Evaluating the feasibility of automating dataset retrieval for biodiversity monitoring

PeerJ, Journal Year: 2025, Volume and Issue: 13, P. e18853 - e18853

Published: Jan. 29, 2025

Aim Effective management strategies for conserving biodiversity and mitigating the impacts of global change rely on access to comprehensive up-to-date data. However, manual search, retrieval, evaluation, integration this information into databases present a significant challenge keeping pace with rapid influx large amounts data, hindering its utility in contemporary decision-making processes. Automating these tasks through advanced algorithms holds immense potential revolutionize monitoring. Innovation In study, we investigate automating retrieval evaluation data from Dryad Zenodo repositories. We have designed an system based various criteria, including type provided spatio-temporal range, applied it manually assess relevance monitoring datasets retrieved application programming interface (API). evaluated supervised classification identify potentially relevant feasibility automatically ranking relevance. Additionally, same appraoch scientific literature source, using Semantic Scholar reference. Our centers database utilized by national Quebec, Canada. Main conclusions 89 (55%) our database, showing value automated dataset search find that publication sources offer broader temporal coverage can serve as conduits guiding researchers toward other valuable sources. showed moderate performance detecting (with F-score up 0.68) signs overfitting, emphasizing need further refinement. A key identified is scarcity uneven distribution metadata texts, especially pertaining spatial extents. evaluative framework, predefined be adopted streamlined prioritization, make publicly available, serving benchmark improving techniques.

Language: Английский

New opportunities and challenges for conservation evidence synthesis from advances in natural language processing

Conservation Biology, Journal Year: 2025, Volume and Issue: 39(2)

Published: April 1, 2025

Abstract Addressing global environmental conservation problems requires rapidly translating natural and social science evidence to policy‐relevant information. Yet, exponential increases in scientific production combined with disciplinary differences reporting research make interdisciplinary syntheses especially challenging. Ongoing developments language processing (NLP), such as large models, machine learning (ML), data mining, hold the promise of accelerating cross‐disciplinary primary research. The evolution ML, NLP, artificial intelligence (AI) systems computational provides new approaches accelerate all stages synthesis science. To show how processing, AI can help automate scale science, we describe methods that querying literature, process unstructured bodies textual evidence, extract parameters interest from studies. Automation translate other agendas by categorizing labeling at scale, yet there are major unanswered questions about use hybrid AI‐expert ethically effectively conservation.

Language: Английский

Technological advances have enhanced and expanded conservation genomics research but are yet to be integrated fully into biodiversity management

Biological Conservation, Journal Year: 2024, Volume and Issue: 299, P. 110788 - 110788

Published: Sept. 16, 2024

Language: Английский