Browsing by Author "Cortés, Hermilo"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Groundwater parameters estimation: A hybrid approach of convolutional layers with asynchronous and distributed bio-inspired algorithms
    (2025) Tesen, Kiara; Cortés, Hermilo; Vicuña, Sebastián; Molina-Perez, Edmundo; Suárez, Francisco
    This 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
  • Thumbnail Image
    Item
    Using a robust decision making (RDM) approach to explore current and future vulnerabilities of a semi-arid coastal basin: a case study of the Quilimarí basin in Chile
    (2025) Poblete López, David Nicolás; Vicuña Díaz, Sebastián; Aedo, Sebastián; Molina-Pérez, Edmundo; Cortés, Hermilo; Melo Contreras, Óscar; Ocampo-Melgar, Anahí; Tesen Arambulo, Kiara Aimee; Suárez Poch, Francisco Ignacio; Herane Espinosa, Juan Pablo; Meza, Francisco Javier; Duarte Becerra, Katherine Mariela; González Santander, Diego Nicolás; Leray, Sarah; Williams, Megan Elizabeth; Gaxiola, Aurora; Alfaro, Gabriela; Morales Moraga, David Alejandro
    Climate change, land use alterations, human activities, and regulatory frameworks all contribute to deep uncertainties that define water security in hydrological basins. This is particularly significant in drylands where water scarcity limits agricultural productivity. Robust Decision Making (RDM) is an effective approach for identifying strategies that perform well under uncertainty across a wide range of possible futures. One of RDM’s key strengths is its ability to guide decisions without relying on precise future predictions, emphasizing robustness rather than optimality. This study focuses on the Quilimarí River basin, located in the semi-arid coastal region of Chile, where groundwater is the primary water source. Small coastal communities rely on shallow boreholes, which have become brackish due to saline intrusion. We present the initial stages of implementing an RDM process with key local decisionmakers to explore the expected impacts of socio-hydrological stressors and uncertainties on the main water-dependent objectives. Different levels and approaches of participation during the 2 years of RDM process enabled the identification of critical concerns raised by local stakeholders and government agencies, the uncertainties likely to affect these issues, and potential actions for improving outcomes. To explore current and future vulnerabilities we used a WEAP-MODFLOW water resources model that integrates data on extraction wells, irrigation schemes, agricultural production, potable water supply, and associated costs, including saline intrusion processes. The model simulates trade-offs between different objectives, such as groundwater extraction for agriculture and job creation versus potable water for rural communities. The vulnerability exploration scenarios suggest a complex future, with up to a 40% reduction in precipitation and increased water demand from household and tourism use. To cope with the impacts associated with these global change scenarios a series of adaptation options were tested. Overall, desalination emerged as a favorable option for local human consumption demands, although tested only under basin-level metrics. This study illustrates valuable insights on how the water management strategies under uncertainty can benefit from local engagement towards testing robust decisions in arid and semi-arid coastal basis around the world.