Evaluating the method reproducibility of deep learning models in biodiversity research
Artificial intelligence (AI) is revolutionizing biodiversity research by enabling advanced data analysis, species identification, and habitats monitoring, thereby enhancing conservation efforts. Ensuring reproducibility in AI-driven biodiversity research is crucial for fostering transparency, verify...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-02-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2618.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825202050717188096 |
|---|---|
| author | Waqas Ahmed Vamsi Krishna Kommineni Birgitta König-Ries Jitendra Gaikwad Luiz Gadelha Sheeba Samuel |
| author_facet | Waqas Ahmed Vamsi Krishna Kommineni Birgitta König-Ries Jitendra Gaikwad Luiz Gadelha Sheeba Samuel |
| author_sort | Waqas Ahmed |
| collection | DOAJ |
| description | Artificial intelligence (AI) is revolutionizing biodiversity research by enabling advanced data analysis, species identification, and habitats monitoring, thereby enhancing conservation efforts. Ensuring reproducibility in AI-driven biodiversity research is crucial for fostering transparency, verifying results, and promoting the credibility of ecological findings. This study investigates the reproducibility of deep learning (DL) methods within the biodiversity research. We design a methodology for evaluating the reproducibility of biodiversity-related publications that employ DL techniques across three stages. We define ten variables essential for method reproducibility, divided into four categories: resource requirements, methodological information, uncontrolled randomness, and statistical considerations. These categories subsequently serve as the basis for defining different levels of reproducibility. We manually extract the availability of these variables from a curated dataset comprising 100 publications identified using the keywords provided by biodiversity experts. Our study shows that a dataset is shared in 50% of the publications; however, a significant number of the publications lack comprehensive information on deep learning methods, including details regarding randomness. |
| format | Article |
| id | doaj-art-37d4c9daf90d433fb5be94ac74565f41 |
| institution | Kabale University |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-37d4c9daf90d433fb5be94ac74565f412025-02-07T15:05:11ZengPeerJ Inc.PeerJ Computer Science2376-59922025-02-0111e261810.7717/peerj-cs.2618Evaluating the method reproducibility of deep learning models in biodiversity researchWaqas Ahmed0Vamsi Krishna Kommineni1Birgitta König-Ries2Jitendra Gaikwad3Luiz Gadelha4Sheeba Samuel5Heinz Nixdorf Chair of Distributed Information Systems, Friedrich-Schiller Universität Jena, Jena, Thuringia, GermanyHeinz Nixdorf Chair of Distributed Information Systems, Friedrich-Schiller Universität Jena, Jena, Thuringia, GermanyHeinz Nixdorf Chair of Distributed Information Systems, Friedrich-Schiller Universität Jena, Jena, Thuringia, GermanyHeinz Nixdorf Chair of Distributed Information Systems, Friedrich-Schiller Universität Jena, Jena, Thuringia, GermanyHeinz Nixdorf Chair of Distributed Information Systems, Friedrich-Schiller Universität Jena, Jena, Thuringia, GermanyHeinz Nixdorf Chair of Distributed Information Systems, Friedrich-Schiller Universität Jena, Jena, Thuringia, GermanyArtificial intelligence (AI) is revolutionizing biodiversity research by enabling advanced data analysis, species identification, and habitats monitoring, thereby enhancing conservation efforts. Ensuring reproducibility in AI-driven biodiversity research is crucial for fostering transparency, verifying results, and promoting the credibility of ecological findings. This study investigates the reproducibility of deep learning (DL) methods within the biodiversity research. We design a methodology for evaluating the reproducibility of biodiversity-related publications that employ DL techniques across three stages. We define ten variables essential for method reproducibility, divided into four categories: resource requirements, methodological information, uncontrolled randomness, and statistical considerations. These categories subsequently serve as the basis for defining different levels of reproducibility. We manually extract the availability of these variables from a curated dataset comprising 100 publications identified using the keywords provided by biodiversity experts. Our study shows that a dataset is shared in 50% of the publications; however, a significant number of the publications lack comprehensive information on deep learning methods, including details regarding randomness.https://peerj.com/articles/cs-2618.pdfReproducibilityDeep learningMetadataBiodiversity |
| spellingShingle | Waqas Ahmed Vamsi Krishna Kommineni Birgitta König-Ries Jitendra Gaikwad Luiz Gadelha Sheeba Samuel Evaluating the method reproducibility of deep learning models in biodiversity research PeerJ Computer Science Reproducibility Deep learning Metadata Biodiversity |
| title | Evaluating the method reproducibility of deep learning models in biodiversity research |
| title_full | Evaluating the method reproducibility of deep learning models in biodiversity research |
| title_fullStr | Evaluating the method reproducibility of deep learning models in biodiversity research |
| title_full_unstemmed | Evaluating the method reproducibility of deep learning models in biodiversity research |
| title_short | Evaluating the method reproducibility of deep learning models in biodiversity research |
| title_sort | evaluating the method reproducibility of deep learning models in biodiversity research |
| topic | Reproducibility Deep learning Metadata Biodiversity |
| url | https://peerj.com/articles/cs-2618.pdf |
| work_keys_str_mv | AT waqasahmed evaluatingthemethodreproducibilityofdeeplearningmodelsinbiodiversityresearch AT vamsikrishnakommineni evaluatingthemethodreproducibilityofdeeplearningmodelsinbiodiversityresearch AT birgittakonigries evaluatingthemethodreproducibilityofdeeplearningmodelsinbiodiversityresearch AT jitendragaikwad evaluatingthemethodreproducibilityofdeeplearningmodelsinbiodiversityresearch AT luizgadelha evaluatingthemethodreproducibilityofdeeplearningmodelsinbiodiversityresearch AT sheebasamuel evaluatingthemethodreproducibilityofdeeplearningmodelsinbiodiversityresearch |