Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List

Full text release has been delayed at the author's request until December 10, 2024

ETD Abstract Container

Abstract Header

Neural Network Emulation for Computer Model with High Dimensional Outputs using Feature Engineering and Data Augmentation

Alamari, Mohammed Barakat
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1668635352808922

Abstract Details

2022, PhD, University of Cincinnati, Arts and Sciences: Mathematical Sciences.
Expensive computer models (simulators) are frequently used to simulate the behavior of a complex system in many scientific fields because an explicit experiment is very expensive or dangerous to conduct. Usually, only a limited number of computer runs are available due to limited sources. Therefore, one desires to use the available runs to construct an inexpensive statistical model, an emulator. Then the constructed statistical model can be used as a surrogate for the computer model. Building an emulator for high dimensional outputs with the existing standard method, the Gaussian process model, can be computationally infeasible because it has a cubic computational complexity that scales with the total number of observations. Also, it is common to impose restrictions on the covariance matrix of the Gaussian process model to keep computations tractable. This work constructs a flexible emulator based on a deep neural network (DNN) with feedforward multilayer perceptrons (MLP). High dimensional outputs and limited runs can pose considerable challenges to DNN in learning a complex computer model's behavior. To overcome this challenge, we take advantage of the computer model's spatial structure to engineer features at each spatial location and then make the training of DNN feasible. Also, to improve the predictive performance and avoid overfitting, we adopt a data augmentation technique into our method. Finally, we apply our approach using data from the UVic ESCM model and the PSU3D-ICE model to demonstrate good predictive performance and compare it with an existing state-of-art emulation method.
Won Chang, Ph.D. (Committee Member)
Xia Wang, Ph.D. (Committee Member)
Emily Kang, Ph.D. (Committee Member)
89 p.
Statistics
Computer Model Emulation; Deep Neural Networks

Recommended Citations

Citations

  • Alamari, M. B. (2022). Neural Network Emulation for Computer Model with High Dimensional Outputs using Feature Engineering and Data Augmentation [Doctoral dissertation, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1668635352808922

    APA Style (7th edition)

  • Alamari, Mohammed Barakat. Neural Network Emulation for Computer Model with High Dimensional Outputs using Feature Engineering and Data Augmentation. 2022. University of Cincinnati, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1668635352808922.

    MLA Style (8th edition)

  • Alamari, Mohammed Barakat. "Neural Network Emulation for Computer Model with High Dimensional Outputs using Feature Engineering and Data Augmentation." Doctoral dissertation, University of Cincinnati, 2022. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1668635352808922

    Chicago Manual of Style (17th edition)

ucin1668635352808922
© 2022, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.