Macroscopic Model

Macroscopic models aim to describe the overall behavior of complex systems by focusing on aggregate properties rather than individual components. Current research emphasizes developing and validating these models across diverse applications, including traffic flow optimization (using methods like deep learning with Graph Attention Networks and Recurrent Units), autonomous swarm robotics (combining formal verification with real-world experiments), and material science (employing physics-informed neural networks and thermodynamic principles). This approach offers significant advantages in computational efficiency and interpretability, leading to improved predictions and control in various fields ranging from transportation to manufacturing and even neuroscience.

Papers

October 31, 2024

Learning Macroscopic Dynamics from Partial Microscopic Observations
Mengyi Chen, Qianxiao Li
Partial Observation Atomic Knowledge Thermodynamic Observables Closure Model Macroscopic Model

July 22, 2024

A Multi-Level Corroborative Approach for Verification and Validation of Autonomous Robotic Swarms
Dhaminda B. Abeywickrama, Suet Lee, Chris Bennett, Razanne Abu-Aisheh, Tom Didiot-Cook, Simon Jones, Sabine Hauert, Kerstin Eder
Verification Task External Validation Real Robot Autonomous Robotic Swarm Macroscopic Model

May 23, 2024

Deep Learning Methods for Adjusting Global MFD Speed Estimations to Local Link Configurations
Zhixiong Jin, Dimitrios Tsitsokas, Nikolas Geroliminis, Ludovic Leclercq
Deep Learning World Event Traffic Management Macroscopic Model Speed Estimation

May 3, 2024

Dyna-Style Learning with A Macroscopic Model for Vehicle Platooning in Mixed-Autonomy Traffic
Yichuan Zou, Li Jin, Xi Xiong
Autonomous Vehicle Platoon Control Mixed Autonomy Traffic Macroscopic Model Smart Road GD Learning

March 4, 2024

Macroscopic auxiliary asymptotic preserving neural networks for the linear radiative transfer equations
Hongyan Li, Song Jiang, Wenjun Sun, Liwei Xu, Guanyu Zhou
Neural Network Physic Informed Neural Network Transfer Function Radiative Transfer Macroscopic Model

January 30, 2024

Traffic estimation in unobserved network locations using data-driven macroscopic models
Pablo Guarda, Sean Qian
Travel Time Transportation Network Traffic Assignment Travel Time Estimation Macroscopic Model Unobserved Node Macroscopic Traffic Traffic Estimation

December 14, 2023

Real-time Autonomous Control of a Continuous Macroscopic Process as Demonstrated by Plastic Forming
Shun Muroga, Takashi Honda, Yasuaki Miki, Hideaki Nakajima, Don N. Futaba, Kenji Hata
Active Learning Algorithm Autonomous Control Profile Extrusion Macroscopic Model Manufacturing Process Fat Shattering Dimension Iterative Source Situ Sensing

August 29, 2023

Thermodynamics-inspired Macroscopic States of Bounded Swarms
Hossein Haeri, Kshitij Jerath, Jacob Leachman
Robot Swarm Macroscopic Model Swarm Architecture Swarm Feature Macroscopic Change

August 22, 2023

Generalized dimension reduction approach for heterogeneous networked systems with time-delay
Cheng Ma, Gyorgy Korniss, Boleslaw K. Szymanski, Jianxi Gao
High Dimensional Nonlinear Dynamic Complex Network Dimension Reduction Heterogeneous Network Macroscopic Model

August 8, 2023

Constructing Custom Thermodynamics Using Deep Learning
Xiaoli Chen, Beatrice W. Soh, Zi-En Ooi, Eleonore Vissol-Gaudin, Haijun Yu, Kostya S. Novoselov, Kedar Hippalgaonkar, Qianxiao Li
Deep Learning Elastomer Deformation Particle Trajectory Macroscopic Model

May 10, 2023

A synchronization-capturing multi-scale solver to the noisy integrate-and-fire neuron networks
Ziyu Du, Yantong Xie, Zhennan Zhou
Automatic Solver Neuronal Network Fokker Planck Equation Multiscale System Macroscopic Model

March 21, 2023

Inverting the Fundamental Diagram and Forecasting Boundary Conditions: How Machine Learning Can Improve Macroscopic Models for Traffic Flow
Maya Briani, Emiliano Cristiani, Elia Onofri
Machine Learning LSTM Network Traffic Flow Multi Class Traffic Model Fundamental Diagram Boundary Prediction Macroscopic Model Traffic Estimation

December 3, 2022

Quantify the Causes of Causal Emergence: Critical Conditions of Uncertainty and Asymmetry in Causal Structure
Liye Jia, Fengyufan Yang, Ka Lok Man, Erick Purwanto, Sheng-Uei Guan, Jeremy Smith, Yutao Yue
High Uncertainty Anticipation Causal Structure Causal Relationship Actual Cause Information Theoretic Framework Macroscopic Model

September 27, 2022

Evolution TANN and the identification of internal variables and evolution equations in solid mechanics
Filippo Masi, Ioannis Stefanou
Person Identification Constitutive Model Variable Model Solid Mechanic Incremental Model Macroscopic Model

January 10, 2022

Macroprogramming: Concepts, State of the Art, and Opportunities of Macroscopic Behaviour Modelling
Roberto Casadei
Emerging Opportunity Internal State Concept Identification Programming Assistance Global Scale Macroscopic Model Collective Response System

December 31, 2021

How Infinitely Wide Neural Networks Can Benefit from Multi-task Learning -- an Exact Macroscopic Characterization
Jakob Heiss, Josef Teichmann, Hanna Wutte
Deep Neural Network Multi Task Learning Neural Tangent Kernel Wide Neural Network Macroscopic Model

Macroscopic Model

Papers

Learning Macroscopic Dynamics from Partial Microscopic Observations

A Multi-Level Corroborative Approach for Verification and Validation of Autonomous Robotic Swarms

Deep Learning Methods for Adjusting Global MFD Speed Estimations to Local Link Configurations

Dyna-Style Learning with A Macroscopic Model for Vehicle Platooning in Mixed-Autonomy Traffic

Macroscopic auxiliary asymptotic preserving neural networks for the linear radiative transfer equations

Traffic estimation in unobserved network locations using data-driven macroscopic models

Real-time Autonomous Control of a Continuous Macroscopic Process as Demonstrated by Plastic Forming

Thermodynamics-inspired Macroscopic States of Bounded Swarms

Generalized dimension reduction approach for heterogeneous networked systems with time-delay

Constructing Custom Thermodynamics Using Deep Learning

A synchronization-capturing multi-scale solver to the noisy integrate-and-fire neuron networks

Inverting the Fundamental Diagram and Forecasting Boundary Conditions: How Machine Learning Can Improve Macroscopic Models for Traffic Flow

Quantify the Causes of Causal Emergence: Critical Conditions of Uncertainty and Asymmetry in Causal Structure

Evolution TANN and the identification of internal variables and evolution equations in solid mechanics

Macroprogramming: Concepts, State of the Art, and Opportunities of Macroscopic Behaviour Modelling

How Infinitely Wide Neural Networks Can Benefit from Multi-task Learning -- an Exact Macroscopic Characterization