Accelerating joint species distribution modelling with Hmsc-HPC by GPU porting
PLOS Computational Biology · 03.09.2024 · 20 (9) · e1011914
DOI: 10.1371/journal.pcbi.1011914 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 03.09.2024. Verfasst von Anis Ur Rahman und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biological and Environmental Science, Faculty of Mathematics and Science, University of Jyväskylä, Jyväskylä, Finland. Hauptthemen laut MEDLINE: Algorithms, Computational Biology, Software. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Academy of Finland, European Union: the European Research Council (ERC), ERC-synergy project (LIFEPLAN).
Abstract (Originalsprache)
Joint species distribution modelling (JSDM) is a widely used statistical method that analyzes combined patterns of all species in a community, linking empirical data to ecological theory and enhancing community-wide prediction tasks. However, fitting JSDMs to large datasets is often computationally demanding and time-consuming. Recent studies have introduced new statistical and machine learning techniques to provide more scalable fitting algorithms, but extending these to complex JSDM structures that account for spatial dependencies or multi-level sampling designs remains challenging. In this study, we aim to enhance JSDM scalability by leveraging high-performance computing (HPC) resources for an existing fitting method. Our work focuses on the Hmsc R-package, a widely used JSDM framework that supports the integration of various dataset types into a single comprehensive model. We developed a GPU-compatible implementation of its model-fitting algorithm using Python and the TensorFlow library. Despite these changes, our enhanced framework retains the original user interface of the Hmsc R-package. We evaluated the performance of the proposed implementation across various model configurations and dataset sizes. Our results show a significant increase in model fitting speed for most models compared to the baseline Hmsc R-package. For the largest datasets, we achieved speed-ups of over 1000 times, demonstrating the substantial potential of GPU porting for previously CPU-bound JSDM software. This advancement opens promising opportunities for better utilizing the rapidly accumulating new biodiversity data resources for inference and prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biological and Environmental Science, Faculty of Mathematics and Science, University of Jyväskylä, Jyväskylä, Finland.
- Organismal and Evolutionary Biology Research Programme, Faculty of Biological and Environmental Sciences, University of Helsinki, Helsinki, Finland.
- CSC - IT Center for Science Ltd., Espoo, Finland.
ORCID-Profile: Anis Ur Rahman, Gleb Tikhonov, Tuomas Rossi, Otso Ovaskainen
Förderung
- Academy of Finland
- European Union: the European Research Council (ERC)
- ERC-synergy project (LIFEPLAN)
- European Research Council
Zitieren
APA
Rahman, A. U., Tikhonov, G., Oksanen, J., Rossi, T., & Ovaskainen, O. (2024). Accelerating joint species distribution modelling with Hmsc-HPC by GPU porting. PLOS Computational Biology, 20(9), e1011914. https://doi.org/10.1371/journal.pcbi.1011914
Vancouver
Rahman AU, Tikhonov G, Oksanen J, Rossi T, Ovaskainen O. Accelerating joint species distribution modelling with Hmsc-HPC by GPU porting. PLOS Computational Biology. 2024;20(9):e1011914. doi:10.1371/journal.pcbi.1011914
BibTeX
@article{Rahman2024,
author = {Rahman, Anis Ur and Tikhonov, Gleb and Oksanen, Jari and Rossi, Tuomas and Ovaskainen, Otso},
title = {Accelerating joint species distribution modelling with Hmsc-HPC by GPU porting},
journal = {PLOS Computational Biology},
year = {2024},
volume = {20},
number = {9},
pages = {e1011914},
doi = {10.1371/journal.pcbi.1011914}
}
EUVIMED