Adaptive residual modeling for scenario-based load forecasting

Integrating ML and uncertainty quantification for real-time decisions in digital twins

A narrative review examines how predictive modeling, machine learning, uncertainty quantification and decision-making are combined in engineering digital twins. It surveys decision architectures and methods addressing their limits across the decision loop, with attention to maintaining them during online operation.

Calibrating persona-based digital twin simulation against real data

Evaluating workforce training programs with tax records and experimental benchmarks

Using anonymized income tax records for all US adults from 1999 to 2025, the study estimates earnings effects of workforce training programs, predicting counterfactuals with machine learning from work histories, demographics and location. Estimated bias is benchmarked against 37 randomized controlled trials.