Computationally efficient nonstationary nearest‐neighbor Gaussian process models using data‐driven techniques

2019 ◽  
Vol 30 (8) ◽  
Author(s):  
B. A. Konomi ◽  
A. A. Hanandeh ◽  
P. Ma ◽  
E. L. Kang
Keyword(s):  
Gaussian Process ◽  
Nearest Neighbor ◽  
Process Models ◽  
Data Driven ◽  
Computationally Efficient ◽  
Gaussian Process Models ◽  
Using Data

scholarly journals Hierarchical Nearest-Neighbor Gaussian Process Models for Large Geostatistical Datasets

2016 ◽  
Vol 111 (514) ◽  
pp. 800-812 ◽  
Author(s):  
Abhirup Datta ◽  
Sudipto Banerjee ◽  
Andrew O. Finley ◽  
Alan E. Gelfand
Keyword(s):  
Gaussian Process ◽  
Nearest Neighbor ◽  
Process Models ◽  
Gaussian Process Models

Machine Learning-Enabled Prediction of Transient Injection Map In Automotive Injectors With Uncertainty Quantification

2021 ◽  
Author(s):  
Sudeepta Mondal ◽  
Gina M. Magnotti ◽  
Bethany Lusch ◽  
Romit Maulik ◽  
Roberto Torelli
Keyword(s):  
Machine Learning ◽  
Gaussian Process ◽  
Void Fraction ◽  
Internal Flow ◽  
Operating Conditions ◽  
Process Models ◽  
Data Driven ◽  
Design Parameters ◽  
Uncertainty Estimates ◽  
Gaussian Process Models

Abstract Accurate prediction of injection profiles is a critical aspect of linking injector operation with engine performance and emissions. However, highly resolved injector simulations can take one to two weeks of wall-clock time, which is incompatible with engine design cycles with desired turnaround times of less than a day. Hence, it is important to reduce the time-to-solution of the internal flow simulations by several orders of magnitude to make it compatible with engine simulations. This work demonstrates a data-driven approach for tackling the computational overhead of injector simulations, whereby the transient injection profiles are emulated for a side-oriented, single-hole diesel injector using a Bayesian machine-learning framework. First, an interpretable Bayesian learning strategy was employed to understand the effect of design parameters on the total void fraction field. Then, autoencoders are utilized for efficient dimensionality reduction of the flowfields. Gaussian process models are finally used to predict the spatio-temporal void fraction field at the injector exit for unknown operating conditions. The Gaussian process models produce principled uncertainty estimates associated with the emulated flowfields, which provide the engine designer with valuable information of where the data-driven predictions can be trusted in the design space. The Bayesian flowfield predictions are compared with the corresponding predictions from a deep neural network, which has been transfer-learned from static needle simulations from a previous work by the authors. The emulation framework can predict the void fraction field at the exit of the orifice within a few seconds, thus achieving a speed-up factor of up to 38 million over the traditional simulation-based approach of generating transient injection maps.

scholarly journals Nonseparable dynamic nearest neighbor Gaussian process models for large spatio-temporal data with an application to particulate matter analysis

2016 ◽  
Vol 10 (3) ◽  
pp. 1286-1316 ◽  
Author(s):  
Abhirup Datta ◽  
Sudipto Banerjee ◽  
Andrew O. Finley ◽  
Nicholas A. S. Hamm ◽  
Martijn Schaap
Keyword(s):  
Particulate Matter ◽  
Gaussian Process ◽  
Nearest Neighbor ◽  
Process Models ◽  
Temporal Data ◽  
Gaussian Process Models ◽  
Spatio Temporal

scholarly journals Hybrid Gaussian Process Models for continuous time series in bolus fed-batch cultures

2021 ◽  
Author(s):  
Mariano Nicolas Cruz-Bournazou ◽  
Harini Narayanan ◽  
Alessandro Fagnani ◽  
Alessandro Butte
Keyword(s):  
Differential Equation ◽  
Gaussian Process ◽  
Continuous Time ◽  
Polynomial Regression ◽  
Machine Learning Algorithms ◽  
Process Models ◽  
Data Driven ◽  
Support Vector ◽  
Fed Batch ◽  
Gaussian Process Models

Hybrid modeling, meaning the integration of data-driven and knowledge-based methods, is quickly gaining popularity among many research fields, including bioprocess engineering and development. Recently, the data-driven part of hybrid methods have been largely extended with machine learning algorithms (e.g., artificial neural network, support vector regression), while the mechanistic part is typically using differential equations to describe the dynamics of the process based on its current state. In this work we present an alternative hybrid model formulation that merges the advantages of Gaussian Process State Space Models and the numerical approximation of differential equation systems through full discretization. The use of Gaussian Process Models to describe complex bioprocesses in batch, fed-batch, has been reported in several applications. Nevertheless, handling the dynamics of the states of the system, known to have a continuous time-dependent evolution governed by implicit dynamics, has proven to be a major challenge. Discretization of the process on the sampling steps is a source of several complications, as are: 1) not being able to handle multi-rate date sets, 2) the step-size of the derivative approximation is defined by the sampling frequency, and 3) a high sensitivity to sampling and addition errors. We present a coupling of polynomial regression with Gaussian Process Models as representation of the right-hand side of the ordinary differential equation system and demonstrate the advantages in a typical fed-batch cultivation for monoclonal antibody production.

scholarly journals On nearest-neighbor Gaussian process models for massive spatial data

2016 ◽  
Vol 8 (5) ◽  
pp. 162-171 ◽  
Author(s):  
Abhirup Datta ◽  
Sudipto Banerjee ◽  
Andrew O. Finley ◽  
Alan E. Gelfand
Keyword(s):  
Gaussian Process ◽  
Spatial Data ◽  
Nearest Neighbor ◽  
Process Models ◽  
Gaussian Process Models ◽  
Massive Spatial Data

Identification of Continuous-time Nonlinear Systems via Local Gaussian Process Models

2014 ◽  
Vol 134 (11) ◽  
pp. 1708-1715
Author(s):  
Tomohiro Hachino ◽  
Kazuhiro Matsushita ◽  
Hitoshi Takata ◽  
Seiji Fukushima ◽  
Yasutaka Igarashi
Keyword(s):  
Nonlinear Systems ◽  
Gaussian Process ◽  
Continuous Time ◽  
Process Models ◽  
Gaussian Process Models
Sign in / Sign up

Export Citation Format

Share Document