Nowcasting significant wave height by hierarchical machine learning classification

Demetriou, Demetris; Michailides, Constantine; Papanastasiou, George; Onoufriou, Toula

doi:10.1016/j.oceaneng.2021.110130

Cited by 5 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was seen that some models used as few as one or two inputs, relying on historical trends for their predictive ability, while others used as many as 12 parameters trying to mimic physical models to map the relations between the input features and the outcome resulting in a high dimensionality and complex models. Still, this could also result in overfitting [32,44]. This is especially true when the data are not enough to account for all input combinations, resulting in a spurious fitting and a decreased predictive skill [111], in which case, researchers resort to some techniques to reduce overfitting, such as stopping training once validation gets worse, introducing weight penalties in the model, or using dimensionality reduction tools such as PCA.…”

Section: Discussionmentioning

confidence: 99%

“…Hastie et al [30] advise growing a large tree with many splits and then pruning the tree (collapsing some splits) based on cross-validation and cost complexity. Trees are usually used for classification problems and have been used in coastal engineering problems in context with other ML techniques (e.g., [31][32][33]). The tree structure is visually appealing and aids in interpreting the paths to which the prediction is made, therefore making it easier to identify errors in the model.…”

Section: Regression Treementioning

confidence: 99%

“…Despite their novel methodology, the model was not applied to real conditions. Continuing on the previous approach, Demetriou et al [32] proposed a method for the estimation of significant wave heights by monitoring meteorological data and the structural acceleration response of coastal structures. They developed an ANN and decision tree ensembles to use the inputs of accelerometers fixed Nowcasting waves based on collected data from fixed devices such as accelerometers also showed potential in wave characteristic estimates.…”

Section: Wave Field Predictionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning in Coastal Engineering: Applications, Challenges, and Perspectives

Abouhalima,

das Neves,

Taveira-Pinto

et al. 2024

JMSE

View full text Add to dashboard Cite

The integration of machine learning (ML) techniques in coastal engineering marks a paradigm shift in how coastal processes are modeled and understood. While traditional empirical and numerical models have been stalwarts in simulating coastal phenomena, the burgeoning complexity and computational demands have paved the way for data-driven approaches to take center stage. This review underscores the increasing preference for ML methods in coastal engineering, particularly in predictive tasks like wave pattern prediction, water level fluctuation, and morphology change. Although the scope of this review is not exhaustive, it aims to spotlight recent advancements and the capacity of ML techniques to harness vast datasets for more efficient and cost-effective simulations of coastal dynamics. However, challenges persist, including issues related to data availability and quality, algorithm selection, and model generalization. This entails addressing fundamental questions about data quantity and quality, determining optimal methodologies for specific problems, and refining techniques for model training and validation. The reviewed literature paints a promising picture of a future where ML not only complements but significantly enhances our ability to predict and manage the intricate dynamics of coastal environments.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Regression Treementioning

confidence: 99%

Section: Wave Field Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning in Coastal Engineering: Applications, Challenges, and Perspectives

Abouhalima,

das Neves,

Taveira-Pinto

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…Point forecasting delves into the spectral features, context, and temporal dependencies within SWH sequences to facilitate continuous time series forecasting. This category encompasses a variety of methods such as wavelet analysis, Particle Swarm Optimization (PSO), Extreme Learning Machine (ELM) approaches, Bayesian hyperparameter optimization, Elastic Net methods, Singular Value Decomposition (SVD), and Empirical Mode Decomposition (EMD) (Altunkaynak, 2015;Kaloop et al, 2020;Pirhooshyaran and Snyder, 2020;Demetriou et al, 2021;Zhou et al, 2021;Çelik, 2022). An expanded version of point forecasting not only analyzes the time evolution of SWH but also integrates influencing factors like wind speed, direction, duration, fetch, sea level pressure, and air temperature.…”

Section: Introductionmentioning

confidence: 99%

A transformer-based method for correcting significant wave height numerical forecasting errors

Kang,

Song,

Zhang

et al. 2024

Front. Mar. Sci.

View full text Add to dashboard Cite

Accurate significant wave height (SWH) forecasting is essential for various marine activities. While traditional numerical and mathematical-statistical methods have made progress, there is still room for improvement. This study introduces a novel transformer-based approach called the 2D-Geoformer to enhance SWH forecasting accuracy. The 2D-Geoformer combines the spatial distribution capturing capabilities of SWH numerical models with the ability of mathematical-statistical methods to identify intrinsic relationships among datasets. Using a comprehensive long time series of SWH numerical hindcast datasets as the numerical forecasting database and ERA5 reanalysis SWH datasets as the observational proxies database, with a focus on a 72-hour forecasting window, the 2D-Geoformer is designed. By training the potential connections between SWH numerical forecasting fields and forecasting errors, we can retrieve SWH forecasting errors for each numerical forecasting case. The corrected forecasting results can be obtained by subtracting the retrieved SWH forecasting errors from the original numerical forecasting fields. During long-term validation periods, this method consistently and effectively corrects numerical forecasting errors for almost every case, resulting in a significant reduction in root mean square error compared to the original numerical forecasting fields. Further analysis reveals that this method is particularly effective for numerical forecasting fields with higher errors compared to those with relatively smaller errors. This integrated approach represents a substantial advancement in SWH forecasting, with the potential to improve the accuracy of operational SWH forecasts. The 2D-Geoformer combines the strengths of numerical models and mathematical-statistical methods, enabling better capture of spatial distributions and intrinsic relationships in the data. The method's effectiveness in correcting numerical forecasting errors, particularly for cases with higher errors, highlights its potential for enhancing SWH forecasting accuracy in operational settings.

show abstract

A clustering machine learning approach for improving concrete compressive strength prediction

Demetriou,

Polydorou,

Nicolaides

et al. 2024

Engineering Reports

View full text Add to dashboard Cite

This study investigates the application of clustering techniques to enhance the accuracy of hierarchical classification and regression (HCR) models for predicting concrete compressive strength (CCS). Following the hypothesis that integrating clustering at the initial levels of model hierarchy reduces classification errors and prevents their propagation to subsequent levels, HCR models were developed utilizing both the unweighted pair group method with arithmetic mean (UPGMA) and hard clustering (HC) methods. Findings demonstrate that models using UPGMA significantly outperform those based on HC. Furthermore, it was demonstrated that further hierarchical clustering allows for multilayered HCR models that improve predictive performance by further leveraging parent–child relationships within data clusters. Overall, this study demonstrates that the proposed methodology can be introduced in the model development pipeline to enhance the prediction accuracy of CCS models.

show abstract

Nowcasting significant wave height by hierarchical machine learning classification

Cited by 5 publications

References 31 publications

Machine Learning in Coastal Engineering: Applications, Challenges, and Perspectives

Machine Learning in Coastal Engineering: Applications, Challenges, and Perspectives

A transformer-based method for correcting significant wave height numerical forecasting errors

A clustering machine learning approach for improving concrete compressive strength prediction

Contact Info

Product

Resources

About