Research
Papers and Research Work
08/2026
The Two Faces of Outliers in Distributionally Robust Learning: Exclusion and Emphasis via One-Sided Partial Optimal Transport
Teach robust models to learn more from unusual but informative data that is often overlooked.
2026/08
Distributionally robust optimization for Gaussian mixture model ambiguity under moment variations
Make reliable decisions when the likelihood of different operating conditions is well known, but the outcomes within each condition are uncertain.
04/2026
Database-driven and property-constrained inference of molecular composition of petroleum fractions from routine experimental data
Bring molecular-level petroleum analysis closer to everyday refinery lab tests.
10/2025
Simultaneous outlier-exclusion and distributionally robust learning through partial optimal transport
Teach robust models to separate truly misleading data from unusual but useful surprises.
09/2025
Molecular composition reconstruction of naphtha fractions through data-driven modeling and interpretable optimization
From a few routine fuel measurements, rebuild the molecular ingredient list of naphtha.
03/2025
Dynamic Process Flexibility Analysis Using Neural Networks and a Volumetric Flexibility Index
Measure how much breathing room a process has while its safe operating region changes over time.
06/2024
Novel feasible set learning and process flexibility analysis method using deep neural networks
Design neural networks to find and measure scattered safe operating zones.
01/2024
Model Predictive Control for Renal Anemia Treatment through Physics-informed Neural Network
Turn hemoglobin prediction into a dosing planner that keeps treatment inside a healthy target zone.
08/2023
Haemoglobin response modelling under erythropoietin treatment: Physiological model-informed machine learning method
Predict how a patient's hemoglobin will respond by combining clinical data with the body's known biology.