Publicacións

@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{Cea2022,

title = {Hydraulic Modeling of Bridges in Two-Dimensional Shallow Water Models},

author = {Luis Cea-Gómez and Gabriela Vila and Gonzalo García-Alén-Lores and Jerónimo Puertas-Agudo and Luis Pena-Mosquera},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85130617800&doi=10.1061%2f%28ASCE%29HY.1943-7900.0001992&partnerID=40&md5=c2d1ecf9ae2ed0bc6143847662735276},

doi = {10.1061/(ASCE)HY.1943-7900.0001992},

issn = {07339429},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

journal = {Journal of Hydraulic Engineering},

volume = {148},

number = {8},

publisher = {American Society of Civil Engineers (ASCE)},

abstract = {The backwater effect generated by bridges can significantly increase the risk of flooding. In this work we compare two different methods to include the effect of bridges in two-dimensional (2D) shallow water models. The first method is based on empirical discharge equations that are implemented as internal conditions. The second method is the recently proposed 2D extension of the two-component pressure approach, which accounts for the vertical confinement of the flow. Both approaches are tested and compared using a new set of experimental data obtained in 32 laboratory tests, including four different bridge geometries under different flow conditions. The results show that both methods can reproduce the observed bridge afflux for a wide range of flow conditions, but the two-component pressure approach is less dependent on model calibration. On the other hand, both methods fail to correctly reproduce the 2D water depth patterns observed around the bridge. © 2022 American Society of Civil Engineers.},

note = {cited By 3},

keywords = {2D shallow waters; Backwater effects; Component pressure; Condition; Discharge equations; Floodings; Flow condition; Shallow-water models; Two-component; Two-dimensional, bridge; calibration; comparative study; equation; hydraulics; numerical model; shallow-water equation; water depth, Floods, Water resources},

pubstate = {published},

tppubtype = {article}

}