■ Deep Learning-Based Rapid Residual Capacity Evaluation of Structures after Earthquakes

Rapid and accurate evaluation of the damage state of structures after a seismic event is critical for post-event emergency response and recovery. The existing rapid damage evaluation methodology is typically based on fragility curves incorporated into earthquake alerting platforms. However, the extent of damage predicted solely based on the fragility curves can vary significantly depending on ground motion characteristics. This research proposes methodologies for tagging based (classification problem) damage assessment of structures while accounting for temporal and spectral non-stationarity of ground motions (a) using convolutional neural networks (CNNs) based on continuous wavelet transform and image analysis techniques and (b) stacked long short term memory (LSTM) neural networks based on direct use of acceleration time history data. The methodologies are demonstrated through several case studies for bridges and buildings. 

Selected Publications

• Bilal Ahmed, Taehyo Park, and Jong-Su Jeon* (2025). Blast response and damage assessment of reinforced concrete slabs using convolutional neural networks. International Journal of Damage Mechanics; 34(5): 771–797, May 1.

• Mengdie Chen, Sujith Mangalathu, and Jong-Su Jeon* (2024). Rapid damage state identification of structures using generalized zero-shot learning method. Earthquake Engineering & Structural Dynamics; 53(14): 4269–4286, November 1.

• Bilal Ahmed, Sujith Mangalathu, and Jong-Su Jeon* (2023). Unveiling out-of-distribution data for reliable structural damage assessment in earthquake emergency situations. Automation in Construction; 156: 105142, December 1. 

• Bilal Ahmed, Sujith Mangalathu, and Jong-Su Jeon*(2023). Generalized stacked LSTM for the seismic damage evaluation of ductile reinforced concrete buildings. Earthquake Engineering & Structural Dynamics; 52(11): 3477–3503, September 1. 

• Bilal Ahmed, Sujith Mangalathu, and Jong-Su Jeon*2022). Seismic damage state predictions of reinforced concrete structures using stacked long short-term memory neural networks. Journal of Building Engineering; 46: 103737, April 1.

• Sujith Mangalathu and Jong-Su Jeon* (2020). Ground motion-dependent rapid damage assessment of structures based on wavelet transform and image analysis techniques. Journal of Structural Engineering ASCE; 146(11): 04020230, November 1.

■ Machine Learning (ML)-Based Seismic Vulnerability of Structures Using Numerical Simulations

It is highly likely that various uncertainties such as geometric, material or component response parameters exist due to structure-to-structure variation in the generation of fragility curves, especially if the fragility curves are intended for the regional seismic risk assessment of bridges. Also, it is not possible/warranted to generate fragility curves for each bridge. A multi-parameter fragility framework using various machine learning techniques such as Lasso regression, artificial neural network, and random forests was suggested to generate bridge-specific fragility curves. The proposed framework helps bridge owners to spend their resources judiciously (e.g. data collection, field investigations, censoring) on parameters significantly affecting bridge fragilities. 

Selected Publications

• Sergei Shturmin, Sujith Mangalathu, and Jong-Su Jeon* (2025). Application of latent variable models for hidden pattern identification and machine learning prediction improvement in structural engineering. Engineering Applications of Artificial Intelligence; 156(C): 111282, September 15.

• Mengdie Chen#,, Yewon Park#,, Sujith Mangalathu, and Jong-Su Jeon* (2024). Effect of data drift on the performance of machine-learning models: Seismic damage prediction for aging bridges. Earthquake Engineering & Structural Dynamics; 53(15): 4541–4561, December 1.

• Sergei Shturmin, Chang Seok Lee, Eunsoo Choi, and Jong-Su Jeon* (2024). Machine learning-based residual drift prediction of concrete-filled steel tube columns under earthquake loads. Journal of Building Engineering; 97: 110903, November 15.

• Chang Seok Lee, Sujith Mangalathu, and Jong-Su Jeon* (2023). Machine-learning-assisted drift capacity prediction models for reinforced concrete columns with shape memory alloy bars. Computer-Aided Civil and Infrastructure Engineering; 39(4): 595–616, February 15. 

