Domain-informed Statistical Machine learning and modeling with Uncertainty Quantification

Statistical and machine learning methods for engineering processes and systems, integrating domain knowledge with data and uncertainty.

Our research integrates domain knowledge, statistical and machine learning modeling, and uncertainty quantification. The original diagram connects physics/engineering knowledge, data-driven modeling, and a Bayesian framework.

Domain Knowledge: physics/engineering knowledge
Statistical/ML Modeling: data-driven modeling
Uncertainty Quantification: Bayesian framework

Domain knowledge integrated with data-driven modeling View full-size figure

Research directions

AI for Engineering Systems

Monitoring, diagnostics, prognostics and decision-making for complex engineering systems.

AI for Engineering Processes

Data-driven modeling, quality control and optimization for advanced engineering processes.

Physics-Informed AI

Physics-informed inference of heterogeneous physical properties from noisy observations.

Research interests

Integration of domain knowledge into the data-analytics/machine-learning models

Data-driven Modeling, Design, Control, and Analysis on various Engineering Processes and Systems by leveraging the domain knowledge.

Monitoring, Diagnostics, Prognostics, and Prescriptive analysis (decision-making) on Engineering systems

Methodologies of interest: Statistical Analysis, Bayesian Modeling, Bayesian Optimization, Gaussian Processes, Reinforcement Learning, Physics-Informed Machine Learning

Previous & ongoing work

Tasks:

Quality Control (Process Monitoring [J3, C3], Prognosis [J9,J15], Diagnosis [J2, J15], Preventive Maintenance [J9,J11]),
Process/Design Optimization [J5, J8, J7, C5],
Statistical Calibration/Inference [J2, J4],
PDE Heterogeneous Parameter Estimation (Inverse Problem) [J10]
Faults Identification [J12, J13, J14]

Approaches:

Probabilistic Modeling [J3, C3, J11],
Statistical/Bayesian Modeling [J2, J4, J15],
Bayesian optimization [J5, J8, C5],
Gaussian process modeling [J4, J5, J8, J15, C5],
Survival Model [J15],
Uncertainty Quantification [J2, J4, J5, J8, J15],
Reinforcement Learning [J11],
Physics-Informed Machine Learning [J10]

Applications:

Advanced Manufacturing Process: e.g., Nano-scale Inkjet Printing, GFET Nanosensor Manufacturing & Design
Manufacturing System: e.g., Autobody assembly
Service System
Clinical Imaging (Elastography)/Bone biomechanics

Overview of data science methods for engineering processes and systems View full-size figure

Projects & applications

Preventive Maintenance on multi-component system (IoT-enabled Smart and Connected Production System)

Goal: Establishing a reinforcement learning method combined with a stochastic model to find the optimal preventive maintenance policy in a multi-components production system.

Methodologies: Deep Reinforcement learning, deep neural network, stochastic process modeling

Collaborators: This work is done with a Ph.D. student, T. Srikitrungruang and Collaborator, Dr. S. Jahani

Publications

[J11] Jaesung Lee^*, Tatthapong Srikitrungruang (advisee), and Salman Jahani, “Knowledge-Guided Reinforcement Learning for Preventive Maintenance Planning in Economically Dependent Multi-Component Systems,” IISE Transactions, vol. 58, no. 11, pp. 1352–1369, 2026, Published online 2026-01-22, Assigned November 2026 issue, doi:10.1080/24725854.2025.2610967.
Publication record: [J11]
- This work was selected as a finalist in the QSR Best Referred Paper Competition in 2025 INFORMS Conference.

Research diagram: Preventive Maintenance on multi-component system (IoT-enabled Smart and Connected Production System) — Preventive Maintenance on multi-component system (IoT-enabled Smart and Connected Production System) View full-size figure

Physics-Informed Machine Learning to estimate heterogeneous stiffness (elastic moduli) of bones based on the bone deformation data

Goal: To infer the unobserved underlying elastic properties based on observed noisy deformation data using the law of physics (partial differential equation; PDE).

Methodologies: Physics-Informed Neural Network, deep neural network

PDE Equation: Linear Elasticity with heterogeneous elastic moduli

Collaborators: This work is done with a Ph.D. students, T. Srikitrungruang, S Aghaee, an undergraduate student, M. Lemon, and Collaborator, Dr. Yuxiao Zhou.

