Plot of DR vs FD.
<div><p>Accurate prediction of mean wave overtopping discharge is essential for the safe and cost-effective design of coastal defence structures. While traditional empirical, physical, and numerical models remain important, Machine Learning (ML) has recently emerged as a powerful complem...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852014029404372992 |
|---|---|
| author | M. A. Habib (16839161) |
| author2 | S. Abolfathi (16839167) J. J. O’Sullivan (16839164) M. Salauddin (10017388) |
| author2_role | author author author |
| author_facet | M. A. Habib (16839161) S. Abolfathi (16839167) J. J. O’Sullivan (16839164) M. Salauddin (10017388) |
| author_role | author |
| dc.creator.none.fl_str_mv | M. A. Habib (16839161) S. Abolfathi (16839167) J. J. O’Sullivan (16839164) M. Salauddin (10017388) |
| dc.date.none.fl_str_mv | 2025-12-10T18:38:12Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0337830.g009 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Plot_of_DR_vs_FD_/30852934 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified influential parameters across gaussian process regression coastal defence structures improved predictive formulae best predictive performance practical engineering needs powerful complementary tool coastal infrastructure design respectively ), indicating five ml algorithms div >< p >) based solely predictive accuracy reliable tool practical usability effective design >) within svr ), gbdt ), work advances wave overtopping validated using traditional empirical three kernel study presents structured pre strong agreement sloped breakwaters simplified equations relative freeboard recently emerged rae values q </ processing steps observed data new set model interpretability ml findings machine learning lowest rmse ln (< gpr yielded gpr ). gp ). genetic programming freeboard deficit enhance interpretability effectively modelling driven techniques based models |
| dc.title.none.fl_str_mv | Plot of DR vs FD. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Accurate prediction of mean wave overtopping discharge is essential for the safe and cost-effective design of coastal defence structures. While traditional empirical, physical, and numerical models remain important, Machine Learning (ML) has recently emerged as a powerful complementary tool. This study presents a ML–based framework to predict mean wave overtopping discharge at sloped breakwaters, with a focus on both predictive accuracy and model interpretability, supported by a series of structured pre- and post-processing steps. Five ML algorithms were evaluated: two decision tree–based models, i.e., Random Forest (RF) and Gradient Boosted Decision Trees (GBDT), and three kernel-based models, i.e., Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Gaussian Process Regression (GPR). The models were trained and validated using the EurOtop (2018) dataset on sloped breakwaters. Among them, GPR yielded the best predictive performance, achieving an R² of 0.80 and the lowest RMSE, MAE, and RAE values (0.100, 0.013, and 0.30, respectively), indicating a strong agreement with observed data. Feature importance analysis revealed that Relative Freeboard and Freeboard Deficit (FD) were the most influential parameters across the models. To enhance interpretability and practical usability, we translated the ML findings into mathematical expressions using polynomial regression and Genetic Programming (GP). A new set of simplified equations was developed to estimate mean overtopping discharge (<i>q</i>) based solely on FD, effectively modelling the relationship between FD and ln(<i>q</i>) within the EurOtop dataset. The proposed formulae provide coastal engineers with a rapid, interpretable, and reliable tool for estimating mean wave overtopping, significantly enhancing design efficiency and decision-making under uncertainty. By bridging the gap between advanced data-driven techniques and practical engineering needs, this work advances the integration of ML into coastal infrastructure design and supports the development of more adaptive and climate-resilient defence systems.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_6850cc5d3e2c0ed4e8e5eba76af4a4cd |
