The Laurentian Great Lakes, one of the world’s largest surface freshwater systems, pose a modeling challenge in seasonal forecast and climate projection. While physics-based hydrodynamic modeling is a fundamental approach, improving the forecast accuracy remains critical. In recent years, machine learning (ML) has quickly emerged in geoscience applications, but its application to the Great Lakes hydrodynamic prediction is still in its early stages. This work is the first one to explore a deep learning approach to predicting spatiotemporal distributions of the lake surface temperature (LST) in the Great Lakes. Our study shows that the Long Short-Term Memory (LSTM) neural network, trained with the limited data from hypothetical monitoring networks, can provide consistent and robust performance. The LSTM prediction captured the LST spatiotemporal variabilities across the five Great Lakes well, suggesting an effective and efficient way for monitoring network design in assisting the ML-based forecast. Furthermore, we employed an explainable artificial intelligence (XAI) technique named SHapley Additive exPlanations (SHAP) to uncover how the features impact the LSTM prediction. Our XAI analysis shows air temperature is the most influential feature for predicting LST in the trained LSTM. The relatively large bias in the LSTM prediction during the spring and fall was associated with substantial heterogeneity of air temperature during the two seasons. In contrast, the physics-based hydrodynamic model performed better in spring and fall yet exhibited relatively large biases during the summer stratification period. Finally, we developed a statistical integration of the hydrodynamic modeling and deep learning results based on the Best Linear Unbiased Estimator (BLUE). The integration further enhanced prediction accuracy, suggesting its potential for next-generation Great Lakes forecast systems.

Current numerical methods for simulating biophysical processes in aquatic environments are typically constructed in a grid-based Eulerian framework or as an individual-based model in a particle-based Lagrangian framework. Often, the biogeochemical processes and physical (hydrodynamic) processes occur at different time and space scales, and changes in biological processes do not affect the hydrodynamic conditions. Therefore, it is possible to develop an alternative strategy to grid-based approaches for linking hydrodynamic and biogeochemical models that can significantly improve computational efficiency for this type of linked biophysical model. In this work, we utilize a new technique that links hydrodynamic effects and biological processes through a property-carrying particle model (PCPM) in a Lagrangian/Eulerian framework. The model is tested in idealized cases and its utility is demonstrated in a practical application to Sandusky Bay. Results show the integration of Lagrangian and Eulerian approaches allows for a natural coupling of mass transport (represented by particle movements and random walk) and biological processes in water columns which is described by a nutrient-phytoplankton-zooplankton-detritus (NPZD) biological model. This method is far more efficient than traditional tracer-based Eulerian biophysical models for 3-D simulation, particularly for a large domain and/or ensemble simulations.

The filamentous green alga Cladophora grows to nuisance proportions in Lake Ontario. Stimulated by high phosphorus concentrations, nuisance growth results in the degradation of beaches and clogging of industrial water intakes with attendant loss of beneficial uses. We develop a multi-module bioavailable phosphorus model to examine the efficacy of phosphorus management strategies in mitigating nuisance algal growth. The model platform includes modules simulating hydrodynamics (FVCOM), phosphorus-phytoplankton dynamics (GEM) and Cladophora growth (GLCMv3). The model is applied along a 25 km stretch of the Lake Ontario nearshore, extending east from Toronto, ON and receiving effluent from three wastewater treatment plants. Simulation results identify the Duffin Creek wastewater treatment plant effluent as a driving force for nuisance conditions of Cladophora growth, as reflected in effluent bioavailable phosphorus concentrations and the dimensions of the plant’s phosphorus footprint. Simulation results demonstrate that phosphorus removal by chemically enhanced secondary treatment is insufficient to provide relief from nuisance conditions. Tertiary treatment (chemically enhanced secondary treatment with ballasted flocculation) is shown to eliminate phosphorus-saturated conditions associated with the Duffin Creek wastewater treatment plant effluent, providing local relief from nuisance conditions. Management guidance presented here has wider application at sites along the highly urbanized Canadian nearshore of Lake Ontario.

The emerging shift in Great Lakes management from offshore to nearshore waters will require attention to complexities of coastal hydrodynamics and biogeochemical transformations. Emphasizing hydrodynamics, this work resolves transport processes in quantifying discharge plume and pollutant of concern (POC) footprint dimensions, the latter being the portion of the plume where water quality standards are not met. A generic approach, isolated from pollutant-specific biokinetics, provides first-approximation estimates of the footprint area. A high-resolution, linked hydrodynamic-tracer model is applied at a site in the Greater Toronto Area on Lake Ontario. Model results agree with observed meteorological and hydrodynamic conditions and satisfactorily simulate plume dimensions. Footprints are examined in the context of guidelines for regulatory mixing zone size and attendant loss of beneficial use. We demonstrate that the ratio of the water quality standard to the POC concentration at discharge is a key determinant of footprint dimensions. Footprint size for traditional pollutants (ammonia, total phosphorus) meets regulatory guidelines; however, that for soluble reactive phosphorus, a presently unattended pollutant, is ~1–2 orders of magnitude larger. This suggests that it may be necessary to upgrade treatment technologies to maintain consistency with regulatory guidelines and mitigate manifestations of the eutrophication-related soluble reactive phosphorus POC.

Accurate estimates for the lake surface temperature (LST) of the Great Lakes are critical to understanding the regional climate. Dedicated lake models of various complexity have been used to simulate LST but they suffer from noticeable biases and can be computationally expensive. Additionally, the available historical LST datasets are limited by either short temporal coverage (<30 years) or lower spatial resolution (0.25° × 0.25°). Therefore, in this study, we employed a deep learning model based on Long Short-Term Memory (LSTM) neural networks to produce a daily LST dataset for the Great Lakes that spans an unparalleled 42 years (1979–2020) at a spatial resolution of ~1 km. In our dataset, the Great Lakes are represented by ~33,000 unstructured grid points and the LSTM training incorporated the information from each grid point. The LSTM was trained with seven meteorological variables from reanalysis data as feature variables and the LST from a historical satellite-derived dataset as the target variable. The LSTM was able to capture the spatial heterogeneity of LST in the Great Lakes well and exhibited high correlation (≥0.92) and low bias (limited to ±1.5 °C) for the temporal evolution of LST during the training (1995–2020) and testing (1979–1994) periods.