Digital twinОпубликованы итоги форсайт-сессии «Будущее безопасности киберфизических систем в России. Перспективы и векторы развития»spbIT · 3hModellingStochastic Model Predictive Control under AC Power-Flow Constraints Using Generative LearningarXiv — Systems and Control (eess.SY) · yesterdayMarket & productsPalantir меняет метрику: вместо количества клиентов — совокупная стоимость контрактовTechora.ru · 11hModellingАтаки на агентные системы и защита данныхХабр · 16hDigital twinEmbedding Model-form Uncertainty in Probabilistic Calibration of Digital Twins for BridgesarXiv API — полнотекстовый поиск "digital twin" · 17hModellingAgentHomeID - Agent-based modelling of building stock transformation: A multi-scale framework for policy assessment and infrastructure planningarXiv — Systems and Control (eess.SY) · yesterdayDigital twinFrom State Synchronization to Cognitive Self-Evolution: An Operational Architecture for Cognitive Digital TwinsarXiv API — полнотекстовый поиск "digital twin" · yesterdayForecastingTD-STGT: A Spatio-Temporal Graph Transformer for Mobile Traffic Demand ForecastingarXiv — Systems and Control (eess.SY) · yesterdayForecastingUser-specified Kelvin-hour budgets within model predictive control for energy-efficient buildings: Simulation and field demonstrationarXiv — Systems and Control (eess.SY) · yesterdayForecastingKoopman-Based Model Predictive Control for Simultaneous State of Charge and Temperature Balancing of Lithium-Ion CellsarXiv — Systems and Control (eess.SY) · yesterdayForecastingModel Predictive Control for Dynamic Hydraulic Balancing in Building Radiator Heating Systems: Modeling, Design, and Experimental ValidationarXiv — Systems and Control (eess.SY) · yesterdayForecastingAsynchronous Model Predictive Control Under Model Mismatch: Stability and Performance GuaranteesarXiv — Systems and Control (eess.SY) · yesterday
Deep Learning for Fast Climate Risk Assessment of Crops
US & West ·
A deep-learning framework SECSF is presented that emulates the process-based ECroPS model for maize and barley using only daily temperatures and precipitation. Trained on ERA5 data, it reproduces crop growth dynamics and harvest timing while reducing computational cost by ~10^4 times, enabling probabilistic risk assessment for large seasonal and climate ensembles.
Why it matters
Important for scalable forecasting in agriculture, where fast and accurate climate risk estimates are crucial.
arXiv:2609.06636v1 Announce Type: new Abstract: Fine-grained mobile traffic demand forecasting is essential for long-term planning of 5G and future 6G networks, including radio upgrades, site densification, backhaul expansion, and spectrum activation.
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.
Two headroom-aware adaptive MPC strategies are developed for PV-dominated microgrids, accounting for stochastic and time-varying reserve headroom of inverter-based resources to avoid control saturation and improve load frequency control.
