Mesozooplankton are a crucial link between primary producers and higher trophic levels and play a vital role in marine food webs, biological carbon pumps, and sustaining fishery resources. However, the global distribution of mesozooplankton biomass and the relevant controlling mechanisms remain elusive. We compared four machine learning algorithms (boosted regression trees, random forest, artificial neural network, and support vector machine) to model the spatiotemporal distributions of global mesozooplankton biomass. These algorithms were fit to a compiled dataset of published mesozooplankton biomass observations with corresponding environmental predictors from contemporaneous satellite observations (temperature, chlorophyll, salinity, and mixed layer depth). We found that Random Forest (RF) achieved the best predictive accuracy with R² and RMSE (Root Mean Standard Error) of 0.57 and 0.39, respectively. Also, the global distribution of mesozooplankton biomass predicted by the RF model was more consistent with the observational data than other models. Hence, RF was recommended for mesozooplankton biomass modelling. Our model created a more comprehensive global map of mesozooplankton biomass with general patterns and regional details and reproduced their seasonal variations. It serves as a good reference for validating process-based ecosystem models. The model outputs confirmed that environmental factors, especially surface Chl a, a proxy for prey availability, drove the spatiotemporal distribution of mesozooplankton biomass. A scaling relationship between the mesozooplankton biomass and Chl a was identified and can be used as an emergent constraint for model validation and development. Moreover, our data-driven model predicted that the global mesozooplankton biomass would decrease by 3% by the end of this century under the “business-as-usual” scenarios, albeit the changes vary among regions, potentially reducing fishery production and carbon sequestration. Our study enhanced the ability to predict global mesozooplankton biomass and provided deep insights into the mechanisms controlling the distribution of mesozooplankton.

mesozooplankton; data-driven model; spatiotemporal pattern; random forest; monthly climatology