Dispersion modeling is crucial for marine environmental modeling and management. However, operational applications require a practical balance between model accuracy and computational efficiency. To address this challenge, we develop and validate a generalized cell-based model (CBM) framework for contaminant dispersion. The framework enhances physical realism through a novel three-dimensional (3D) transport model and a formulation for chemical reactions. Additionally, a new discretization-based approach is proposed to robustly relate the CBM’s diffusion coefficient to its partial differential equation counterpart, improving performance in scenarios with sharp gradients of the concentration level. The proposed framework’s favorable trade-off between accuracy and efficiency is demonstrated in a comparative simulation study, where the 3D CBM reduces computation time from 14.72 s to 0.06 s compared to finite-element methods (FEM), with a relative Root Mean Square Error (RMSE) of 7.67%. To demonstrate its practical applicability, the proposed framework is validated using ocean current and nitrate concentration data from the Copernicus Marine Environment Monitoring Service. After identifying a key model parameter from the data, the model’s forward predictions accurately reproduce the observed nitrate concentration patterns, confirming its suitability for operational scenarios.

In practice, achieving a balance between accuracy, stability, and computational efficiency in modeling contaminant dispersion in marine environments remains challenging due to complex physical dynamics and numerical constraints. To address these challenges, an enhanced cell-based model (CBM) is developed and applied to simulate pollutant transport in the ocean. The CBM discretizes the spatial domain into uniform cells, resulting in a naturally parallelizable structure, and characterizes the transport process by incorporating both water flow-driven convection and diffusion effects. Moreover, two approaches are proposed for estimating the diffusion coefficient, and their performance is compared to a first-order upwind scheme finite-difference method (FDM) solution. Finally, the CBM is comprehensively compared with both the FDM and the finite-element method (FEM) solvers under varying spatial and temporal resolutions. Simulation results show that the CBM is less affected by the Courant-Friedrichs-Lewy (CFL) conditions and demonstrates stable convergence where the FDM fails or requires stricter settings. In addition, the CBM offers a favorable trade-off between accuracy and computational efficiency under coarse configurations. These results indicate that the CBM provides a reliable foundation for dynamic modeling and integration with learning-based frameworks in marine environment simulations.

Most existing work on direct data-driven stabilization considers the equilibrium at the origin. When the desired equilibrium is not the origin, existing data-driven approaches often require performing coordinate transformation, or adding integrator action to the controller. As an alternative, this work addresses data-driven state feedback stabilization of any given assignable equilibrium via dissipativity theory. We show that for a polynomial system, if a data-driven stabilizer can be designed to render the origin globally asymptotically stable, then by modifying the stabilizer, we obtain a stabilizer for any given assignable equilibrium.

This paper proposes a reinforcement learning approach to the output synchronization problem for heterogeneous leader-follower multi-agent systems, where the system dynamics of all agents are completely unknown. First, to solve the challenge caused by unknown dynamics of the leader, we develop an experience-replay learning method to estimate the leader’s dynamics, which only uses the leader’s past state and output information as training data. Second, based on the newly estimated leader’s dynamics, we design an event-triggered observer for each follower to estimate the leader’s state and output. Furthermore, the experience-replay learning method and the event-triggered leader observer are co-designed, which ensures the convergence and Zeno behavior exclusion. Subsequently, to free the followers from reliance on system dynamics, a data-driven adaptive dynamic programming (ADP) method is presented to iteratively derive the optimal control gains, based on which we design a policy iteration (PI) algorithm for output synchronization. Finally, the proposed algorithm’s performance is validated through a simulation.

Marine litter pollution is a major environmental threat due to the widespread presence of plastics and their detrimental impact on marine life and human health. There is a need for autonomous systems with computer vision to help clean the oceans. This study compares the latest state-of-the-art You Only Look Once (YOLO) models YOLOv9 - YOLOv12 in an underwater object detection setting in terms of accuracy, computational speed, and architecture complexity. We specifically focus on the smallest versions of these architectures, due to the real-time constraints of the setting. Multiple underwater datasets are combined to obtain a wide representation of underwater conditions and marine objects. The findings provide valuable insights into selecting and optimizing object detection architectures for underwater litter detection, contributing to monitoring marine ecosystems and addressing marine pollution. This work can be used as a building ground for further improving underwater object detection systems.

Lyapunov’s indirect methodLyapunovindirect method is one of the oldest and most popular approaches to model-based controller design for nonlinear systemsNonlinearsystem. When the explicit model of the nonlinear systemNonlinearsystem is unavailable for designing such a linear controller, finite-length off-line data is used to obtain a data-based representation of the closed-loop system, and a data-driven linear control law is designed to render the considered equilibrium locally asymptotically stable. This work presents a systematic approach for data-driven linear stabilizer design for continuous-time and discrete-time general nonlinear systemsNonlinearsystem. Moreover, under mild conditions on the nonlinear dynamics, we show that the region of attractionRegion of attraction of the resulting locally asymptotically stable closed-loop system can be estimated using data.

In this paper, we analyze the regret incurred by a computationally efficient exploration strategy, known as naive exploration, for controlling unknown partially observable systems within the Linear Quadratic Gaussian (LQG) framework. We introduce a two-phase control algorithm called LQG-NAIVE, which involves an initial phase of injecting Gaussian input signals to obtain a system model, followed by a second phase of an interplay between naive exploration and control in an episodic fashion. We show that LQG-NAIVE achieves a regret growth rate of Õ(√T), i.e., O(√T) up to logarithmic factors after T time steps, and we validate its performance through numerical simulations. Additionally, we propose LQG-IF2E, which extends the exploration signal to a 'closed-loop' setting by incorporating the Fisher Information Matrix (FIM). We provide compelling numerical evidence of the competitive performance of LQG-IF2E compared to LQG-NAIVE.

We consider data-driven control of input-affine systems via approximate nonlinearity cancellation. Data-dependent semi-definite program is developed to characterize the stabilizer such that the linear dynamics of the closed-loop systems is stabilized and the influence of the nonlinear dynamics is decreased. Because of the additional nonlinearity brought by the state-dependent input vector field, nonlinearity cancellation is more difficult to achieve. We show that under some assumptions on the nonlinearity, the nonlinearity cancellation control approach can render the equilibrium locally asymptotically stable even if the additional nonlinearity is neglected. Data-based estimation of the region of the attraction is also presented.

A technique to design controllers for nonlinear systems from data consists of letting the controllers learn the nonlinearities, cancel them out and stabilize the closed-loop dynamics. When control and nonlinearities are unmatched, the technique leads to an approximate cancellation and local stability results are obtained. In this paper, we show that, if the system has some structure that the designer can exploit, an iterative use of the data leads to a globally stabilizing controller even when control and nonlinearities are unmatched.