arXiv subjects

Jian Cheng Wong

Publications and source records attributed to Jian Cheng Wong.

25 records · Page 2Linked to original sources

arXiv2022

Robustness of Physics-Informed Neural Networks to Noise in Sensor Data

Physics-Informed Neural Networks (PINNs) have been shown to be an effective way of incorporating physics-based domain knowledge into neural network models for many important real-world systems. They have been particularly effective as a means of inferring system information based on data, even in cases where data is scarce. Most of the current work however assumes the availability of high-quality data. In this work, we further conduct a preliminary investigation of the robustness of physics-informed neural networks to the magnitude of noise in the data. Interestingly, our experiments reveal that the inclusion of physics in the neural network is sufficient to negate the impact of noise in data originating from hypothetical low quality sensors with high signal-to-noise ratios of up to 1. The resultant predictions for this test case are seen to still match the predictive value obtained for equivalent data obtained from high-quality sensors with potentially 10x less noise. This further implies the utility of physics-informed neural network modeling for making sense of data from sensor networks in the future, especially with the advent of Industry 4.0 and the increasing trend towards ubiquitous deployment of low-cost sensors which are typically noisier.

cs.LG↗

arXiv2022

CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method

In this study, novel physics-informed neural network (PINN) methods for coupling neighboring support points and their derivative terms which are obtained by automatic differentiation (AD), are proposed to allow efficient training with improved accuracy. The computation of differential operators required for PINNs loss evaluation at collocation points are conventionally obtained via AD. Although AD has the advantage of being able to compute the exact gradients at any point, such PINNs can only achieve high accuracies with large numbers of collocation points, otherwise they are prone to optimizing towards unphysical solution. To make PINN training fast, the dual ideas of using numerical differentiation (ND)-inspired method and coupling it with AD are employed to define the loss function. The ND-based formulation for training loss can strongly link neighboring collocation points to enable efficient training in sparse sample regimes, but its accuracy is restricted by the interpolation scheme. The proposed coupled-automatic-numerical differentiation framework, labeled as can-PINN, unifies the advantages of AD and ND, providing more robust and efficient training than AD-based PINNs, while further improving accuracy by up to 1-2 orders of magnitude relative to ND-based PINNs. For a proof-of-concept demonstration of this can-scheme to fluid dynamic problems, two numerical-inspired instantiations of can-PINN schemes for the convection and pressure gradient terms were derived to solve the incompressible Navier-Stokes (N-S) equations. The superior performance of can-PINNs is demonstrated on several challenging problems, including the flow mixing phenomena, lid driven flow in a cavity, and channel flow over a backward facing step. The results reveal that for challenging problems like these, can-PINNs can consistently achieve very good accuracy whereas conventional AD-based PINNs fail.

cs.LG↗

arXiv2022

Learning in Sinusoidal Spaces with Physics-Informed Neural Networks

A physics-informed neural network (PINN) uses physics-augmented loss functions, e.g., incorporating the residual term from governing partial differential equations (PDEs), to ensure its output is consistent with fundamental physics laws. However, it turns out to be difficult to train an accurate PINN model for many problems in practice. In this paper, we present a novel perspective of the merits of learning in sinusoidal spaces with PINNs. By analyzing behavior at model initialization, we first show that a PINN of increasing expressiveness induces an initial bias around flat output functions. Notably, this initial solution can be very close to satisfying many physics PDEs, i.e., falling into a local minimum of the PINN loss that only minimizes PDE residuals, while still being far from the true solution that jointly minimizes PDE residuals and the initial and/or boundary conditions. It is difficult for gradient descent optimization to escape from such a local minimum trap, often causing the training to stall. We then prove that the sinusoidal mapping of inputs, in an architecture we label as sf-PINN, is effective to increase input gradient variability, thus avoiding being trapped in such deceptive local minimum. The level of variability can be effectively modulated to match high-frequency patterns in the problem at hand. A key facet of this paper is the comprehensive empirical study that demonstrates the efficacy of learning in sinusoidal spaces with PINNs for a wide range of forward and inverse modelling problems spanning multiple physics domains.

cs.LG↗

arXiv2021

Improved Surrogate Modeling of Fluid Dynamics with Physics-Informed Neural Networks

