Remote Sensing-Based Hybrid Statistical and Machine Learning Ensemble Modeling of Yellowfin Tuna Catch in the Western Equatorial Indian Ocean

Abstract

Yellowfin tuna (Thunnus albacares) is an economically important pelagic species in the Indian Ocean, but its monthly catch variability is difficult to predict because reported catch is influenced by ocean productivity, thermal habitat, monsoon seasonality, fishing-ground characteristics, and fleet behavior. This study develops a remote sensing-based statistical and machine learning stacked ensemble for modeling monthly yellowfin tuna catch across five fishing grounds in the western equatorial Indian Ocean during 2003-2024. Monthly fishery records were integrated with satellite-derived chlorophyll-a concentration (CHL) and sea surface temperature (SST). Linear mixed models (LMMs) and a generalized additive mixed model (GAMM) were used to represent interpretable current and lagged environmental effects, while Random Forest models captured nonlinear interactions among lagged, rolling, seasonal, anomaly, and spatial predictors. Expanding-window validation over the pre-COVID evaluation period from 2008 to 2019 was used to reduce temporal leakage. Among the individual models, the GAMM achieved the best log-scale performance, with an R-squared value of 0.137 and an RMSE of 1.284, while RF-E6 achieved the lowest RMSE on the kilogram scale. The nonnegative Ridge stacked ensemble improved the log-scale R-squared value to 0.177, with an RMSE of 1.254 and an MAE of 1.000. These results show that satellite-derived CHL and SST contain useful but incomplete predictive information for monthly catch modeling.