Papers

@article{hilo_computational_2026,

title = {Computational modelling of hydrodynamic loads on offshore monopiles in concurrent wave and current conditions},

author = {Ali Kareem Hilo-Al-Behadili and Félix Nieto-Mouronte and Gabriel Barajas and Javier L. Lara and Byoung-Kwon Ahn and Antonio J. Álvarez-Naveira and Hrvoje Kozmar},

url = {https://www.sciencedirect.com/science/article/pii/S0029801826000387},

doi = {10.1016/j.oceaneng.2026.124204},

issn = {0029-8018},

year  = {2026},

date = {2026-04-01},

urldate = {2026-08-17},

journal = {Ocean Engineering},

volume = {352},

pages = {124204},

abstract = {Offshore monopile wind-turbine systems face significant design challenges due to complex environmental loading conditions, including wind, waves, current, and their intricate coupling effects. Computational Fluid Dynamics (CFD) simulations of complex nonlinear wave-structure interactions have become essential for understanding offshore systems. However, high-fidelity (HF) CFD analyses are computationally demanding, making it impractical to use them alone for extensive parametric studies. Surrogate models provide a promising alternative, as they can deliver efficient and accurate predictions once trained. This study presents a methodology for combining HF computational models and a data-driven approach to assess hydrodynamic loads on an offshore monopile subjected to waves and current. A three-dimensional numerical wave tank was developed in the OpenFOAM environment and validated using experimental and theoretical data. This model accurately accounts for complex wave-current interactions and the resulting force variations on the monopile. The obtained results indicate that the hydrodynamic forces on the monopile are significantly affected when waves and current act concurrently. To reduce the extensive computational HF simulations, a Gaussian Process Regression (GPR)-based surrogate model was developed using HF simulations sampled via Latin Hypercube Sampling. The surrogate model was trained to predict peak inline and transverse forces for various wave heights, frequencies, and current velocities. The GPR model exhibits high accuracy with R2 = 0.98 (coefficient of determination) and MAE = 0.03 (Mean Absolute Error) for the inline force, and R2 = 0.94 and MAE = 0.01 for the transverse force, thus demonstrating its ability to accurately assess complex nonlinear responses, while reducing the computational demand significantly. These findings provide a practical and applicable solution for offshore structural design, especially during early-stage assessments or probabilistic load evaluations.},

keywords = {Computational fluid dynamics, Current, Gaussian process regression, Hydrodynamic forces, Offshore monopile, Surrogate model, Wave},

pubstate = {published},

tppubtype = {article}

}

@article{farfan-duran_integrating_2025,

title = {Integrating net rainfall calculation in deep learning-based surrogate modeling frameworks for 2D flood prediction},

author = {Juan F. Farfán-Durán and Carlos I. Montalvo-Montenegro and Luis Cea-Gómez and João P. Leitão},

url = {https://www.sciencedirect.com/science/article/pii/S0022169425009709},

doi = {10.1016/j.jhydrol.2025.133632},

issn = {0022-1694},

year  = {2025},

date = {2025-11-01},

urldate = {2025-11-01},

journal = {Journal of Hydrology},

volume = {661},

pages = {133632},

abstract = {This study proposes a novel deep learning (DL)-based surrogate model that incorporates the calculation of net rainfall using the SCS-CN method, providing a flexible framework for evaluating the influence of rainfall events under different antecedent moisture conditions (AMC). The proposed framework involves establishing a ground truth model (Iber-SWMM) and defining the necessary terrain features and rainfall patterns for training the surrogate. A benchmark surrogate model using only gross rainfall, replicating methodologies from previous studies, is also developed for comparison. The trained models are then applied to predict water depth maps using test rainfall patterns under different scenarios, both with and without net rainfall. The results demonstrate that the proposed surrogate model reduces the computational times of Iber-SWMM by 2 to 4 orders of magnitude while outperforming the benchmark surrogate in all the measures. It presents satisfactory accuracy in water depth prediction, with 80% to 95% of predictions within a -0.2 to 0.2 m error range and hit ratios between 0.87 to 0.91 in terms of flooded pixels in the more extreme events. These outcomes are comparable to those achieved by a physics-based model on one of the test events. The study also suggests future lines for refinement.},

keywords = {Deep learning, Flood prediction, Hydrological modeling, Surrogate model, Urban hydrology},

pubstate = {published},

tppubtype = {article}

}

@article{farfan-duran_surrogate-assisted_2024,

title = {Surrogate-Assisted Evolutionary Algorithm for the Calibration of Distributed Hydrological Models Based on Two-Dimensional Shallow Water Equations},

author = {Juan F. Farfán-Durán and Arash Heidari and Tom Dhaene and Ivo Couckuyt and Luis Cea-Gómez},

