Combining process-based and data-driven approaches to forecast beach and dune change

Itzkin, Michael; Moore, Laura J.; Ruggiero, Peter; Hovenga, Paige A.; Hacker, Sally D.

doi:10.1016/j.envsoft.2022.105404

Cited by 11 publications

(7 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is a powerful tool that excels in identifying patterns within large data sets and is commonly used to analyze data generated from remote sensed products (e.g., Barbarella et al., 2021; Gómez et al., 2022; Lary et al., 2016; Maxwell et al., 2018). These data‐driven techniques have been used in a variety of coastal applications, including the prediction of wave ripples (Goldstein et al., 2013), shoreline evolution (Montaño et al., 2020), and the calibration of a physically based dune‐beach model (Itzkin et al., 2022), among others. In this study, we used DT analysis and RF modeling to categorize transects as either “shrub” or “non‐shrub” based on our eight morphometric variables.…”

Section: Methodsmentioning

confidence: 99%

“…Recent examples include the use of machine learning to classify images to calculate coastal landslide risk (Fisher et al., 2023), characterize biological marsh communities (Martínez Prentice et al., 2021), and identify shoreline features (McAllister et al., 2022). Additionally, machine learning algorithms have been coupled with physically based models to predict changes in barrier island habitat (Enwright et al., 2021), calibrate dune evolution models (Itzkin et al., 2022), and simulate shoreline evolution (Montaño et al., 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Barrier Island Shrub Presence Using Remote Sensing Products and Machine Learning Techniques

Franklin,

Moore,

Zinnert

2024

JGR Earth Surface

Self Cite

View full text Add to dashboard Cite

Barrier islands are highly dynamic coastal landforms that are economically, ecologically, and societally important. Woody vegetation located within barrier island interiors can alter patterns of overwash, leading to periods of periodic‐barrier island retreat. Due to the interplay between island interior vegetation and patterns of barrier island migration, it is critical to better understand the factors controlling the presence of woody vegetation on barrier islands. To provide new insight into this topic, we use remote sensing data collected by LiDAR, LANDSAT, and aerial photography to measure shrub presence, coastal dune metrics, and island characteristics (e.g., beach width, island width) for an undeveloped mixed‐energy barrier island system in Virginia along the US mid‐Atlantic coast. We apply decision tree and random forest machine learning methods to identify new empirical relationships between island geomorphology and shrub presence. We find that shrubs are highly likely (90% likelihood) to be present in areas where dune elevations are above ∼1.9 m and island interior widths are greater than ∼160 m and that shrubs are unlikely (10% likelihood) to be present in areas where island interior widths are less than ∼160 m regardless of dune elevation. Our machine learning predictions are 90% accurate for the Virginia Barrier Islands, with almost half of our incorrect predictions (5% of total transects) being attributable to system hysteresis; shrubs require time to adapt to changing conditions and therefore their growth and removal lags changes in island geomorphology, which can occur more rapidly.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting Barrier Island Shrub Presence Using Remote Sensing Products and Machine Learning Techniques

Franklin,

Moore,

Zinnert

2024

JGR Earth Surface

Self Cite

View full text Add to dashboard Cite

show abstract

“…Combining process models with datadriven approaches may offer the potential to maintain the complexity of process models with reduced computational demand. This is a novel method, requiring significant future development, however Itzkin et al (2022) applied this approach to model dune and beach evolution with reasonable success over multi-year timescales.…”

Section: Process Modelsmentioning

confidence: 99%

“…Secondly, complex processes can be accurately encapsulated by data learning methodologies, including Artificial Neural Networks (ANN). Thus, embedding ANNs within more complex models can also increase computational efficiency (Itzkin et al (2022).…”

Section: Medium-to-long Term Timescalesmentioning

confidence: 99%

Shoreline modelling on timescales of days to decades

Hunt¹,

Davidson²,

Steele³

et al. 2023

Camb. prisms Coast. futures

View full text Add to dashboard Cite

In the context of increased probability of coastal erosion and flooding associated with climate change, there is a pressing need to predict future shorelines at both short-(daily) and mediumterm (decadal) timescales. Such predictions are essential for the assessment of the climateresilience of the world's coastlines and the delivery of effective, economic and data-informed coastal management. Coastal managers currently lack these predictions and there are many different modelling approaches to inform where increased coastal protection, adaption measures or future infrastructure developments should be focussed. Promising modelling advances have recently been made, particularly in the context of reduced complexity models. This paper reviews various numerical modelling approaches to predicting shoreline and coastal morphological change, comments on some of the most promising methods used to-date, provides some guidance on model selection, and highlights important future research directions and challenges to progress.

show abstract

“…Duna comprises a wind flow module, a flow‐vegetation interaction module and a sand transport module and accounts for a wide array of supply limiting conditions (armoring, fetch limitation, moisture, slope). For long‐term simulations, approaches combining machine learning algorithms with morphodynamic models to reduce computational loads, such as the Long Short‐Term Memory model paired with Windsurf (Itzkin et al., 2022), have also been employed. Similarly, simplified semi‐empirical models, such as the cross‐shore sediment transport (CS) model (Hallin et al., 2019) that solves conceptual morphological models for the coupled evolution of beach‐dune systems, have been used over decadal to centennial time scales.…”

Section: Introductionmentioning

confidence: 99%

Exploring Controls on Coastal Dune Growth Through a Simplified Model

Kombiadou

Roelvink

2023

JGR Earth Surface

View full text Add to dashboard Cite

Process‐based morphodynamic models can be useful in understanding coastal dune responses to disturbances, as well as possible evolutionary patterns. To this aim, we employ Duna, a simplified 1D morphodynamic model, to assess the influence of dune morphology (height and slope) on sand transfer and deposition across the dune profile for different beach widths and wind incidence angles through idealized experiments. Simulations of real conditions show good model performance, both in wind flow reproduction and in topographic change along the dune profiles tested. The idealized experiments show that wind speed increases and sand accumulation decreases logarithmically with dune height and linearly with stoss slope along the dune profile. Fetch and cosine transport limiting parameters are reflected in the sand accumulated windwards from the toe, while sand transfer to the dune appears controlled by multiple factors; the higher the dune and/or the narrower the beach, the likelier that maximum accumulation occurs under oblique winds. Results point to two different types of evolution for high dunes. Either the vegetation is dense enough to maintain the stoss position, in which case vertical growth near‐ceases and seaward progradation is promoted, or the stoss is eroded and landward retreat dominates, in which case sand transfer to the crest and lee continues as a mixture of low input from the beach and recycled sand from the stoss.

show abstract

Combining process-based and data-driven approaches to forecast beach and dune change

Cited by 11 publications

References 72 publications

Predicting Barrier Island Shrub Presence Using Remote Sensing Products and Machine Learning Techniques

Predicting Barrier Island Shrub Presence Using Remote Sensing Products and Machine Learning Techniques

Shoreline modelling on timescales of days to decades

Exploring Controls on Coastal Dune Growth Through a Simplified Model

Contact Info

Product

Resources

About