More Like this

1. Physics-Based Regression vs. CFD for Hagen-Poiseuille and Womersley Flows and Uncertainty Quantification

   Li, H.; Islam, M.; Yu, H.; Du, X. (July 2022, Eleventh International Conference on Computational Fluid Dynamics (ICCFD11))

   Brehm, Christoph; Pandya, Shishir (Ed.)

   Computational fluid dynamics (CFD) and its uncertainty quantification are computationally expensive. We use Gaussian Process (GP) methods to demonstrate that machine learning can build efficient and accurate surrogate models to replace CFD simulations with significantly reduced computational cost without compromising the physical accuracy. We also demonstrate that both epistemic uncertainty (machine learning model uncertainty) and aleatory uncertainty (randomness in the inputs of CFD) can be accommodated when the machine learning model is used to reveal fluid dynamics. The demonstration is performed by applying simulation of Hagen-Poiseuille and Womersley flows that involve spatial and spatial-tempo responses, respectively. Training points are generated by using the analytical solutions with evenly discretized spatial or spatial-temporal variables. Then GP surrogate models are built using supervised machine learning regression. The error of the GP model is quantified by the estimated epistemic uncertainty. The results are compared with those from GPU-accelerated volumetric lattice Boltzmann simulations. The results indicate that surrogate models can produce accurate fluid dynamics (without CFD simulations) with quantified uncertainty when both epistemic and aleatory uncertainties exist. 

   more » « less
2. Machine learning electronic structure methods based on the one-electron reduced density matrix

   https://doi.org/10.1038/s41467-023-41953-9  

   Shao, Xuecheng; Paetow, Lukas; Tuckerman, Mark E.; Pavanello, Michele (December 2023, Nature Communications)

   Abstract The theorems of density functional theory (DFT) establish bijective maps between the local external potential of a many-body system and its electron density, wavefunction and, therefore, one-particle reduced density matrix. Building on this foundation, we show that machine learning models based on the one-electron reduced density matrix can be used to generate surrogate electronic structure methods. We generate surrogates of local and hybrid DFT, Hartree-Fock and full configuration interaction theories for systems ranging from small molecules such as water to more complex compounds like benzene and propanol. The surrogate models use the one-electron reduced density matrix as the central quantity to be learned. From the predicted density matrices, we show that either standard quantum chemistry or a second machine-learning model can be used to compute molecular observables, energies, and atomic forces. The surrogate models can generate essentially anything that a standard electronic structure method can, ranging from band gaps and Kohn-Sham orbitals to energy-conserving ab-initio molecular dynamics simulations and infrared spectra, which account for anharmonicity and thermal effects, without the need to employ computationally expensive algorithms such as self-consistent field theory. The algorithms are packaged in an efficient and easy to use Python code, QMLearn, accessible on popular platforms. 

   more » « less
3. Modern semiempirical electronic structure methods and machine learning potentials for drug discovery: Conformers, tautomers, and protonation states

   https://doi.org/10.1063/5.0139281  

   Zeng, Jinzhe; Tao, Yujun; Giese, Timothy J.; York, Darrin M. (March 2023, The Journal of Chemical Physics)

   Modern semiempirical electronic structure methods have considerable promise in drug discovery as universal “force fields” that can reliably model biological and drug-like molecules, including alternative tautomers and protonation states. Herein, we compare the performance of several neglect of diatomic differential overlap-based semiempirical (MNDO/d, AM1, PM6, PM6-D3H4X, PM7, and ODM2), density-functional tight-binding based (DFTB3, DFTB/ChIMES, GFN1-xTB, and GFN2-xTB) models with pure machine learning potentials (ANI-1x and ANI-2x) and hybrid quantum mechanical/machine learning potentials (AIQM1 and QD π) for a wide range of data computed at a consistent ωB97X/6-31G* level of theory (as in the ANI-1x database). This data includes conformational energies, intermolecular interactions, tautomers, and protonation states. Additional comparisons are made to a set of natural and synthetic nucleic acids from the artificially expanded genetic information system that has important implications for the design of new biotechnology and therapeutics. Finally, we examine the acid/base chemistry relevant for RNA cleavage reactions catalyzed by small nucleolytic ribozymes, DNAzymes, and ribonucleases. Overall, the hybrid quantum mechanical/machine learning potentials appear to be the most robust for these datasets, and the recently developed QD π model performs exceptionally well, having especially high accuracy for tautomers and protonation states relevant to drug discovery. 

