Abstract
The main aim of this paper is to conduct an empirical study on Machine Learning Applications in Civil Engineering. Engineers have continuously been striving to improve the efficiency of conventional materials, solutions, and the testing methodology in civil engineering. With the advancement of materials science and different composite materials, complex mathematical problems have recently been introduced in civil engineering [1]. As a result, the traditional methods of underlying theories and testing methods cannot be performed. Elsewhere, these modern solutions and materials may be exposed to extreme natural or non-natural loading circumstances during their service life and cause tremendous fatalities and property loss.Machine learning (ML) provides a wide range of applications in our current society, including predicting, classifying, and solving complex mathematical problems in civil engineering. ML methods and techniques, including neural networks, evolutionary computation, fuzzy logic systems, deep learning, and image processing applications, have rapidly evolved in recent decades [1]. Recently, ML algorithms have attracted close attention from researchers and have also been applied successfully to solve problems in civil engineering. For example, informing unmanned, intelligent, and fully automatic urban and regional planning, prediction of rainfall, hydrological problems, as well as developing new technologies, engineering design, construction, maintenance, and disaster management.