url = {https://www.mdpi.com/2073-4441/16/5/652},

doi = {10.3390/w16050652},

issn = {2073-4441},

year  = {2024},

date = {2024-01-01},

urldate = {2026-04-20},

journal = {Water},

volume = {16},

number = {5},

pages = {652},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {Distributed hydrological models based on shallow water equations have gained popularity in recent years for the simulation of storm events, due to their robust and physically based routing of surface runoff through the whole catchment, including hill slopes and water streams. However, significant challenges arise in their calibration due to their relatively high computational cost and the extensive parameter space. This study presents a surrogate-assisted evolutionary algorithm (SA-EA) for the calibration of a distributed hydrological model based on 2D shallow water equations. A surrogate model is used to reduce the computational cost of the calibration process by creating a simulation of the solution space, while an evolutionary algorithm guides the search for suitable parameter sets within the simulated space. The proposed methodology is evaluated in four rainfall events located in the northwest of Spain: one synthetic storm and three real storms in the Mandeo River basin. The results show that the SA-EA accelerates convergence and obtains superior fit values when compared to a conventional global calibration technique, reducing the execution time by up to six times and achieving between 98% and 100% accuracy in identifying behavioral parameter sets after four generations of the SA-EA. The proposed methodology offers an efficient solution for the calibration of complex hydrological models, delivering improved computational efficiency and robust performance.},

keywords = {evolutionary algorithm, hydrological model, Optimization, shallow water equations, Surrogate model},

pubstate = {published},

tppubtype = {article}

}

@article{farfan_coupling_2021,

title = {Coupling artificial neural networks with the artificial bee colony algorithm for global calibration of hydrological models},

author = {Juan F. Farfán-Durán and Luis Cea-Gómez},

url = {https://doi.org/10.1007/s00521-020-05601-3},

doi = {10.1007/s00521-020-05601-3},

issn = {1433-3058},

year  = {2021},

date = {2021-07-01},

urldate = {2026-08-07},

journal = {Neural Computing and Applications},

volume = {33},

number = {14},

pages = {8479–8494},

abstract = {Hydrological models are widely used tools in water resources management. Their successful application requires an efficient calibration of the model parameters. Nowadays, there are very powerful global search methods applied to this end, but they have the disadvantage of presenting a high computational cost, because the numerical model to be calibrated needs to be evaluated a large number of times with different parameter sets. In this context, surrogate models can reduce significantly the run time of hydrological models, easing the total computational burden of global search methods. In the present work, we propose and explore the combination of a swarm intelligence-based optimization method, the artificial bee colony algorithm, with a surrogate model based on artificial neural networks in order to calibrate hydrological models. The proposed approach (ABC-ANN) is applied to the calibration and validation of a nine-parameter continuous hydrological model in two basins located in the northwest of Spain. Several aspects of the algorithm are evaluated, including its capability to calibrate the model parameters and its efficiency in terms of CPU time compared to a standard implementation of the ABC algorithm. Results show that the ABC-ANN algorithm is able to identify the location of suitable parameter sets with an accuracy rate within 89 and 99 %, and a reduction in CPU time of more than three orders of magnitude when compared to a sequential implementation. In addition, the frequency distribution of the parameter sets identified gives valuable information about the sensitivity of model output to the input parameters.},

keywords = {Artificial bee colony, Artificial neural networks, Global optimization, hydrological model, Surrogate model, Water resources management},

pubstate = {published},

tppubtype = {article}

}

@article{kusano_reliability_2020,

title = {Reliability based design optimization for bridge girder shape and plate thicknesses of long-span suspension bridges considering aeroelastic constraint},

author = {Ibuki Kusano and Miguel Cid Montoya and Aitor Baldomir-García and Félix Nieto-Mouronte and José Ángel Jurado-Albarracín-Martinón and Santiago Hernández-Ibáñez},

url = {https://www.sciencedirect.com/science/article/pii/S0167610520300866},

doi = {10.1016/j.jweia.2020.104176},

issn = {0167-6105},

year  = {2020},

date = {2020-07-01},

urldate = {2026-08-06},

journal = {Journal of Wind Engineering and Industrial Aerodynamics},

volume = {202},

pages = {104176},

abstract = {Reliability based design optimization (RBDO) for deck shape and thicknesses of the steel plates that form a box girder of long-span suspension bridges is performed considering probabilistic flutter constraint. The entire process was carried out fully computationally including the definition of flutter derivatives. Surrogate models were constructed to estimate the aerodynamic response of the bridge for different deck shapes based on the results from a series of CFD simulations. Some of the aerodynamic coefficients were validated by wind tunnel tests. Flutter derivatives were then estimated using quasi-steady approach for the evaluation of critical flutter velocity. Uncertainty in the aerodynamic coefficients from CFD simulations as well as the extreme wind speed at the bridge site were considered. The formulated methodology was applied to the Great Belt East Bridge.},

keywords = {CFD simulation, Flutter derivatives, Force coefficients, Random variables, RBDO, Reliability analysis, Shape optimization, Surrogate model, Suspension bridge},

pubstate = {published},

tppubtype = {article}

}