scholarly journals Multifidelity computing for coupling full and reduced order models

PLoS ONE ◽  
2021 ◽  
Vol 16 (2) ◽  
pp. e0246092
Author(s):  
Shady E. Ahmed ◽  
Omer San ◽  
Kursat Kara ◽  
Rami Younis ◽  
Adil Rasheed
Keyword(s):  
Short Term Memory ◽  
Broad Class ◽  
Integrated Approach ◽  
Building Blocks ◽  
Transport Processes ◽  
Learning Approaches ◽  
Order Model ◽  
Reduced Order ◽  
Memory Network ◽  
Spatiotemporal Scales

Hybrid physics-machine learning models are increasingly being used in simulations of transport processes. Many complex multiphysics systems relevant to scientific and engineering applications include multiple spatiotemporal scales and comprise a multifidelity problem sharing an interface between various formulations or heterogeneous computational entities. To this end, we present a robust hybrid analysis and modeling approach combining a physics-based full order model (FOM) and a data-driven reduced order model (ROM) to form the building blocks of an integrated approach among mixed fidelity descriptions toward predictive digital twin technologies. At the interface, we introduce a long short-term memory network to bridge these high and low-fidelity models in various forms of interfacial error correction or prolongation. The proposed interface learning approaches are tested as a new way to address ROM-FOM coupling problems solving nonlinear advection-diffusion flow situations with a bifidelity setup that captures the essence of a broad class of transport processes.

scholarly journals A Comparative Analysis for Air Quality Estimation from Traffic and Meteorological Data

2020 ◽  
Vol 10 (13) ◽  
pp. 4587 ◽  
Author(s):  
Edoardo Arnaudo ◽  
Alessandro Farasin ◽  
Claudio Rossi
Keyword(s):  
Air Quality ◽  
Quality Index ◽  
Linear Models ◽  
Short Term Memory ◽  
Meteorological Data ◽  
Learning Approaches ◽  
Short Term ◽  
Quality Estimation ◽  
Memory Network ◽  
Long Short Term Memory

Air pollution in urban regions remains a crucial subject of study, given its implications on health and environment, where much effort is often put into monitoring pollutants and producing accurate trend estimates over time, employing expensive tools and sensors. In this work, we study the problem of air quality estimation in the urban area of Milan (IT), proposing different machine learning approaches that combine meteorological and transit-related features to produce affordable estimates without introducing sensor measurements into the computation. We investigated different configurations employing machine and deep learning models, namely a linear regressor, an Artificial Neural Network using Bayesian regularization, a Random Forest regressor and a Long Short Term Memory network. Our experiments show that affordable estimation results over the pollutants can be achieved even with simpler linear models, therefore suggesting that reasonably accurate Air Quality Index (AQI) measurements can be obtained without the need for expensive equipment.

Initially Imperfect MEMS Microplates Under Electrostatic Actuation: Theory and Experiment

2016 ◽  
Author(s):  
Shahid Saghir ◽  
Mohammed L. Bellaredj ◽  
Mohammad I. Younis
Keyword(s):  
Building Blocks ◽  
Governing Equations ◽  
Flat Plates ◽  
Order Model ◽  
Micro Electro Mechanical Systems ◽  
Reduced Order ◽  
Electrostatically Actuated ◽  
Harmonic Voltage ◽  
Static Behaviour ◽  
Good Agreement

Microplates are building blocks of many Micro-Electro-Mechanical Systems (MEMS). It is common for them to undergo imperfections due to residual stresses caused by the micro fabrication process. Such plates are essentially different from perfectly flat plates and cannot be modeled using the governing equations of flat plates. In this article, we adopt the governing equations of imperfect plates employing the modified von-Karman strains. These equations then are used to develop a Reduced Order Model based on the Galerkin procedure to simulate the static and dynamic behavior of an electrostatically actuated microplate. Also, microplates made of silicon nitride are fabricated and tested. First, the static behaviour of the microplate is investigated when applying a static voltage Vdc. To study the dynamic behaviour we apply a harmonic voltage, Vac, superimposed to Vdc. Simulation results show good agreement with the experimentally measured responses.

Learnt variability as a tool for climate prediction and predictability

2020 ◽  
Author(s):  
Balasubramanya Nadiga
Keyword(s):  
Short Term Memory ◽  
Fluid Flows ◽  
Climate Prediction ◽  
Lead Times ◽  
Network Architectures ◽  
Learning Approaches ◽  
Earth System ◽  
Practical Tool ◽  
Memory Network ◽  
Near Term

<p>Whether it is turbulence fluid flows or climate variability, there is a big gap between our ability to develop understanding of underlying phenomena/processes and our ability to produce skillful predictions. We focus on near-term prediction of climate as an example. In this context, the state-of-the-art is such that we are able to predict how 30-year global averages of surface temperature will change, but we are unable to predict shorter time scale regional changes.  We investigate a range of deep learning approaches to the problem ranging from reservoir computing to deep convolutional Long Short-Term Memory network architectures. The best performing architectures are seen to be capable of predicting an Earth System Model’s leading modes of global temperature variability with prediction lead times of up to a year. This approach is proposed as a useful practical tool for climate prediction. Further insight into the difficulty of the prediction problem is provided by considering the Lorenz '63 model: Long prediction horizons seen when the system is fully observed is seen to be progressively degraded as the system is less thoroughly observed, while noting the difficulty of fully observing the earth system</p>

Sign in / Sign up

Export Citation Format

Share Document