Predicting ecosystem components in the Gulf of Mexico and their responses to climate variability with a dynamic Bayesian network model

Abstract

The Gulf of Mexico is an ecologically and economically important marine ecosystem that is affected by a variety of natural and anthropogenic pressures. These complex and interacting pressures, together with the dynamic environment of the Gulf, present challenges for the effective management of its resources. The recent adoption of Bayesian networks to ecology allows for the discovery and quantification of complex interactions from data after making only a few assumptions about observations of the system. In this study, we apply Bayesian network models, with different levels of structural complexity and a varying number of hidden variables to account for uncertainty when modeling ecosystem dynamics. From these models, we predict focal ecosystem components within the Gulf of Mexico. The predictive ability of the models varied with their structure. The model that performed best was parameterized through data-driven learning techniques and accounted for multiple ecosystem components’ associations and their interactions with human and natural pressures over time. Then, we altered sea surface temperature in the best performing model to explore the response of different ecosystem components to increased temperature. The magnitude and even direction of predicted responses varied by ecosystem components due to heterogeneity in driving factors and their spatial overlap. Our findings suggest that due to varying components’ sensitivity to drivers, changes in temperature will potentially lead to trade-offs in terms of population productivity. We were able to discover meaningful interactions between ecosystem components and their environment and show how sensitive these relationships are to climate perturbations, which increases our understanding of the potential future response of the system to increasing temperature. Our findings demonstrate that accounting for additional sources of variation, by incorporating multiple interactions and pressures in the model layout, has the potential for gaining deeper insights into the structure and dynamics of ecosystems.

Using Bayesian Networks to Investigate the Influence of Subseasonal Arctic Variability on Midlatitude North Atlantic Circulation

“…A hidden variable (HV) can be used to capture the underlying state of a time series or represent a variable of interest to the network that cannot be directly observed (Murphy 2012). Hidden variables may represent something of importance theoretically to the modeled system, or a process or driver that shares interdependencies with the variables but was not explicitly constrained within the model structure for one reason or another (Trifonova et al 2017). This can occur when no data exist or when the model approach dictates the exclusion of system components; for example, a model where a set of symptoms is observed, but the disease is unknown (Murphy 2012).…”

“…Given the challenges associated with identifying AA-midlatitude linkages due to noisy internal dynamics and the time-constrained nature of AA processes, potential improvements in model accuracy make hidden variables worth consideration. Graphical models with hidden variables inferred from observed data have been largely untouched in climate science studies, but their capabilities have been explored and proven in ecological system analyses (Trifonova et al 2015(Trifonova et al , 2017(Trifonova et al , 2019Uusitalo et al 2018).…”

Early Warning Evaluation of Tuberculosis and Meteorological Factors in Shanxi Province based on Dynamic Bayesian Network

“…DBN is used to describe the dynamic process of random variables, and X t represents the state of node variables at time T. We de ne Dynamic Bayesian network as DBN (B 0 ,B → ) 22 . The Bayes at the initial time obtained by taking X 0 as the node is represented by B 0 , and B→ is the Bayes fragment at the transfer network, and the node includes x t ∪x t+1 , x t represents the current state, with no parent node 23 ; x t+1 represents the state at the next time with conditional probability P (x t+1 /parent(x t+1 ). The transition probability distribution of transfer network B → is de ned as follows:…”

Use of Our Future Seas: Relevance of Spatial and Temporal Scale for Physical and Biological Indicators

“…Bayesian network models have also been applied to investigate the consequences of fisheries catch, temperature and primary productivity scenarios on different fish and zooplankton species, outlining the importance of trophic interactions and the spatial relationship between neighboring areas (Trifonova et al, 2017). The success of using a hidden variable to identify indicator species of key importance to the ecosystem dynamics that has also been helpful in illuminating the possible mechanisms behind functional ecosystem changes has been shown for the North Sea (Trifonova et al, 2015) but also for other systems, e.g., Barents Sea (Uusitalo et al, 2018) and Gulf of Mexico (Trifonova et al, 2019). Bayesian hierarchical hurdle and zero-inflated joint models with integrated nested Laplace approximation (INLA) have been used to model the common spatial habitat between predators and prey and more recently, to predict the "ecological costs" in population terms, following the projected effects of climate change (Sadykova et al, 2020).…”