Generative Flow Networks for Model Adaptation in Digital Twins of Natural Systems

2026-04-22

AI Summary

This study addresses the non-identifiability of model calibration in digital twins of evolving natural systems, which arises from sparse observations and unmeasurable parameters. To tackle this challenge, the work introduces Generative Flow Networks (GFlowNets) into adaptive digital twin modeling for the first time, framing the problem as a simulation-based inference task. By leveraging a mechanistic simulator and an observation-consistency reward, the GFlowNet probabilistically models complete simulation configurations, enabling the simultaneous retention of multiple plausible calibration hypotheses while concentrating sampling on high-likelihood regions. Evaluated on a tomato growth control scenario in agriculture, the proposed approach successfully reconstructs dominant regions of the adaptive landscape, efficiently retrieves strongly calibrated solutions, and preserves the capacity to represent solution multiplicity under uncertainty.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Digital twins of natural systems must remain aligned with physical systems that evolve over time, are only partially observed, and are typically modeled by mechanistic simulators whose parameters cannot be measured directly. In such settings, model adaptation is naturally posed as a simulation-based inference problem. However, sparse and indirect observations often fail to identify a unique and optimal calibration, leaving several simulator parameterizations compatible with the available evidence. This article presents a GFlowNet-based approach to model adaptation for digital twins of natural systems. We formulate adaptation as a generative modeling problem over complete simulator configurations, so that plausible parameterizations can be sampled with probability proportional to a reward derived from agreement between simulated and observed behavior. Using a controlled environment agriculture case study based on a mechanistic tomato model, we show that the learned policy recovers dominant regions of the adaptation landscape, retrieves strong calibration hypotheses, and preserves multiple plausible configurations under uncertainty.

Problem

• digital twins
• model adaptation
• simulation-based inference
• parameter calibration
• natural systems

Innovation

• Generative Flow Networks
• Model Adaptation
• Digital Twins
• Simulation-based Inference
• Mechanistic Simulators