   more » « less
4. In-event surrogate model training for regional transmission tower-line system dynamic responses prediction in realistic hurricane wind fields

   https://doi.org/10.1080/15732479.2024.2345853  

   Zhu, Xiao; Ou, Ge; Pu, Zhaoxia; Li, Xin; Xue, Jiayue (April 2024, Structure and Infrastructure Engineering)

   Surrogate models have shown improved accuracy in predicting infrastructure responses during dynamic loadings. However, training a surrogate model for complex loading inputs across the entire hazard region remains challenging. This study provides insight into the training of surrogate models to estimate the responses of transmission tower-line structures in a coupled high-dimensional and high-resolution wind field and presents innovative methods for addressing these challenges. Four data- and physics-based spatial-temporal decoupling sampling methods are employed and cross-compared to obtain the most representative in-event wind profiles for training the surrogate model. Long Short-Term Memory (LSTM) is utilised as the surrogate model framework to predict the dynamic responses of the structure during the 2017 Hurricane Harvey. The accuracy and robustness of two transmission tower-line structure configuration surrogate models are validated by comparing the predictions with finite element analyses by using randomly distributed temporal and geospatial wind profiles throughout the hurricane. Finally, a single LSTM surrogate model is developed, trained by applying the full reference wind speed range of Hurricane Harvey for the regional-scale structural performance evaluation of the transmission tower-line system. The results demonstrate that the proposed surrogate model training methodology is general and can be applied to regional-scale structural performance evaluations. 

   more » « less
5. Detecting Adversarial Examples Using Data Manifolds

   Jha, Susmit; Jang, Uyeong; Jha, Somesh; Jalaian, Brian (January 2018, MILCOM IEEE Military Communications Conference)

   Models produced by machine learning, particularly deep neural networks, are state-of-the-art for many machine learning tasks and demonstrate very high prediction accuracy. Unfortunately, these models are also very brittle and vulnerable to specially crafted adversarial examples. Recent results have shown that accuracy of these models can be reduced from close to hundred percent to below 5\% using adversarial examples. This brittleness of deep neural networks makes it challenging to deploy these learning models in security-critical areas where adversarial activity is expected, and cannot be ignored. A number of methods have been recently proposed to craft more effective and generalizable attacks on neural networks along with competing efforts to improve robustness of these learning models. But the current approaches to make machine learning techniques more resilient fall short of their goal. Further, the succession of new adversarial attacks against proposed methods to increase neural network robustness raises doubts about a foolproof approach to robustify machine learning models against all possible adversarial attacks. In this paper, we consider the problem of detecting adversarial examples. This would help identify when the learning models cannot be trusted without attempting to repair the models or make them robust to adversarial attacks. This goal of finding limitations of the learning model presents a more tractable approach to protecting against adversarial attacks. Our approach is based on identifying a low dimensional manifold in which the training samples lie, and then using the distance of a new observation from this manifold to identify whether this data point is adversarial or not. Our empirical study demonstrates that adversarial examples not only lie farther away from the data manifold, but this distance from manifold of the adversarial examples increases with the attack confidence. Thus, adversarial examples that are likely to result into incorrect prediction by the machine learning model is also easier to detect by our approach. This is a first step towards formulating a novel approach based on computational geometry that can identify the limiting boundaries of a machine learning model, and detect adversarial attacks. 

   more » « less