Website visits can predict angler presence using machine learning

2024-09-25

arXiv.org

AI Summary

Traditional fisheries surveys are costly and spatially–temporally limited, while environmental/economic driver models suffer from poor generalizability due to data scarcity. Method: This study proposes a novel paradigm for predicting recreational fishing vessel activity by leveraging high-resolution web browsing behavior from online fishing platforms. Using visitation data from nearly 200 Ontario lakes, we integrate meteorological, environmental, and socioecological variables to train random forest and gradient boosting machine models, rigorously evaluated via spatiotemporal cross-validation. Contribution/Results: We provide the first empirical evidence that fishing website traffic serves as a high-fidelity proxy for vessel presence—achieving 78% accuracy in presence/absence prediction and R² = 0.77 for vessel count estimation within known lakes; it retains baseline predictive power (R² = 0.21) for unseen lakes. This approach substantially reduces monitoring costs, enhances real-time management capacity, and extends spatial coverage, offering a scalable methodological framework for sustainable fisheries management in data-poor regions.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Data Mining & Knowledge Management: Knowledge Acquisition from the Web
• Machine Learning: Time-Series/Data Streams

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Sustainability of Web economics

Abstract

Understanding and predicting recreational angler effort is important for sustainable fisheries management. However, conventional methods of measuring angler effort, such as surveys, can be costly and limited in both time and spatial extent. Models that predict angler effort based on environmental or economic factors typically rely on historical data, which often limits their spatial and temporal generalizability due to data scarcity. In this study, high-resolution data from an online fishing platform and easily accessible auxiliary data were tested to predict daily boat presence and aerial counts of boats at almost 200 lakes over five years in Ontario, Canada. Lake-information website visits alone enabled predicting daily angler boat presence with 78% accuracy. While incorporating additional environmental, socio-ecological, weather and angler-reported features into machine learning models did not remarkably improve prediction performance of boat presence, they were substantial for the prediction of boat counts. Models achieved an R2 of up to 0.77 at known lakes included in the model training, but they performed poorly for unknown lakes (R2 = 0.21). The results demonstrate the value of integrating data from online fishing platforms into predictive models and highlight the potential of machine learning models to enhance fisheries management.

Problem

• Predict angler presence using website visit data
• Improve fisheries management with machine learning models
• Overcome data scarcity in angler effort prediction

Innovation

• Machine learning predicts angler presence via website visits
• Online fishing platform data enhances prediction accuracy
• Models integrate environmental and angler-reported features