Static and auto-regressive neural emulation of phytoplankton biomass dynamics from physical predictors in the global ocean

2026-02-04

AI Summary

Accurately simulating global oceanic phytoplankton biomass is hindered by inadequate parameterizations, sparse observations, and the inherent complexity of underlying biogeochemical processes. This work proposes a deep learning–based modeling framework that integrates satellite-derived observations with physical environmental variables through both static and autoregressive UNet architectures to effectively capture seasonal to interannual variability in phytoplankton dynamics. Experimental results demonstrate that the UNet outperforms benchmark models—including CNN, ConvLSTM, and 4CastNet—in reconstructing the spatiotemporal distribution of phytoplankton biomass. Moreover, its autoregressive variant enables high-accuracy short-term forecasts up to five months ahead, substantially enhancing the capability to simulate dynamic changes in marine ecosystems.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Phytoplankton is the basis of marine food webs, driving both ecological processes and global biogeochemical cycles. Despite their ecological and climatic significance, accurately simulating phytoplankton dynamics remains a major challenge for biogeochemical numerical models due to limited parameterizations, sparse observational data, and the complexity of oceanic processes. Here, we explore how deep learning models can be used to address these limitations predicting the spatio-temporal distribution of phytoplankton biomass in the global ocean based on satellite observations and environmental conditions. First, we investigate several deep learning architectures. Among the tested models, the UNet architecture stands out for its ability to reproduce the seasonal and interannual patterns of phytoplankton biomass more accurately than other models like CNNs, ConvLSTM, and 4CastNet. When using one to two months of environmental data as input, UNet performs better, although it tends to underestimate the amplitude of low-frequency changes in phytoplankton biomass. Thus, to improve predictions over time, an auto-regressive version of UNet was also tested, where the model uses its own previous predictions to forecast future conditions. This approach works well for short-term forecasts (up to five months), though its performance decreases for longer time scales. Overall, our study shows that combining ocean physical predictors with deep learning allows for reconstruction and short-term prediction of phytoplankton dynamics. These models could become powerful tools for monitoring ocean health and supporting marine ecosystem management, especially in the context of climate change.

Problem

• phytoplankton biomass
• spatio-temporal dynamics
• biogeochemical modeling
• oceanic processes
• environmental predictors

Innovation

• UNet
• auto-regressive modeling
• phytoplankton biomass prediction
• deep learning
• ocean biogeochemistry