Physics-Informed Neural Networks (PINNs) have recently shown great promise as a way of incorporating physics-based domain knowledge, including fundamental governing equations, into neural network models for many complex engineering systems. They have been particularly effective in the area of inverse problems, where boundary conditions may be ill-defined, and data-absent scenarios, where typical supervised learning approaches will fail. Here, we further explore the use of this modeling methodology to surrogate modeling of a fluid dynamical system, and demonstrate additional undiscussed and interesting advantages of such a modeling methodology over conventional data-driven approaches: 1) improving the model's predictive performance even with incomplete description of the underlying physics; 2) improving the robustness of the model to noise in the dataset; 3) reduced effort to convergence during optimization for a new, previously unseen scenario by transfer optimization of a pre-existing model. Hence, we noticed the inclusion of a physics-based regularization term can substantially improve the equivalent data-driven surrogate model in many substantive ways, including an order of magnitude improvement in test error when the dataset is very noisy, and a 2-3x improvement when only partial physics is included. In addition, we propose a novel transfer optimization scheme for use in such surrogate modeling scenarios and demonstrate an approximately 3x improvement in speed to convergence and an order of magnitude improvement in predictive performance over conventional Xavier initialization for training of new scenarios.

cs.LG↗

arXiv2021

Can Transfer Neuroevolution Tractably Solve Your Differential Equations?

This paper introduces neuroevolution for solving differential equations. The solution is obtained through optimizing a deep neural network whose loss function is defined by the residual terms from the differential equations. Recent studies have focused on learning such physics-informed neural networks through stochastic gradient descent (SGD) variants, yet they face the difficulty of obtaining an accurate solution due to optimization challenges. In the context of solving differential equations, we are faced with the problem of finding globally optimum parameters of the network, instead of being concerned with out-of-sample generalization. SGD, which searches along a single gradient direction, is prone to become trapped in local optima, so it may not be the best approach here. In contrast, neuroevolution carries out a parallel exploration of diverse solutions with the goal of circumventing local optima. It could potentially find more accurate solutions with better optimized neural networks. However, neuroevolution can be slow, raising tractability issues in practice. With that in mind, a novel and computationally efficient transfer neuroevolution algorithm is proposed in this paper. Our method is capable of exploiting relevant experiential priors when solving a new problem, with adaptation to protect against the risk of negative transfer. The algorithm is applied on a variety of differential equations to empirically demonstrate that transfer neuroevolution can indeed achieve better accuracy and faster convergence than SGD. The experimental outcomes thus establish transfer neuroevolution as a noteworthy approach for solving differential equations, one that has never been studied in the past. Our work expands the resource of available algorithms for optimizing physics-informed neural networks.

cs.NE↗

arXiv2011

Causal Links Between US Economic Sectors

In this paper, we perform a comparative segmentation and clustering analysis of the time series for the ten Dow Jones US economic sector indices between 14 February 2000 and 31 August 2008. From the temporal distributions of clustered segments, we find that the US economy took one and a half years to recover from the mid-1998-to-mid-2003 financial crisis, but only two months to completely enter the present financial crisis. We also find the oil & gas and basic materials sectors leading the recovery from the previous financial crisis, while the consumer goods and utilities sectors led the descent into the present financial crisis. On a macroscopic level, we find sectors going earlier into a crisis emerge later from it, whereas sectors going later into the crisis emerge earlier. On the mesoscopic level, we find leading sectors experiencing stronger and longer volatility shocks, while trailing sectors experience weaker and shorter volatility shocks. In our shock-by-shock causal-link analysis, we also find shorter delays between corresponding shocks in more closely related economic sectors. In addition, our analysis reveals evidences for complex sectorial structures, as well as nonlinear amplification in the propagating volatility shocks. From a perspective relevant to public policy, our study suggests an endogeneous sectorial dynamics during the mid-2003 economic recovery, in contrast to strong exogeneous driving by Federal Reserve interest rate cuts during the mid-2007 onset. Most interestingly, we find for the sequence of closely spaced interest rate cuts instituted in 2007/2008, the first few cuts effectively lowered market volatilities, while the next few cuts counter-effectively increased market volatilities. Subsequent cuts evoked little response from the market.

q-fin.GN↗

arXiv2010

Will the US Economy Recover in 2010? A Minimal Spanning Tree Study

We calculated the cross correlations between the half-hourly times series of the ten Dow Jones US economic sectors over the period February 2000 to August 2008, the two-year intervals 2002--2003, 2004--2005, 2008--2009, and also over 11 segments within the present financial crisis, to construct minimal spanning trees (MSTs) of the US economy at the sector level. In all MSTs, a core-fringe structure is found, with consumer goods, consumer services, and the industrials consistently making up the core, and basic materials, oil and gas, healthcare, telecommunications, and utilities residing predominantly on the fringe. More importantly, we find that the MSTs can be classified into two distinct, statistically robust, topologies: (i) star-like, with the industrials at the center, associated with low-volatility economic growth; and (ii) chain-like, associated with high-volatility economic crisis. Finally, we present statistical evidence, based on the emergence of a star-like MST in Sep 2009, and the MST staying robustly star-like throughout the Greek Debt Crisis, that the US economy is on track to a recovery.

q-fin.ST↗