Groundwater parameters estimation: A hybrid approach of convolutional layers with asynchronous and distributed bio-inspired algorithms

Simple item page
dc.article.number112098
dc.catalogadorpau
dc.contributor.authorTesen, Kiara
dc.contributor.authorCortés, Hermilo
dc.contributor.authorVicuña, Sebastián
dc.contributor.authorMolina-Perez, Edmundo
dc.contributor.authorSuárez, Francisco
dc.date.accessioned2025-09-12T13:59:39Z
dc.date.available2025-09-12T13:59:39Z
dc.date.issued2025
dc.description.abstractThis research focuses on aquifer hydraulic parameters estimation using bio-inspired algorithms since they can tackle groundwater model non-linearities. We propose two novel hybrid frameworks that combine the advantages of convolutional layers (CL) to enhance pattern recognition with heuristic search of Particle Swarm Optimization (PSO) and Differential Evolution (DE) algorithms. These integrations are implemented using an asynchronous and distributed approach to address efficiency issues in large-scale problems, resulting in ADPSO-CL (Asynchronous and Distributed Particle Swarm Optimization with Convolutional Layers) and ADDE-CL (Asynchronous and Distributed Differential Evolution with Convolutional Layers). The distributed method employs virtual machines, where a server generates and assigns particles to workers, which run in parallel with asynchronous iterative solution exchanges. We assess different algorithm configurations in an integrated water management model by coupling two software: Water Evaluation and Planning (WEAP) and MODFLOW. Results indicate that ADPSO-CL outperforms ADDE-CL by demonstrating more stable asynchronous communication, with fewer incomplete experiments (more than one worker was disconnected before completing all iterations), 33% in contrast to 71%. Additionally, produces results closer to the expected values, with mean absolute percentage error (MAPE) values of 78.25% for hydraulic conductivity and 55.56% for specific yield, compared to 299% and 209% in ADDE-CL. Moreover, ADPSO-CL has the fastest convergence rate, achieving efficient results in about half of the total iterations. This study introduces a novel and scalable architecture for intricate simulation–optimization problems, demonstrating its potential for future applications in real-world water resources planning and management
dc.format.extent13 páginas
dc.fuente.origenSRIA
dc.identifier.doi10.1016/j.engappai.2025.112098
dc.identifier.issn1873-6769
dc.identifier.urihttps://doi.org/10.1016/j.engappai.2025.112098
dc.identifier.urihttps://www.sciencedirect.com/science/article/pii/S0952197625021062?via%3Dihub
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/105672
dc.information.autorucEscuela de Ingeniería; Tesen, Kiara; S/I; 1101925
dc.information.autorucEscuela de Ingeniería; Vicuña, Sebastián; 0000-0001-6971-0068; 7907
dc.information.autorucEscuela de Ingeniería; Suárez, Francisco; 0000-0002-4394-957X; 15891
dc.language.isoen
dc.nota.accesocontenido parcial
dc.revistaEngineering Applications of Artificial Intelligence
dc.rightsacceso restringido
dc.subjectAquifer parameters estimation
dc.subjectInverse problem
dc.subjectParticle Swarm Optimization
dc.subjectDifferential Evolution
dc.subjectSimulation–optimization model
dc.subject.ddc620
dc.subject.deweyIngenieríaes_ES
dc.subject.ods06 Clean water and sanitation
dc.subject.odspa06 Agua limpia y saneamiento
dc.titleGroundwater parameters estimation: A hybrid approach of convolutional layers with asynchronous and distributed bio-inspired algorithms
dc.typeartículo
dc.volumen161
sipa.codpersvinculados1101925
sipa.codpersvinculados7907
sipa.codpersvinculados15891
Files
Collections
Artículos de revistas