Publications

[J10] Tatthapong Srikitrungruang (advisee), Sina Aghaee Dabaghan Fard (advisee), Matthew Lemon (advisee), Jaesung Lee^*, and Yuxiao Zhou, “Robust Physics-Informed Neural Network Approach for Estimating Heterogeneous Elastic Properties from Noisy Displacement Data,” Advanced Science, vol. 12, no. 48, article e08445, 2025, Published online 2025-11-25, doi:10.1002/advs.202508445.
Publication record: [J10]
- Advanced Science is a premier interdisciplinary journal with high impact (IF > 14).

Research diagram: Physics-Informed Machine Learning to estimate heterogeneous stiffness (elastic moduli) of bones based on the bone deformation data — Physics-Informed Machine Learning to estimate heterogeneous stiffness (elastic moduli) of bones based on the bone deformation data View full-size figure

Prognostics with diagnostics capability : Real-time failure time and types prediction and uncertainty quantification

Methodologies: Bayesian Hierarchical Modeling, Convolutional Gaussian Process, Variational Inference, Proportional Cox Hazard model

Collaborators: This work is done with a Ph.D. student, S. Aghaee

Publications

[J15] Sina Aghaee Dabaghan Fard (advisee), Minhee Kim, Akash Deep, and Jaesung Lee^*, “Bayesian Joint Model of Multi-Sensor and Failure Event Data for Multi-Mode Failure Prediction,” Technometrics, pp. 1–15, 2026, Published online 2026-05-13, doi:10.1080/00401706.2026.2653564.
Publication record: [J15]
- This work was selected as a finalist in the QCRE Best Student Paper Competition in 2025 IISE Conference .

Research diagram: Prognostics with diagnostics capability : Real-time failure time and types prediction and uncertainty quantification — Prognostics with diagnostics capability : Real-time failure time and types prediction and uncertainty quantification View full-size figure

Monitoring: Probability Modeling & Quality Control of Additive Nanosensor Manufacturing Process

Goal: Establishing a stochastic geometry model and a statistical quality control method using the image data

Methodologies: Stochastic geometry modeling, Stochastic process, physical property analysis

Publications

[J3] Jaesung Lee, Shiyu Zhou, and Junhong Chen, “Statistical Modeling and Analysis of k-Layer Coverage of Two-Dimensional Materials in Inkjet Printing Processes,” Technometrics, vol. 63, no. 3, pp. 410–420, 2021, doi:10.1080/00401706.2020.1805020.
Publication record: [J3]
[C3] J. Lee, C. Wang, S. Zhou, and J. Chen, “Spatial distribution quantification and control of ink flakes in reduced graphene oxide FET inkjet printing,” Procedia Manufacturing, vol. 34, pp. 19–25, 2019, 47th SME North American Manufacturing Research Conference, NAMRC 47, Pennsylvania, USA, doi:10.1016/j.promfg.2019.06.109.
Publication record: [C3]

Research diagram: Monitoring: Probability Modeling & Quality Control of Additive Nanosensor Manufacturing Process — Monitoring: Probability Modeling & Quality Control of Additive Nanosensor Manufacturing Process View full-size figure

Data-driven Robust Design Optimization of Advanced Engineering System or Nanosensors

Goal: Data-driven design method minimizing the variance while satisfying mean outputs leveraging prediction & uncertainty

Methodologies: Bayesian optimization, Gaussian process modeling

Publications

[J8] Jaesung Lee, Shiyu Zhou, and Junhong Chen, “Robust Parameter Design on Dual Stochastic Response Models With Constrained Bayesian Optimization,” IEEE Transactions on Automation Science and Engineering, vol. 21, no. 2, pp. 2039–2050, 2024, doi:10.1109/TASE.2023.3251973.
Publication record: [J8]

Other Bayesian optimization (Process/System/Design optimization) papers:

