Characterization of seawater intrusion based on machine learning and implications for offshore management under shared socioeconomic paths

Yang, Haitao; Sun, Hongbing; Liu, Tao; Yang, Xiao; Yang, Fan; Jiao, Jing

doi:10.1016/j.jhydrol.2023.129862

Cited by 7 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Climate-driven modifications in recharge and sea level rise are major drivers of saltwater intrusion, with rising sea levels affecting a large percentage of coastal watersheds [17]. Seawater intrusion simulation is a valuable tool for understanding and managing the movement of saltwater into coastal aquifers [18].…”

Section: Introductionmentioning

confidence: 99%

Climatic Modeling of Seawater Intrusion in Coastal Aquifers: Understanding the Climate Change Impacts

Lyra,

Loukas,

Sidiropoulos

et al. 2024

Hydrology

View full text Add to dashboard Cite

The study examines the impacts of climate change and sea level rise on coastal aquifers, focusing on the influence of the components of the water cycle on seawater intrusion, and the evolution of the phenomenon in the future. The simulation of coastal water resources was performed using an integrated modeling system (IMS), designed for agricultural coastal watersheds, which consists of inter-connected models of surface hydrology (UTHBAL), groundwater hydrology (MODFLOW), and seawater intrusion (SEAWAT). Climatic models for the adverse impact scenario (RCP8.5) and the medium impact scenario (RCP4.5) of climate change were used. Transient boundary head conditions were set to the coastal boundary, to dynamically represent the rise in sea level due to climate change. The response of groundwater in the coastal Almyros Basin, located in central Greece, was simulated from 1991 to 2100. The findings indicate that seawater intrusion will be advanced in the future, in both climate change scenarios. The models show varying patterns in groundwater recharge, with varying uncertainty projected into the future, and sensitivity to time in the fluctuation of the components of the water cycle.

show abstract

Section: Introductionmentioning

confidence: 99%

Climatic Modeling of Seawater Intrusion in Coastal Aquifers: Understanding the Climate Change Impacts

Lyra,

Loukas,

Sidiropoulos

et al. 2024

Hydrology

View full text Add to dashboard Cite

show abstract

“…These numerical modeling approaches offer a flexible and reliable framework for simulating and predicting SI processes. Moreover, in recent years, the burgeoning field of deep learning (DL) has garnered substantial attention within SI research (Song et al, 2018;Yang et al, 2023;Yin et al, 2022). This data-driven modeling approach holds immense promise for tackling the intricate challenges in coastal aquifer simulations.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning-Based Data Assimilation Approach to Characterizing Coastal Aquifers Amid Non-linearity and Non-Gaussianity Challenges

Cao,

Zhang,

Gan

et al. 2024

Preprint

View full text Add to dashboard Cite

Seawater intrusion (SI) poses a substantial threat to water security in coastal regions, where numerical models play a pivotal role in supporting groundwater management and protection. However, the inherent heterogeneity of coastal aquifers introduces significant uncertainties into SI predictions, potentially diminishing their effectiveness in management decisions. Data assimilation (DA) offers a solution by integrating various types of observational data with the model to characterize heterogeneous coastal aquifers. Traditional DA techniques, like ensemble smoother using the Kalman formula (ES) and Markov chain Monte Carlo, face challenges when confronted with the non-linearity, non-Gaussianity, and high-dimensionality issues commonly encountered in aquifer characterization. In this study, we introduce a novel DA approach rooted in deep learning (DL), referred to as ES, aimed at effectively characterizing coastal aquifers with varying levels of heterogeneity. We systematically investigate a range of factors that impact the performance of ES, including the number and types of observations, the degree of aquifer heterogeneity, the structure and training options of the DL models. Our findings reveal that ES excels in characterizing heterogeneous aquifers under non-linear and non-Gaussian conditions. Comparison between ES and ES under different experimentation settings underscores the robustness of ES. Conversely, in certain scenarios, ES displays noticeable biases in the characterization results, especially when measurement data from non-linear and discontinuous processes are used. To optimize the efficacy of ES, attention must be given to the design of the DL model and the selection of observational data, which are crucial to ensure the universal applicability of this DA method.

show abstract

“…These numerical modeling approaches offer a flexible and reliable framework for simulating and predicting SI processes. Moreover, in recent years, the burgeoning field of deep learning (DL) has garnered substantial attention within SI research (Song et al., 2018; Yang et al., 2023; Yin et al., 2022). This data‐driven modeling approach holds immense promise for tackling the intricate challenges in coastal aquifer simulations.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning‐Based Data Assimilation Approach to Characterizing Coastal Aquifers Amid Non‐Linearity and Non‐Gaussianity Challenges

Cao,

Zhang,

Gan

et al. 2024

Water Resources Research

View full text Add to dashboard Cite

Seawater intrusion (SI) poses a substantial threat to water security in coastal regions, where numerical models play a pivotal role in supporting groundwater management and protection. However, the inherent heterogeneity of coastal aquifers introduces significant uncertainties into SI predictions, potentially diminishing their effectiveness in management decisions. Data assimilation (DA) offers a solution by integrating various types of observational data with the model to characterize heterogeneous coastal aquifers. Traditional DA techniques, like ensemble smoother using the Kalman formula (ESK) and Markov chain Monte Carlo, face challenges when confronted with the non‐linearity, non‐Gaussianity, and high‐dimensionality issues commonly encountered in aquifer characterization. In this study, we introduce a novel DA approach rooted in deep learning (DL), referred to as ESDL, aimed at effectively characterizing coastal aquifers with varying levels of heterogeneity. We systematically investigate a range of factors that impact the performance of ESDL, including the number and types of observations, the degree of aquifer heterogeneity, the structure and training options of the DL models. Our findings reveal that ESDL excels in characterizing heterogeneous aquifers under non‐linear and non‐Gaussian conditions. Comparison between ESDL and ESK under different experimentation settings underscores the robustness of ESDL. Conversely, in certain scenarios, ESK displays noticeable biases in the characterization results, especially when measurement data from non‐linear and discontinuous processes are used. To optimize the efficacy of ESDL, attention must be given to the design of the DL model and the selection of observational data, which are crucial to ensure the universal applicability of this DA method.

show abstract

Characterization of seawater intrusion based on machine learning and implications for offshore management under shared socioeconomic paths

Cited by 7 publications

References 49 publications

Climatic Modeling of Seawater Intrusion in Coastal Aquifers: Understanding the Climate Change Impacts

Climatic Modeling of Seawater Intrusion in Coastal Aquifers: Understanding the Climate Change Impacts

A Deep Learning-Based Data Assimilation Approach to Characterizing Coastal Aquifers Amid Non-linearity and Non-Gaussianity Challenges

A Deep Learning‐Based Data Assimilation Approach to Characterizing Coastal Aquifers Amid Non‐Linearity and Non‐Gaussianity Challenges

Contact Info

Product

Resources

About