Skip to content
DraconiticResearch
Search Sources API
197,788 studies31 sourcesUpdated 31 min ago
Peer-reviewedCC BY 4.0PLOS One

Comparing literature-guided, LLM-assisted, and data-driven models for predicting angler pressure

  • Azar Taheri Tayebi1
  • Julia S. Schmid2
  • Sean Simmons3
  • Mark S. Poesch4
  • Mark A. Lewis5
  • Pouria Ramazi6
6 affiliations
  1. 1Department of Mathematics and Statistics, Brock University, St. Catharines, Ontario, Canada
  2. 2Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton, Alberta, Canada
  3. 3Angler’s Atlas, Goldstream Publishing, Prince George, British Columbia, Canada
  4. 4Department of Renewable Resources, University of Alberta, Edmonton, Alberta, Canada
  5. 5Departments of Mathematics and Statistics and Biology, University of Victoria, Victoria, British Columbia, Canada
  6. 6Department of Mathematics and Statistics and Department of Biological Sciences, University of Calgary, Calgary, Alberta, Canada
Open at sourcePDFDOICite

Abstract

This study compared three models–a literature-guided, a large language model (LLM)-assisted, and a data-driven model–all developed using Bayesian networks as the framework for predicting angler pressure measured by the number of boats observed in aerial surveys. The models used meteorological data from 98 lakes in Ontario, Canada, during 2018 and 2019, as well as platform-derived variables, including angler-reported fishing trips, fishing duration, and catch rate, together with lake webpage views. In five-fold cross-validation, no pairwise difference in fold-level accuracy among the three models remained significant after Holm adjustment. These findings suggest that LLM-assisted model construction has potential to support ecological prediction when paired with empirical validation.

Related

  1. Potential for Predicting the Loop Current Extension From Pressure‐Sensing Inverted Echo Sounders (PIES) in Yucatan Channel
    Gaston Manta, Uwe Send, Matthias Lankhorst +3
    Earth and Space SciencePeer-reviewedCC BY-NC 4.0Full textOceanography & cryosphereCrossref
  2. Single-Particle Microplastics Analysis via Laser-Assisted MicroPyrolysis Flowing Atmospheric-Pressure Afterglow Mass Spectrometry Imaging.
    Dong Zhang, Ejoke Akatugba, Gerardo Gamez
    Analytical chemistryPeer-reviewedCC BY-NC-NDFull textEnvironmental science & pollutionEurope PMC
  3. Comparing the pristine biochar and Zn-biochar composite for stabilizing Cd in a contaminated calcareous soil
    Hamid Reza Boostani
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEnvironmental science & pollutionCrossref
  4. Comparing soil-health- and species-based sensitivity distributions for metal risk assessment in Tianjin soils
    Qiuyun Xu, Yajuan Shi, Xin Xiong +4
    ISciencePeer-reviewedCC BY-NC-NDFull textEnvironmental science & pollutionEurope PMCCrossref
  5. Comparing the effect of organic matter quality on aerobic and anaerobic greenhouse gas production in a temperate peatland
    Rachel Shaw, Lauren Bryan, Alexis Koehl +1
    EarthArXivPreprintCC BY 4.0Full textEnvironmental science & pollutionEarthArXiv

Cite

BibTeXRIS
BibTeX
@article{tayebi2026comparing,
  title = {{Comparing literature-guided, LLM-assisted, and data-driven models for predicting angler pressure}},
  author = {Azar Taheri Tayebi and Julia S. Schmid and Sean Simmons and Mark S. Poesch and Mark A. Lewis and Pouria Ramazi},
  journal = {PLOS One},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pone.0357450},
  url = {https://doi.org/10.1371/journal.pone.0357450},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Comparing literature-guided, LLM-assisted, and data-driven models for predicting angler pressure
AU  - Azar Taheri Tayebi
AU  - Julia S. Schmid
AU  - Sean Simmons
AU  - Mark S. Poesch
AU  - Mark A. Lewis
AU  - Pouria Ramazi
PY  - 2026
DA  - 2026/10/09
JO  - PLOS One
DO  - 10.1371/journal.pone.0357450
UR  - https://doi.org/10.1371/journal.pone.0357450
AB  - This study compared three models–a literature-guided, a large language model (LLM)-assisted, and a data-driven model–all developed using Bayesian networks as the framework for predicting angler pressure measured by the number of boats observed in aerial surveys. The models used meteorological data from 98 lakes in Ontario, Canada, during 2018 and 2019, as well as platform-derived variables, including angler-reported fishing trips, fishing duration, and catch rate, together with lake webpage views. In five-fold cross-validation, no pairwise difference in fold-level accuracy among the three models remained significant after Holm adjustment. These findings suggest that LLM-assisted model construction has potential to support ecological prediction when paired with empirical validation.
SN  - 1932-6203
ER  -