Wave data play a critical role in offshore structure design and coastal vulnerability studies. For various reasons, such as equipment malfunctions, wave data are often incomplete. Despite the interest in completing the data, few studies have considered constructing a machine learning model with publicly available wind measurements as input, while wind data from reanalysis models are commonly used. In this work, ANNs are constructed and tested to fill in missing wave data and extend the original wave measurements in a basin with limited fetch where wind waves dominate. Input features for the ANN are obtained from the publicly available Integrated Surface Database (ISD) maintained by NOAA. The accuracy of the ANNs is also compared to a state-of-the-art reanalysis wave model, MEDSEA, maintained at Copernicus Marine Service. The results of this study show that ANNs can accurately fill in missing wave data and also extend beyond the measurement period, using the wind velocity magnitude and wind direction from nearby weather stations. The MEDSEA reanalysis data showed greater scatter compared to the reconstructed significant wave heights from ANN. Specifically, MEDSEA showed a 22% higher HH index for expanding wave data and a 33% higher HH index for filling in missing wave data points.

Croatia’s coast located on the eastern Adriatic is rich with small gravel beaches with limited fetch. This leads to a specific low-energetic wave climate compared to most other beaches, while their gravel composition makes them unique. Most management of these beaches is performed without understanding the sediment transport occurring on the beaches. XBeach-Gravel is a numerical model capable of simulating bed-level change on gravel beaches, but lacks validation in the case of low significant wave height (under 2.5 m) and low peak periods (under 6 s), conditions that are present on the eastern Adriatic. Based on measurements performed in both laboratory conditions in a water canal in Hannover and actual storm wave conditions on Ploče beach, calibration of the model is performed. Model results are compared between laboratory conditions and field conditions for comparable wave conditions. XBeach-Gravel can simulate low-energetic events resulting in berm formation and berm buildup with a high Brier skill score if calibrated. Simulation of laboratory conditions requires high transport coefficient values and shows more sediment transport than similar wave conditions in the field. Calibration for field conditions is dependent on geodetic survey data capable of isolating wave events with dominant cross-shore transport, but once calibrated, XBeach-Gravel can achieve good to excellent Brier skill score values in simulating sediment change in low-energetic wave conditions on the eastern Adriatic.

Accurately hindcasting waves in semi-enclosed, fetch-limited basins remains challenging for reanalysis models, which tend to underestimate storm peaks near the coast. We developed interpretable ML models for Rijeka Bay (northern Adriatic) using only wind observations from two land-based wind stations to predict buoy H_m0 measurements spanning 2009–2011 (testing) and 2019–2021 (training and validation). The tested tree-based models included Random Forest, XGBoost, and Explainable Boosting Machine. This study introduces a novel approach in the literature by employing weighted schemes and feature engineering to enhance the predictive performance of interpretable, low-complexity machine learning models in hindcasting waves. Representing wind direction as sine–cosine components generally reduced RMSE and BIAS relative to traditional speed–direction inputs, while an exponential sample weight scheme that emphasized storm waves halved extreme H_m0 underprediction without inflating overall RMSE. The best-performing model, a Random Forest model, achieved an RMSE of 0.096 m and a correlation of 0.855 on the unseen test set—30% lower overall RMSE and 50% lower extreme wave RMSE than the MEDSEA and COEXMED hindcasts. Additionally, the underprediction was reduced by 90% compared to these reanalysis models. The method offers a computationally lightweight, transferable supplement to numerical wave guidance for coastal engineering and harbor operations.

Coarse-grained beaches consisting of gravel, pebbles, and cobbles play a crucial role in coastal protection. On the Croatian Adriatic coast, there are artificial gravel pocket beaches created for recreational and protective purposes. However, these beaches are subject to constant morphological changes due to natural forces and human intervention. This study investigates the morphodynamics of artificial gravel pocket beaches, focusing on berm formation and crest build-up processes characteristic for low to moderate wave conditions. Despite mimicking natural formations, artificial beaches require regular maintenance due to sediment shifts dominantly caused by wave action and storm surges. Structure-from-Motion (SfM) photogrammetry and UAV-based surveys were used to monitor morphological changes on the artificial gravel pocket beach Ploče (City of Rijeka). The XBeach-Gravel model, originally adapted to simulate the effects of high-energy waves, was calibrated and validated to analyze low to moderate wave dynamics on gravel pocket beaches. The calibration includes adjustments to the inertia coefficient (ci), which influences sediment transport by shear stress at the bottom; the angle of repose (ϕ), which controls avalanching and influences sediment transport on sloping beds; and the bedload transport calibration coefficient (γ), which scales the transport rates linearly. By calibrating XBeach-G for low to moderate wave conditions, this research improves the accuracy of the model for the cases of morphological responses “berm formation” and “crest build-up”.

Semi-submerged curtain breakwaters are increasingly favored to protect marinas and other microtidal basins, yet they are still almost exclusively designed with deterministic wave transmission equations. This study introduces a fully probabilistic design framework that translates uncertainty in wave climate and water level design parameters into explicit confidence limits for transmitted wave height. Using Latin Hypercube Sampling, input uncertainty is propagated through a modified Wiegel transmission model, yielding empirical distributions of the transmission coefficients K_t and H_t. Our method uses the associated safety factor required to satisfy a 95% non-exceedance criterion, SF₉₅. Regression analysis reveals the existence of a strong inverse linear relationship (R = −0.9) between deterministic K_t and the probabilistic safety factor, indicating that designs trimmed to low nominal transmission (e.g., K_t ≤ 0.35) must be uprated by up to 55% once parameter uncertainty is acknowledged, whereas concepts with greater transmission require far smaller margins. Sobol indices show that uncertainty in H_m0 and T_p each contribute ≈40% of the variance in H_t for a tide signal standard deviation of σ_η = 0.16 m, while tides only become equally important when σ_η > 0.30 m. Model-based uncertainty is negligible, standing at under 8%. The resulting lookup equations allow designers to convert any deterministic K_t target into a site-specific probabilistic limit with a single step, thereby embedding reliability into routine breakwater sizing and reducing the risk of underdesigned marina and port structures.