Applications of Machine Learning to Wind Engineering

Abstract

Advances of the analytical, numerical, experimental and field-measurement approaches in wind engineering offers unprecedented volume of data that, together with rapidly evolving learning algorithms and high-performance computational hardware, provide an opportunity for the community to embrace and harness full potential of machine learning (ML). This contribution examines the state of research and practice of ML for its applications to wind engineering. In addition to ML applications to wind climate, terrain/topography, aerodynamics/aeroelasticity and structural dynamics (following traditional Alan G. Davenport Wind Loading Chain), the review also extends to cover wind damage assessment and wind-related hazard mitigation and response (considering emerging performance-based and resilience-based wind design methodologies). This state-of-the-art review suggests to what extend ML has been utilized in each of these topic areas within wind engineering and provides a comprehensive summary to improve understanding how learning algorithms work and when these schemes succeed or fail. Moreover, critical challenges and prospects of ML applications in wind engineering are identified to facilitate future research efforts.

A machine learning regression approach for predicting the bearing capacity of a strip footing on rock mass under inclined and eccentric load

“…These things can be reduced the calculation time for numerical modelling and selecting the impact parameters of practitioners. Fortunately, together with the development of artificial intelligence, machine learning is applied in data analysis in many scientific fields, including geotechnical problems, which have significant issues in calculating data (e.g., Fernández-Cabán et al, 2018;Ghahramani et al, 2020;Bamer et al, 2021;Wu and Snaiki, 2022). Some machine learning methods, which can be considered as the successful models in geotechnical problems, are artificial neural networks ~ANN, extreme learning machines ~ELM, support vector regression ~SVR, Gaussian process regression ~GPR, and stochastic gradient boosting trees ~SGBT (e.g., Yuan et al, 2021;Keawsawasvong et al, 2022c).…”

A case study and parametric analysis of predicting hurricane-induced building damage using data-driven machine learning approach

“…State-of-the-art models such as Hazus (FEMA, 2021a,b;Vickery et al, 2006a,b) use detailed building characteristics, each with experimentally derived load resistance, when developing building archetypes which are then subjected to loads calculated using hurricane intensity parameters. It is noted by Wu and Snaiki (2022) that "knowledge-enhanced machine learning," which attempts to capture such underlying physics in a data-driven ML model, assists in efficiency and accuracy of ML models in wind engineering. Despite ML algorithms not directly calculating loading and resistance for building components, incorporating these building characteristics as variables aims to maintain the engineering factors at play when buildings are damaged by hurricane hazards.…”

“…While ML has been applied to hurricane hazard engineering in recent years, its application to predicting building damage is limited. For decades, ML has been applied to wind engineering subfields such as predicting windstorm intensity and frequency, incorporating topographic and aerodynamic features into wind models such as those in computational fluid dynamics, and as surrogate models to mitigate the expense of complex computational models (Wu and Snaiki, 2022). In recent practice, ML is utilized in the reactive categorization of building damage after hurricane impact by comparing preand post-storm imagery (e.g., Li et al, 2019;Calton and Wei, 2022;Kaur et al, 2022) and for near real-time detection of damage via analysis of social media posts (e.g., Hao and Wang, 2019;Yuan and Liu, 2020).…”

Modeling nonlinear flutter behavior of long‐span bridges using knowledge‐enhanced long short‐term memory network

“…Unfortunately, the projection‐based reduced‐order modeling cannot fully capture the strong nonlinearities resulting from wind–bridge interactions (T. Wu & Kareem, 2015). On the other hand, the data‐driven reduced‐order modeling based on artificial neural networks (ANNs) has been utilized as a universal approximator of complex, nonlinear bridge aerodynamics system (T. Wu & Kareem, 2011; T. Wu & Snaiki, 2022). Other notable ANN applications in civil engineering field include research on the detections of surface cracks in concrete (Chun et al., 2021; Dung & Anh, 2019; Jiang & Zhang, 2020), infrastructure visual inspection (Hu et al., 2021), damage in structures (Luo et al., 2021; Rafiei & Adeli, 2017a; Zhou et al., 2022), and defects and leaks in tunnels (H. W. Huang et al., 2018; Xue & Li, 2018).…”