| identifier_str_mv | 10.1371/journal.pone.0337830.g009 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30852934 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Plot of DR vs FD.M. A. Habib (16839161)S. Abolfathi (16839167)J. J. O’Sullivan (16839164)M. Salauddin (10017388)Environmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedinfluential parameters acrossgaussian process regressioncoastal defence structuresimproved predictive formulaebest predictive performancepractical engineering needspowerful complementary toolcoastal infrastructure designrespectively ), indicatingfive ml algorithmsdiv >< p>) based solelypredictive accuracyreliable toolpractical usabilityeffective design>) withinsvr ),gbdt ),work advanceswave overtoppingvalidated usingtraditional empiricalthree kernelstudy presentsstructured prestrong agreementsloped breakwaterssimplified equationsrelative freeboardrecently emergedrae valuesq </processing stepsobserved datanew setmodel interpretabilityml findingsmachine learninglowest rmseln (<gpr yieldedgpr ).gp ).genetic programmingfreeboard deficitenhance interpretabilityeffectively modellingdriven techniquesbased models<div><p>Accurate prediction of mean wave overtopping discharge is essential for the safe and cost-effective design of coastal defence structures. While traditional empirical, physical, and numerical models remain important, Machine Learning (ML) has recently emerged as a powerful complementary tool. This study presents a ML–based framework to predict mean wave overtopping discharge at sloped breakwaters, with a focus on both predictive accuracy and model interpretability, supported by a series of structured pre- and post-processing steps. Five ML algorithms were evaluated: two decision tree–based models, i.e., Random Forest (RF) and Gradient Boosted Decision Trees (GBDT), and three kernel-based models, i.e., Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Gaussian Process Regression (GPR). The models were trained and validated using the EurOtop (2018) dataset on sloped breakwaters. Among them, GPR yielded the best predictive performance, achieving an R² of 0.80 and the lowest RMSE, MAE, and RAE values (0.100, 0.013, and 0.30, respectively), indicating a strong agreement with observed data. Feature importance analysis revealed that Relative Freeboard and Freeboard Deficit (FD) were the most influential parameters across the models. To enhance interpretability and practical usability, we translated the ML findings into mathematical expressions using polynomial regression and Genetic Programming (GP). A new set of simplified equations was developed to estimate mean overtopping discharge (<i>q</i>) based solely on FD, effectively modelling the relationship between FD and ln(<i>q</i>) within the EurOtop dataset. The proposed formulae provide coastal engineers with a rapid, interpretable, and reliable tool for estimating mean wave overtopping, significantly enhancing design efficiency and decision-making under uncertainty. By bridging the gap between advanced data-driven techniques and practical engineering needs, this work advances the integration of ML into coastal infrastructure design and supports the development of more adaptive and climate-resilient defence systems.</p></div>2025-12-10T18:38:12ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0337830.g009https://figshare.com/articles/figure/Plot_of_DR_vs_FD_/30852934CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/308529342025-12-10T18:38:12Z |
| spellingShingle | Plot of DR vs FD. M. A. Habib (16839161) Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified influential parameters across gaussian process regression coastal defence structures improved predictive formulae best predictive performance practical engineering needs powerful complementary tool coastal infrastructure design respectively ), indicating five ml algorithms div >< p >) based solely predictive accuracy reliable tool practical usability effective design >) within svr ), gbdt ), work advances wave overtopping validated using traditional empirical three kernel study presents structured pre strong agreement sloped breakwaters simplified equations relative freeboard recently emerged rae values q </ processing steps observed data new set model interpretability ml findings machine learning lowest rmse ln (< gpr yielded gpr ). gp ). genetic programming freeboard deficit enhance interpretability effectively modelling driven techniques based models |
| status_str | publishedVersion |
| title | Plot of DR vs FD. |
| title_full | Plot of DR vs FD. |
| title_fullStr | Plot of DR vs FD. |
| title_full_unstemmed | Plot of DR vs FD. |
| title_short | Plot of DR vs FD. |
| title_sort | Plot of DR vs FD. |
| topic | Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified influential parameters across gaussian process regression coastal defence structures improved predictive formulae best predictive performance practical engineering needs powerful complementary tool coastal infrastructure design respectively ), indicating five ml algorithms div >< p >) based solely predictive accuracy reliable tool practical usability effective design >) within svr ), gbdt ), work advances wave overtopping validated using traditional empirical three kernel study presents structured pre strong agreement sloped breakwaters simplified equations relative freeboard recently emerged rae values q </ processing steps observed data new set model interpretability ml findings machine learning lowest rmse ln (< gpr yielded gpr ). gp ). genetic programming freeboard deficit enhance interpretability effectively modelling driven techniques based models |