Hydrodynamic and biochemical impacts on the development of hypoxia in the Louisiana–Texas shelf – Part 2: statistical modeling and hypoxia prediction

[摘要] This study presents a novel ensemble regression model for forecasts of thehypoxic area (HA) in the Louisiana–Texas (LaTex) shelf. Theensemble model combines a zero-inflated Poisson generalized linear model(GLM) and a quasi-Poisson generalized additive model (GAM) and considerspredictors with hydrodynamic and biochemical features. Both models weretrained and calibrated using the daily hindcast (2007–2020) by athree-dimensional coupled hydrodynamic–biogeochemical model embedded in theRegional Ocean Modeling System (ROMS). Compared to the ROMS hindcasts, theensemble model yields a low root-mean-square error (RMSE) (3256 km 2 ),a high R 2 (0.7721), and low mean absolute percentage biases for overall(29 %) and peak HA prediction (25 %). When compared to the shelf-widecruise observations from 2012 to 2020, our ensemble model provides a moreaccurate summer HA forecast than any existing forecast models with a high R 2 (0.9200); a low RMSE (2005 km 2 ); a low scatter index (15 %); and low mean absolute percentage biases for overall (18 %),fair-weather summer (15 %), and windy-summer (18 %) predictions. Totest its robustness, the model is further applied to a global forecast modeland produces HA prediction from 2012–2020 with the adjusted predictorsfrom the HYbrid Coordinate Ocean Model (HYCOM). In addition, modelsensitivity tests suggest an aggressive riverine nutrient reduction strategy(92 %) is needed to achieve the HA reduction goal of 5000 km 2 .

[学科分类] 大气科学