Sensitivity for inaccuracies, ambiguity, and partial truth is the goal of data-driven and soft computing techniques, which use various methodologies to accomplish this. Several approaches have recently been presented to solve real-world problems within engineerings, such as the ocean, structural, geotechnical, coastal, and hydraulics engineering and water resource management. Substantial knowledge of the different aspects of these engineering study fields is essential for constructing coastal protection systems, offshore structures design, hydraulic processes, engineering hydrology, hydrological modelling, and climate forecasting. Extreme events are often recorded erroneously, although they are greatly interested in engineering manners. Thus, sophisticated tools for reconstructing and predicting engineering-related problems are required. Precisely assessing these problems is vital for designing new structures and infrastructures, hydraulics structures, offshore facilities and transportation systems, urban and coastal resiliency, renewable energy systems, and smart power grids. Full use of big data can help humans achieve better development in responding to engineering design, protecting the ecological environment, and preventing natural disasters. Artificial neural networks (ANN) are widely used for engineering manners reconstruction and prediction as an alternative solution to physics-based modelling. Other machine learning and deep learning techniques such as convolutional neural network (CNN), recurrent neural network (RNN), support vector machine with radial basis kernel (SVM-RBF), and Random Forest are among the most widely used approaches in these issues. Compared with traditional data analysis and numerical simulation methods, these techniques have the advantage of high accuracy, low complexities, and less calculation, and in some cases, reduce data requirements. Recently, deep learning techniques are getting the most popular topic in engineering research, and their related approaches are in rapid development with regard to different subjects.
Key topics: Machine learning, Deep learning, Data-driven, Prediction models