This research develops a surrogate modeling framework to efficiently analyze and optimize a proposed pump and gate system designed to mitigate compound flooding in the Clear Lake region, Texas. Traditional numerical hydraulic models are often computationally expensive for large number of simulations. As probabilistic assessments can require $O(10^3)$ to O(10^5) runs, a cheaper alternative would be necessary for robust probabilistic assessment. This study addresses this limitation by developing a deep-learning surrogate to approximate the complex hydrodynamic behavior.

The methodology involved three main stages. First, a 1D HEC-RAS model of the Clear Lake system was adapted to serve as the physics-based "ground truth" generator. Second, this model was used to generate a training dataset of 2,400 simulations. This was achieved by systematically sampling key infrastructure design parameters (gate width $W_g$, number of pumps $n_p$, and activation levels $h_{on}$) alongside a wide range of synthetic compound flood forcings (inflow hydrographs and downstream storm surge boundaries).

Third, three distinct Long Short-Term Memory (LSTM) network architectures (Models A, B, and C) were developed to compare different data encoding strategies. Model A, a direct sequence-to-sequence (seq2seq) model, was provided with all dynamic inputs, including the known pump discharge time series ($Q_{pump}$). Model B tested the model's ability to infer dynamics by replacing the $Q_{pump}$ time series with static design parameters ($n_p$, $h_{on}$). Model C used an autoregressive structure, feeding its own past water level predictions back as inputs to dynamically infer the pump response.

The results demonstrate that the fully-informed LSTM (Model A) can successfully learn and reproduce the governing hydrodynamic processes with very high accuracy. However, models that attempted to infer dynamic behavior from static design parameters (Models B and C) show reduced performance. These models particularly struggled to capture the sharp, transient effects of pump (de)activation, leading to overly smoothed predictions. This study concludes that while LSTMs are capable of learning the physical patterns of the system. The main challenge lies in feature encoding, specifically, enabling the model to capture complex, dynamic responses from static inputs. The framework demonstrates the potential of LSTMs, but emphasizes that how the data is represented is the key factor in developing a surrogate model suitable for design optimization.
... Read more

Previous studies show that climate change effects and anthropogenic disturbances are having an increasingly strenuous effect on the performance of the coastal system of Sisal, a rural fishing village in the state of Yucatán, Mexico. Resilience has been a crucial component for these studies, as it presents the system's ability to react and adapt to environmental hazards and human interventions. In recent years, several research initiatives have aimed to assess the resilience of Sisal's coastal system through the use of previously identified resilience index calculations. However, these indices lack the ability to quantify disparities of resilience on a local scale. Furthermore, previous studies focus solely on the technical aspects of resilience, and therefore fall short on defining other relevant aspects of the term.

Consequently, this research project aimed to understand Sisal's coastline by understanding the multi-faceted definitions of resilience by analysing the socio-economic and technical factors impacting the coastal system. The study involved examining both its historical context, as well as potential future trends and developments.

This was done through a thorough evaluation of different aspects of the coast, a storm impact study and a social analysis. The findings of these studies are subsequently incorporated into a comprehensive web-tool, providing experts, policymakers, and community members with clear-cut and valuable information on the current resilience of Sisal's coastline.

The findings of the research present that the coastal resilience of Sisal is highly negatively impacted by human interventions along the coast, predominantly causing inadequate resilience performances on profiles with significant anthropogenic perturbations and generally along the coastline westwards of Sisal's port. Current coastal management policies are considered ineffective to deal with these developments, which is among others caused by exclusive decision-making processes and ambiguous governmental policies. Changes in coastal management strategies are therefore needed to effectively deal with future threats of environmental hazards and human interference. Ultimately, resulting in improved coastal and community resilience. ... Read more