Ensemble Machine Learning Approaches for CPUE Forecasting in Kenya’s Artisanal Marine Fisheries: Application of Xgboost and Prophet with Random Forest Feature Selection

Catch Per Unit Effort (CPUE) remains a fundamental index of fishery productivity, supporting assessments of stock status and guiding management decisions. In many data-poor fisheries, including those in the Western Indian Ocean (WIO), CPUE forecasting is constrained by incomplete time series, high variability, and limited analytical capacity. Recent advances in machine learning (ML) offer powerful alternatives to traditional statistical models by capturing nonlinear dynamics, interactions among variables, and temporal patterns in noisy data.

CPUE, XGBoost, Prophet, Random Forest, machine learning

1. Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32. [Google Scholar] [Crossref]

2. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. [Google Scholar] [Crossref]

3. Choi, J., Park, H., & Lee, J. (2021). Machine learning applications for predicting fish stock abundance. Ecological Informatics, 63, 101312. [Google Scholar] [Crossref]

4. FAO (2020). The State of World Fisheries and Aquaculture 2020. Rome. [Google Scholar] [Crossref]

5. Hilborn, R., & Walters, C. (1992). Quantitative Fisheries Stock Assessment: Choice, Dynamics and Uncertainty. Springer. [Google Scholar] [Crossref]

6. KMFRI (2020). Status of the Kenya Marine Fisheries 2019/2020 Report. [Google Scholar] [Crossref]

7. Mbaru, E. K., & Obura, D. (2020). Machine learning approaches to coral reef fisheries monitoring. Marine Ecology Progress Series, 634, 1–15. [Google Scholar] [Crossref]

8. Mbaru, E. K., Ochiewo, J., & Obura, D. (2021). Predicting artisanal fisheries catches in Kenya using machine learning. African Journal of Marine Science, 43(2), 203–214. [Google Scholar] [Crossref]

9. Maunder, M. N., & Punt, A. E. (2004). Standardizing catch and effort data: A review of recent approaches. Fisheries Research, 70(2–3), 141–159. [Google Scholar] [Crossref]

10. Obura, D. O., et al. (2017). Coral reef fisheries management in Kenya: Successes, challenges, and policy directions. Marine Policy, 81, 81–92. [Google Scholar] [Crossref]

11. Taylor, S. J., & Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1), 37–45. [Google Scholar] [Crossref]

12. Wanyonyi, I., Mangi, S. C., & Catchpole, T. L. (2018). Socioeconomic impacts of marine artisanal fisheries in Kenya. Ocean & Coastal Management, 163, 372–381. [Google Scholar] [Crossref]

13. Zhou, C., Sun, S., & Xu, Y. (2022). Ensemble learning for marine resource prediction: A review and case study. Ecological Modelling, 464, 109819. [Google Scholar] [Crossref]

14. Zhu, G., Zhang, H., & Wang, S. (2019). Machine learning in fisheries science: Advances and applications. Frontiers in Marine Science, 6, 662. [Google Scholar] [Crossref]

• The Impact of Ownership Structure on Dividend Payout Policy of Listed Plantation Companies in Sri Lanka
• Urban Sustainability in North-East India: A Study through the lens of NER-SDG index
• Performance Assessment of Predictive Forecasting Techniques for Enhancing Hospital Supply Chain Efficiency in Healthcare Logistics
• The Fractured Self in Julian Barnes' Postmodern Fiction: Identity Crisis and Deflation in Metroland and the Sense of an Ending
• Impact of Flood on the Employment, Labour Productivity and Migration of Agricultural Labour in North Bihar