• Mengdie Chen, Sujith Mangalathu, and Jong-Su Jeon* (2022). Machine-learning-based seismic reliability assessment of bridge networks. Journal of Structural Engineering ASCE; 148(7): 06022002, July 1 .

• Seong-Hoon Hwang, Sujith Mangalathu, Jinwon Shin, and Jong-Su Jeon* (2022). Estimation of economic seismic loss of steel moment-frame buildings using a machine learning algorithm. Engineering Structures; 254: 113877, March 1.

• Sujith Mangalathu, Karthikeyan K, De-Cheng Feng, and Jeon J-S* (2022). Machine-learning interpretability techniques for seismic performance assessment of infrastructure systems. Engineering Structures; 250: 112883, January 1.

• Sujith Mangalathu and Jong-Su Jeon* (2020). Regional seismic risk assessment of infrastructure systems through machine learning: active learning approach. Journal of Structural Engineering ASCE; 146(12): 04020269, December 1.

• Sujith Mangalathu Seong-Hoon Hwang*, Eunsoo Choi, and Jong-Su Jeon* (2019). Rapid seismic damage evaluation of bridge portfolios using machine learning techniques. Engineering Structures; 201: 109785, December 15.

• Sujith Mangalathu and Jong-Su Jeon* (2019). Stripe-based fragility analysis of multispan concrete bridge classes using machine learning techniques. Earthquake Engineering & Structural Dynamics; 48(11): 1238–1255, September 1.

• Sujith Mangalathu, Gwanghee Heo, and Jong-Su Jeon* (2018). Artificial neural network based multi-dimensional fragility development of skewed concrete bridge classes. Engineering Structures; 162: 166–176, May 1.

• Sujith Mangalathu, Jong-Su Jeon*, and Reginald DesRoches (2018). Critical uncertainty parameters influencing seismic performance of bridges using Lasso regression. Earthquake Engineering & Structural Dynamics; 47(3): 784–801, March 1.

■ ML-Based Failure Mode Classification and Capacity Estimation Using Experimental Database

To identify the response mechanism, including the classification of failure mode and the prediction of associated shear strength, of critical components, this research introduces the application of machine learning techniques. The efficiency of various machine learning techniques is evaluated using extensive experimental data collected from existing experimental tests. The suggested formulations (classification and prediction) as a function of influential input design variables can be easily used by structural engineers to provide an optimal rehabilitation strategy for existing structures and to design new structures. 

Selected Publications

• Koochul Ji#, Gil Hwan Wang#, Ilyoon Choi, and Jong-Su Jeon* (2025). Machine learning based life prediction of rail tracks using environmental and operational factors. Developments in the Built Environment; 23: 100718, October 1.

• Sujith Mangalathu, Hanbyeol Shin, Eunsoo Choi, and Jong-Su Jeon* (2021). Explainable machine learning models for punching shear strength estimation of flat slabs without transverse reinforcement. Journal of Building Engineering; 39: 102300, July 1.

• Sujith Mangalathu and Jong-Su Jeon* (2020). Regional seismic risk assessment of infrastructure systems through machine learning: active learning approach. Journal of Structural Engineering ASCE; 146(12): 04020269, December 1.

• Sujith Mangalathu, Seong-Hoon Hwang, and Jong-Su Jeon* (2020). Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach. Engineering Structures; 219: 110927, September 15.

• Sujith Mangalathu, Hansol Jang, Seong-Hoon Hwang, and Jong-Su Jeon* (2020). Data-driven machine-learning-based seismic failure mode identification of reinforced concrete shear walls. Engineering Structures; 208: 110331, April 1.

• Sujith Mangalathu and Jong-Su Jeon* (2019). Machine learning-based failure mode recognition of circular reinforced concrete bridge columns: a comparative study. Journal of Structural Engineering ASCE; 145(10): 04019104, October 1. 

• Sujith Mangalathu and Jong-Su Jeon* (2018). Classification of failure mode and prediction of shear strength for reinforced concrete beam-column joints using machine learning techniques. Engineering Structures; 160: 85–94, April 1.

• Jong-Su Jeon*, Abdollah Shafieezadeh, and Reginald DesRoches (2014). Statistical models for shear strength of RC beam-column joints using machine-learning techniques. Earthquake Engineering & Structural Dynamics; 43(14): 2075–2095, November 1.