Multifidelity digital twin for real-time monitoring of structural dynamics in aquaculture net cages

Abstract

As the global population grows and climate change intensifies, sustainable food production is critical. Marine aquaculture offers a viable solution, providing a sustainable protein source. However, the industry's expansion requires novel technologies for remote management and autonomous operations. Digital twin technology can advance the aquaculture industry, but its adoption has been limited. Fish net cages, which are flexible floating structures, are critical yet vulnerable components of aquaculture farms. Exposed to harsh and dynamic marine environments, the cages experience significant loads and risk damage, leading to fish escapes, environmental impacts, and financial losses. We propose a multifidelity surrogate modeling framework for integration into a digital twin for real-time monitoring of aquaculture net cage structural dynamics under stochastic marine conditions. Central to this framework is the nonlinear autoregressive Gaussian process method, which learns complex, nonlinear cross-correlations between models of varying fidelity. It combines low-fidelity simulation data with a small set of high-fidelity field sensor measurements, which offer the real dynamics but are costly and spatially sparse. Validated at the SINTEF ACE fish farm in Norway, our digital twin receives online metocean data and accurately predicts net cage displacements and mooring line loads, aligning closely with field measurements. The proposed framework is beneficial where application-specific data are scarce, offering rapid predictions and real-time system representation. The developed digital twin prevents potential damages by assessing structural integrity and facilitates remote operations with unmanned underwater vehicles. Our work also compares GP and GCNs for predicting net cage deformation, highlighting the latter's effectiveness in complex structural applications.

Figures (6)

• Figure 1: Real-time monitoring and remote fish farm management using digital twin technology. The structural response of a net cage to dynamic marine environments is modeled using data from varying fidelity sources, including low-fidelity numerical simulations and high-fidelity field sensor measurements. A digital twin of the physical net cage is developed using the proposed multifidelity framework, central to which is the Nonlinear Autoregressive Gaussian Process (NARGP) method perdikaris2017nonlinear.
• Figure 2: Net cage numerical representation and field sensor placement. (a) Detailed view of net cage's critical components. (b) The net cage is discretized into 321 nodes for FhSim numerical simulations. It consists of 10 layers, with the first 32 nodes forming the first layer. Node 321 is at the bottom, connecting all nodes of the 10th layer. c) The net cage in the FhSim simulation environment, showing deformation under wave and current excitation. (d) Top view of the fish farm highlighting net cage 11, which accommodates the sensors. A buoy located 400 meters from the net cage measures waves and currents, with the main flow direction indicated. (e) Close-up of net cage 11 showing sensor locations: 5 load shackles measuring mooring line forces and 3 depth sensors measuring net displacement. (f) Side view of the net cage illustrating sensor locations along its depth.
• Figure 3: Multifidelity digital twin for SINTEF ACE fish farm.(a) The digital twin's workflow is illustrated. (b) The training stage of the low-fidelity GP models using data from FhSim simulations is described. (c) The training stage of the high-fidelity GP models based on multifidelity data is illustrated.
• Figure 4: Multifidelity framework predictions for mooring line loads. Scatter plots (a), (d), (g) show the low-fidelity GP posterior mean against load shackle measurements. Color scale indicates log count density of data points, with lighter colors representing higher concentrations. The dashed diagonal line signifies perfect prediction accuracy; the red line is the best-fit trend. Scatter plots (b), (e), (h) show the multifidelity GP model predictions against sensor measurements. Plots (c), (f), (i) display predictions over a 36-hour period, excluding the data used for training. Low-fidelity GP posterior mean deviates significantly from actual measurements. Multifidelity GP posterior aligns closely with real observations, capturing the overall trend despite some oscillatory behavior deviations.
• Figure 5: Multifidelity framework predictions for net cage displacement. Scatter plots (a), (d), (g) contrast the predictions from the low-fidelity GP model with the depth sensor measurements. The broad dispersion of data points and the notable deviation of the red best-fit line from the dashed diagonal line underscore the model's limited accuracy. Scatter plots (b), (e), (h) for the multifidelity GP model. Data points cluster more closely around the dashed line, and the red best-fit line aligns more precisely with the diagonal, indicating enhanced predictive accuracy. The MAE values annotated on these plots quantitatively highlight the multifidelity model's superiority over the low-fidelity model. Plots (c), (f), (i) show the temporal comparison of predicted and actual net cage displacements over a specific period (January 18 to January 27, 2020). The low-fidelity GP model (blue line) exhibits substantial deviations from the actual measurements (green line), particularly for depth sensors #1 and #3. The multifidelity GP model (red line) significantly mitigates these discrepancies, closely mirroring the actual measurements and capturing the underlying trend with greater fidelity.