Publicacións

@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_regional_2023,

title = {Regional streamflow prediction in northwest Spain: A comparative analysis of regionalisation schemes},

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

url = {https://www.sciencedirect.com/science/article/pii/S2214581823001143},

doi = {10.1016/j.ejrh.2023.101427},

issn = {2214-5818},

year  = {2023},

date = {2023-06-01},

urldate = {2026-08-13},

journal = {Journal of Hydrology: Regional Studies},

volume = {47},

pages = {101427},

abstract = {Study Region: The present study was conducted in 24 watersheds located in the region of Galicia, in the northwest of Spain, covering an extension of approximately 13,000 km2. Study focus: This study is focused on the application and evaluation of different schemes for streamflow Prediction in Ungauged Basins (PUB). The MHIA model (Spanish acronym for Modelo HIdrológico Agregado), is first used to reproduce the observed time series of discharge in several gauged basins. Then, six different regionalisation schemes are applied to transfer the hydrological model parameters to ungauged catchments. For that purpose, we explore and compare two physical similarity, two spatial proximity and two regression-based regionalisation schemes. Output averaging (also known as ensemble modelling) as well as parameter averaging implementations of the physical similarity and spatial proximity methods are analysed. New hydrological insights: The most efficient methods are those based on output averaging, with acceptable success rates (SR) in 88% of the cases. On the other hand, the parameter averaging-based methods have the lowest SR. The methods based on spatial proximity output averaging provide the best performance when the receptor basin has a sufficient number of nearby donor basins. On the other hand, the methods based on physical similarity output averaging show a better performance in areas where there is a low density of donor catchments. The regression-based methods showed the lowest performance in all cases. The existence of correlations between the performance of the regionalisation schemes and the area of the receptor catchments was observed, with higher performances in large basins than in small basins.},

keywords = {Artificial neural networks, hydrological model, Physical similarity, Regionalisation, Spatial proximity, Ungauged basin},

pubstate = {published},

tppubtype = {article}

}

@article{farfan_improving_2023,

title = {Improving the predictive skills of hydrological models using a combinatorial optimization algorithm and artificial neural networks},

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

url = {https://doi.org/10.1007/s40808-022-01540-1},

doi = {10.1007/s40808-022-01540-1},

issn = {2363-6211},

year  = {2023},

date = {2023-03-01},

urldate = {2026-08-07},

journal = {Modeling Earth Systems and Environment},

volume = {9},

number = {1},

pages = {1103–1118},

abstract = {Ensemble modelling is a numerical technique used to combine the results of a number of different individual models in order to obtain more robust, better-fitting predictions. The main drawback of ensemble modeling is the identification of the individual models that can be efficiently combined. The present study proposes a strategy based on the Random-Restart Hill-Climbing algorithm to efficiently build ANN-based hydrological ensemble models. The proposed technique is applied in a case study, using three different criteria for identifying the model combinations, different number of individual models to build the ensemble, and two different ANN training algorithms. The results show that model combinations based on the Pearson coefficient produce the best ensembles, outperforming the best individual model in 100% of the cases, and reaching NSE values up to 0.91 in the validation period. Furthermore, the Levenberg-Marquardt training algorithm showed a much lower computational cost than the Bayesian regularisation algorithm, with no significant differences in terms of accuracy.},

keywords = {Artificial neural networks, Ensemble model, hydrological model, Water resources},

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}

}