Digital twinEarth System World Model for What-If Simulations: A Case Study for Terrestrial EcosystemsarXiv API — полнотекстовый поиск "digital twin" · 14hDigital twinDigital Twin and Extended Reality for Robot-Assisted FinishingarXiv API — полнотекстовый поиск "digital twin" · 12hModellingStochastic Adaptive MPC for Load Frequency Control in MicrogridsarXiv — Systems and Control (eess.SY) · 2dForecastingCritical Review of LLMs for HVAC Operations in BuildingsarXiv — Systems and Control (eess.SY) · 2dDigital twinWhen Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical SubstitutabilityarXiv API — полнотекстовый поиск "digital twin" · yesterdayDigital twinCyber-physical systems lab opens at Voronezh State UniversityВоронежский госуниверситет · yesterdayDigital twinKODAMA: Multimodal Digital Twin Reconstruction for Urban RF Propagation ModellingarXiv API — полнотекстовый поиск "digital twin" · yesterdayDigital twinAI-Powered CPS Urban Transportation Digital TwinarXiv — Systems and Control (eess.SY) · 2dModellingSelectel and ITMO JV develops multi-agent system technologies for businessspbIT · 2dForecastingGrid-Aware MPC for Smoothing AI Data Center Power DemandarXiv — Systems and Control (eess.SY) · 2dEnergyComparison of Direct vs Indirect Net Load Forecasting with RenewablesarXiv — Systems and Control (eess.SY) · 2dDigital twinHalifaxDT: A Wireless Digital Twin from Open Geospatial DataarXiv API — полнотекстовый поиск "digital twin" · 4d
Digital Twin for Personalized Respiratory Support Decisions
US & West ·
A digital twin named DINIRS was developed and validated to estimate individualized treatment effects when choosing between noninvasive and invasive respiratory support for patients with acute respiratory failure. The model uses 23 clinical variables from the first 24 ICU hours of 5,336 patients from MIMIC-IV. DINIRS accounts for censoring and predicts both mortality and ventilation duration, helping clinicians make more informed decisions.
Why it matters
The news illustrates the application of digital twins for personalized management in medicine, resonating with the challenges of modeling complex systems with heterogeneous effects.
An action-conditioned world-modeling framework for Earth-system emulation is proposed, allowing users to specify interventions and explore system responses. It reformulates simulator trajectories as supervision for controllable state-transition learning, going beyond passive forecasting. This is relevant for interactive scientific workflows and Earth-system digital twins.
A cyber-physical system is presented for programming, supervision, training, and teleoperation of robot-assisted finishing of metal additive-manufactured parts. A digital twin built in Unity is delivered as a WebGL app supporting desktop and WebXR modes, exchanging robot state and pose commands with a collaborative robot via MQTT. The twin enforces kinematic and collision constraints before releasing poses and augments the virtual component with a color map of surface topography to support operator decisions.
The concept of statistical substitutability is introduced to assess whether LLM-based digital twins can replace repeated human data collection while preserving valid inference. A framework grounded in mixed-subject and prediction-powered inference evaluates four dimensions: aggregate fidelity, paired respondent-level signal, finite-sample label recovery, and stability across populations. This helps determine when twins can reduce measurement burden.
