An official website of the United States government
Abstract Attempts to use machine learning to discover hidden physical rules are in their infancy, and such attempts confront more challenges when experiments involve multifaceted measurements over three-dimensional objects. Here we propose a framework that can infuse scientists’ basic knowledge into a glass-box rule learner to extract hidden physical rules behind complex physics phenomena. A “convolved information index” is proposed to handle physical measurements over three-dimensional nano-scale specimens, and the multi-layered convolutions are “externalized” over multiple depths at the information level, not in the opaque networks. A transparent, flexible link function is proposed as a mathematical expression generator, thereby pursuing “glass-box” prediction. Consistent evolution is realized by integrating a Bayesian update and evolutionary algorithms. The framework is applied to nano-scale contact electrification phenomena, and results show promising performances in unraveling transparent expressions of a hidden physical rule. The proposed approach will catalyze a synergistic machine learning-physics partnership.
more »
« less
Unraveling hidden rules behind the wet-to-dry transition of bubble array by glass-box physics rule learner
Abstract A liquid–gas foam, here called bubble array, is a ubiquitous phenomenon widely observed in daily lives, food, pharmaceutical and cosmetic products, and even bio- and nano-technologies. This intriguing phenomenon has been often studied in a well-controlled environment in laboratories, computations, or analytical models. Still, real-world bubble undergoes complex nonlinear transitions from wet to dry conditions, which are hard to describe by unified rules as a whole. Here, we show that a few early-phase snapshots of bubble array can be learned by a glass-box physics rule learner (GPRL) leading to prediction rules of future bubble array. Unlike the black-box machine learning approach, the glass-box approach seeks to unravel expressive rules of the phenomenon that can evolve. Without known principles, GPRL identifies plausible rules of bubble prediction with an elongated bubble array data that transitions from wet to dry states. Then, the best-so-far GPRL-identified rule is applied to an independent circular bubble array, demonstrating the potential generality of the rule. We explain how GPRL uses the spatio-temporal convolved information of early bubbles to mimic the scientist’s perception of bubble sides, shapes, and inter-bubble influences. This research will help combine foam physics and machine learning to better understand and control bubbles.
more »
« less
- PAR ID:
- 10363316
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- Scientific Reports
- Volume:
- 12
- Issue:
- 1
- ISSN:
- 2045-2322
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Boiling is arguably Nature’s most effective thermal management mechanism that cools submersed matter through bubble-induced advective transport. Central to the boiling process is the development of bubbles. Connecting boiling physics with bubble dynamics is an important, yet daunting challenge because of the intrinsically complex and high dimensional of bubble dynamics. Here, we introduce a data-driven learning framework that correlates high-quality imaging on dynamic bubbles with associated boiling curves. The framework leverages cutting-edge deep learning models including convolutional neural networks and object detection algorithms to automatically extract both hierarchical and physics-based features. By training on these features, our model learns physical boiling laws that statistically describe the manner in which bubbles nucleate, coalesce, and depart under boiling conditions, enabling in situ boiling curve prediction with a mean error of 6%. Our framework offers an automated, learning-based, alternative to conventional boiling heat transfer metrology.more » « less
-
Abstract Predicting individual large earthquakes (EQs)’ locations, magnitudes, and timing remains unreachable. The author’s prior study shows that individual large EQs have unique signatures obtained from multi-layered data transformations. Via spatio-temporal convolutions, decades-long EQ catalog data are transformed into pseudo-physics quantities (e.g., energy, power, vorticity, and Laplacian), which turn into surface-like information via Gauss curvatures. Using these new features, a rule-learning machine learning approach unravels promising prediction rules. This paper suggests further data transformation via Fourier transformation (FT). Results show that FT-based new feature can help sharpen the prediction rules. Feasibility tests of large EQs ($$M\ge$$ 6.5) over the past 40 years in the western U.S. show promise, shedding light on data-driven prediction of individual large EQs. The handshake among ML methods, Fourier, and Gauss may help answer the long-standing enigma of seismogenesis.more » « less
-
ABSTRACT An important characteristic of cosmic hydrogen reionization is the growth of ionized gas bubbles surrounding early luminous objects. Ionized bubble sizes are beginning to be probed using Lyman α emission from high-redshift galaxies, and will also be probed by upcoming 21 cm maps. We present results from a study of bubble sizes using the state-of-the-art thesan radiation-hydrodynamics simulation suite, which self-consistently models radiation transport and realistic galaxy formation. We employ the mean free path method and track the evolution of the effective ionized bubble size at each point (Reff) throughout the Epoch of Reionization. We show that there is a slow growth period for regions ionized early, but a rapid ‘flash ionization’ process for regions ionized later as they immediately enter a large, pre-existing bubble. We also find that bright sources are preferentially in larger bubbles, and find consistency with recent observational constraints at z ≳ 9, but tension with idealized Lyman α damping-wing models at z ≈ 7. We find that high-overdensity regions have larger characteristic bubble sizes, but the correlation decreases as reionization progresses, likely due to runaway formation of large percolated bubbles. Finally, we compare the redshift at which a region transitions from neutral to ionized (zreion) with the time it takes to reach a given bubble size and conclude that zreion is a reasonable local probe of small-scale bubble size statistics ($$R_\text{eff} \lesssim 1\, \rm {cMpc}$$). However, for larger bubbles, the correspondence between zreion and size statistics weakens due to the time delay between the onset of reionization and the expansion of large bubbles, particularly at high redshifts.more » « less
-
null (Ed.)Bayesian hybrid models fuse physics-based insights with machine learning constructs to correct for systematic bias. In this paper, we compare Bayesian hybrid models against physics-based glass-box and Gaussian process black-box surrogate models. We consider ballistic firing as an illustrative case study for a Bayesian decision-making workflow. First, Bayesian calibration is performed to estimate model parameters. We then use the posterior distribution from Bayesian analysis to compute optimal firing conditions to hit a target via a single-stage stochastic program. The case study demonstrates the ability of Bayesian hybrid models to overcome systematic bias from missing physics with fewer data than the pure machine learning approach. Ultimately, we argue Bayesian hybrid models are an emerging paradigm for data-informed decision-making under parametric and epistemic uncertainty.more » « less