[J5] Congfang Huang, Jaesung Lee, Yang Zhang, Shiyu Zhou, and Jiong Tang, “Mixed-Input Bayesian Optimization Method for Structural Damage Diagnosis,” IEEE Transactions on Reliability, vol. 72, no. 2, pp. 678–691, 2023, doi:10.1109/TR.2022.3179602.
Publication record: [J5]
[C4] J. Lee, S. Zhou, and J. Chen, “Sequential Robust Parameter Design With Sample Size Selection,” ASME 2022 17th International Manufacturing Science and Engineering Conference, vol. 85819, article V002T06A024, 2022, Indiana, USA, doi:10.1115/MSEC2022-85690.
Publication record: [C4]

Research diagram: Data-driven Robust Design Optimization of Advanced Engineering System or Nanosensors — Data-driven Robust Design Optimization of Advanced Engineering System or Nanosensors View full-size figure

Nonparametric Statistical Functional Data Modeling for Nanosensors & Statistical Calibration with Uncertainty Quantification

Goal: Uncertainty quantification, inference of underlying physical variable based on functional data

Methodologies: Functional data modeling, Gaussian Process modeling, Bayesian inference

Publications

[J4] Jaesung Lee, Chao Wang, Xiaoyu Sui, Shiyu Zhou, and Junhong Chen, “Landmark-embedded Gaussian process with applications for functional data modeling,” IISE Transactions, vol. 54, no. 11, pp. 1033–1046, 2022, doi:10.1080/24725854.2021.1974129.
Publication record: [J4]
- This paper was featured in the ISE Magazine (October 2022 issue)
- This work was selected as the Best Paper in IISE Transactions in 2024.

Research diagram: Nonparametric Statistical Functional Data Modeling for Nanosensors & Statistical Calibration with Uncertainty Quantification — Nonparametric Statistical Functional Data Modeling for Nanosensors & Statistical Calibration with Uncertainty Quantification View full-size figure

Diagnosis on Faulty Operation leveraging domain knowledge IoT-enabled Smart and Connected Manufacturing System

IoT-enabled Smart and Connected System

Goal: Identifying faulty operations with excessive variation in a multistage manufacturing system; establishing a sparse-variance statistical model.

Methodologies: Random-effects model, hierarchical Bayesian prior modeling

Publications

[J2] Jaesung Lee, Junbo Son, Shiyu Zhou, and Yong Chen, “Variation source identification in manufacturing processes using Bayesian approach with sparse variance components prior,” IEEE Transactions on Automation Science and Engineering, vol. 17, no. 3, pp. 1469–1485, 2020, doi:10.1109/TASE.2019.2959605.
Publication record: [J2]

Research diagram: Diagnosis on Faulty Operation leveraging domain knowledge IoT-enabled Smart and Connected Manufacturing System — Diagnosis on Faulty Operation leveraging domain knowledge IoT-enabled Smart and Connected Manufacturing System View full-size figure

Collaborated Research: Fully Inkjet-Printed, 2D Materials-Based Field-Effect Transistor for Water Sensing

Detail: Printing uniform channels by the (nano) inkjet printer is extremely challenging due to the well-known coffee-ring effects. The quality of the inkjet printed pattern hinges on many factors, including various material properties and temperature, which are often difficult to obtain. In this work, we proposed a method to achieve a uniform channel covered by an average of a single layer of graphene. By leveraging the fact that multiple printing passes can smooth out the coffee ring effects on the boundary, we formulate an optimization problem and achieve a uniform single layer coverage on the target region.

Publications

[J7] Xiaoyu Sui, Sonal V. Rangnekar, Jaesung Lee, Stephanie E. Liu, Julia R. Downing, Lindsay E. Chaney, Xiaodong Yan, Hyun-June Jang, Haihui Pu, Xiaoao Shi, Shiyu Zhou, Mark C. Hersam, and Junhong Chen, “Fully Inkjet-Printed, 2D Materials-Based Field-Effect Transistor for Water Sensing,” Advanced Materials Technologies, vol. 8, no. 22, article 2301288, 2023, doi:10.1002/admt.202301288.
Publication record: [J7]
- This paper was selected as the top viewed article in 2023.

Research diagram: Collaborated Research: Fully Inkjet-Printed, 2D Materials-Based Field-Effect Transistor for Water Sensing — Collaborated Research: Fully Inkjet-Printed, 2D Materials-Based Field-Effect Transistor for Water Sensing View full-size figure