabilistic matrix actorization (PMF). PMF is a machine learning technique which exploits the correlation structure of sparse matrices to impute missing entries. BHPMF additionally utilizes the taxonomic hierarchy for trait prediction and provides uncertainty estimates for each imputation. In combination with multiple regression against environmental information, BHPMF allows for extrapolation frompoint measurements to larger spatial scales.We demonstrate the applicability of BHPMF in ecological contexts, using different plant functional trait datasets, also comparing results to taking the species mean and PMF.
Main conclusions: Sensitivity analyses validate the robustness and accuracy of BHPMF: our method captures the correlation structure of the trait matrix as well as the phylogenetic trait signal – also for extremely sparse trait matrices – and provides a robust measure of confidence in prediction accuracy for each missing entry. The combination of BHPMF with environmental constraints provides a promising concept to extrapolate traits beyond sampled regions, accounting for intraspecific trait variability. We conclude that BHPMF and its derivatives have a high potential to support future trait-based research in macroecology and functional biogeography. |
| first_indexed | 2025-11-14T20:06:30Z |
| format | Article |
| id | nottingham-47674 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T20:06:30Z |
| publishDate | 2015 |
| publisher | Wiley |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-476742020-05-04T17:24:17Z https://eprints.nottingham.ac.uk/47674/ BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography Schrodt, Franziska Kattge, Jens Shan, Hanhuai Fazayeli, Farideh Joswig, Julia Banerjee, Arindam Reichstein, Markus Bönisch, Gerhard Diaz, Sandra Dickie, John Gillison, Andy Karpatne, Anuj Lavorel, Sandra Leadley, Paul Wirth, Christian B. Wright, Ian J. Wright, S. Joseph Reich, Peter B. Aim: Functional traits of organisms are key to understanding and predicting biodiversity and ecological change, which motivates continuous collection of traits and their integration into global databases. Such trait matrices are inherently sparse, severely limiting their usefulness for further analyses. On the other hand, traits are characterized by the phylogenetic trait signal, trait–trait correlations and environmental constraints, all of which provide information that could be used to statistically fill gaps. We propose the application of probabilistic models which, for the first time, utilize all three characteristics to fill gaps in trait databases and predict trait values at larger spatial scales. Innovation: For this purpose we introduce BHPMF, a ierarchical Bayesian extension of probabilistic matrix actorization (PMF). PMF is a machine learning technique which exploits the correlation structure of sparse matrices to impute missing entries. BHPMF additionally utilizes the taxonomic hierarchy for trait prediction and provides uncertainty estimates for each imputation. In combination with multiple regression against environmental information, BHPMF allows for extrapolation frompoint measurements to larger spatial scales.We demonstrate the applicability of BHPMF in ecological contexts, using different plant functional trait datasets, also comparing results to taking the species mean and PMF. Main conclusions: Sensitivity analyses validate the robustness and accuracy of BHPMF: our method captures the correlation structure of the trait matrix as well as the phylogenetic trait signal – also for extremely sparse trait matrices – and provides a robust measure of confidence in prediction accuracy for each missing entry. The combination of BHPMF with environmental constraints provides a promising concept to extrapolate traits beyond sampled regions, accounting for intraspecific trait variability. We conclude that BHPMF and its derivatives have a high potential to support future trait-based research in macroecology and functional biogeography. Wiley 2015-11-03 Article PeerReviewed Schrodt, Franziska, Kattge, Jens, Shan, Hanhuai, Fazayeli, Farideh, Joswig, Julia, Banerjee, Arindam, Reichstein, Markus, Bönisch, Gerhard, Diaz, Sandra, Dickie, John, Gillison, Andy, Karpatne, Anuj, Lavorel, Sandra, Leadley, Paul, Wirth, Christian B., Wright, Ian J., Wright, S. Joseph and Reich, Peter B. (2015) BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography. Global Ecology and Biogeography, 24 (12). pp. 1510-1521. ISSN 1466-8238 Bayesian hierarchical model; Gap-filling; Imputation; Machine learning; Matrix factorization PFT; Plant functional trait; Sparse matrix; Spatial extrapolation; TRY http://onlinelibrary.wiley.com/wol1/doi/10.1111/geb.12335/abstract doi:10.1111/geb.12335 doi:10.1111/geb.12335 |
| spellingShingle | Bayesian hierarchical model; Gap-filling; Imputation; Machine learning; Matrix factorization PFT; Plant functional trait; Sparse matrix; Spatial extrapolation; TRY Schrodt, Franziska Kattge, Jens Shan, Hanhuai Fazayeli, Farideh Joswig, Julia Banerjee, Arindam Reichstein, Markus Bönisch, Gerhard Diaz, Sandra Dickie, John Gillison, Andy Karpatne, Anuj Lavorel, Sandra Leadley, Paul Wirth, Christian B. Wright, Ian J. Wright, S. Joseph Reich, Peter B. BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography |
| title | BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography |
| title_full | BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography |
| title_fullStr | BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography |
| title_full_unstemmed | BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography |
| title_short | BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography |
| title_sort | bhpmf – a hierarchical bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography |
| topic | Bayesian hierarchical model; Gap-filling; Imputation; Machine learning; Matrix factorization PFT; Plant functional trait; Sparse matrix; Spatial extrapolation; TRY |
| url | https://eprints.nottingham.ac.uk/47674/ https://eprints.nottingham.ac.uk/47674/ https://eprints.nottingham.ac.uk/47674/ |