Coastal regions are increasingly vulnerable to sea-level rise and extreme storm events, making the accurate prediction of wave run-up on seawalls crucial for effective flood and erosion protection. This study presents a novel hybrid approach combining K-means clustering with artificial neural networks (ANNs) to predict wave run-up distance. The method begins with dimensionless analysis to scale all the variables, followed by data segmentation using K-means clustering to group wave characteristics such as the Froude number, scaled distance from the wave front to the shoreline, and wave nonlinearity. These clusters help to focus the ANN on more homogeneous wave conditions, significantly improving prediction accuracy. Two-dimensional flume experiments systematically varied wave height, period, and steepness, producing a robust dataset that accounts for a range of wave conditions. The model’s performance is demonstrated through a high $R^2$ value of 0.97 and low mean squared error (MSE) of 0.0092, surpassing traditional ANN models in its ability to capture complex wave dynamics.

The analysis and prediction of seawall settlement are important for seawall engineering maintenance and disaster prevention. Based on the measured seawall settlement time series data, a combined LS‐ARIMA forecasting model that fits the trend item by the least‐square (LS) method and the season item by the differential self‐regression moving average (ARIMA) model was proposed in this study. The monitoring data of one seawall project in Zhejiang, China, is taken as an example to verify the model efficiency and prediction ability. The results show that the prediction accuracy of the new combined LS‐ARIMA model was high, with the average relative error (ARE) of 0.23%, much better than that of the traditional ARIMA model (ARE = 0.70%) and the GM (1, 1) model (ARE = 33.43%). This new model has clear physical conception and can effectively improve the prediction accuracy, implying that it can fully tap the dynamic information of monitoring data. The proposed model in this study provides a new research idea for data analysis and prediction of the seawall settlement.

Evaluating the stability of seawalls constructed on soft soils is critical but challenging. Traditional methods often depend on whether settlement velocity exceeds predefined thresholds, which can overlook subtle settlement fluctuations and may be less adaptable to varying construction and environmental conditions. To overcome these limitations, this paper presents a novel evaluation framework that combines a new settlement‐to‐loading index with a permutation entropy (PE) algorithm. By incorporating both settlement velocity and loading, the proposed index captures the behavior of seawalls under complex load conditions more comprehensively than fixed settlement velocity thresholds. The PE algorithm is then employed to analyze the time‐series data of the settlement‐to‐loading index, enabling the detection of small‐scale, transient fluctuations, which is a critical feature for soft soil scenarios characterized by significant and sporadic settlement spikes. A case study of a seawall in China demonstrates that this combined approach is more sensitive than conventional methods, effectively signaling early instabilities resulting from minor construction activities or rapid loading changes. Overall, the proposed method offers a physically meaningful, adaptable, and practical approach for evaluating seawall stability on soft soils, potentially reducing misjudgment in coastal infrastructure projects.

Settlement prediction based on monitoring data holds significant importance for engineering maintenance of seawalls. In practical engineering, the volume of the collected monitoring data is often limited due to the restrictions of devices and engineering budgets. Previous studies have applied the fractional-order grey model to time series prediction under the situation of limited data volume. However, the performance of the fractional-order grey model is easily affected by the inappropriate settings of fractional order. Also, the model cannot make dynamic predictions due to the characteristic of fixed step size. To solve the above problems, in this paper, the genetic algorithm with enhanced search capabilities was employed to solve the premature convergence problem. Additionally, to solve the problem of the fractional-order grey model associated with fixed step size, the real-time tracing algorithm was introduced to conduct equal-dimensionally recursive calculation. The proposed model was validated using monitoring data of four monitoring points at Haiyan seawall in Zhejiang province, China. The prediction performance of the proposed model was then compared with those of the fractional-order GM(1,1), integer-order GM(1,1), and fractal theory model. Results indicate that the proposed model significantly improves the prediction performance compared to other models.