skip to main content


Title: Predictions of transient vector solution fields with sequential deep operator network
Abstract

The deep operator network (DeepONet) structure has shown great potential in approximating complex solution operators with low generalization errors. Recently, a sequential DeepONet (S-DeepONet) was proposed to use sequential learning models in the branch of DeepONet to predict final solutions given time-dependent inputs. In the current work, the S-DeepONet architecture is extended by modifying the information combination mechanism between the branch and trunk networks to simultaneously predict vector solutions with multiple components at multiple time steps of the evolution history, which is the first in the literature using DeepONets. Two example problems, one on transient fluid flow and the other on path-dependent plastic loading, were shown to demonstrate the capabilities of the model to handle different physics problems. The use of a trained S-DeepONet model in inverse parameter identification via the genetic algorithm is shown to demonstrate the application of the model. In almost all cases, the trained model achieved an$$R^2$$R2value of above 0.99 and a relative$$L_2$$L2error of less than 10% with only 3200 training data points, indicating superior accuracy. The vector S-DeepONet model, having only 0.4% more parameters than a scalar model, can predict two output components simultaneously at an accuracy similar to the two independently trained scalar models with a 20.8% faster training time. The S-DeepONet inference is at least three orders of magnitude faster than direct numerical simulations, and inverse parameter identifications using the trained model are highly efficient and accurate.

 
more » « less
NSF-PAR ID:
10513891
Author(s) / Creator(s):
; ; ; ; ;
Publisher / Repository:
Springer Science + Business Media
Date Published:
Journal Name:
Acta Mechanica
Volume:
235
Issue:
8
ISSN:
0001-5970
Format(s):
Medium: X Size: p. 5257-5272
Size(s):
p. 5257-5272
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Consider two half-spaces$$H_1^+$$H1+and$$H_2^+$$H2+in$${\mathbb {R}}^{d+1}$$Rd+1whose bounding hyperplanes$$H_1$$H1and$$H_2$$H2are orthogonal and pass through the origin. The intersection$${\mathbb {S}}_{2,+}^d:={\mathbb {S}}^d\cap H_1^+\cap H_2^+$$S2,+d:=SdH1+H2+is a spherical convex subset of thed-dimensional unit sphere$${\mathbb {S}}^d$$Sd, which contains a great subsphere of dimension$$d-2$$d-2and is called a spherical wedge. Choosenindependent random points uniformly at random on$${\mathbb {S}}_{2,+}^d$$S2,+dand consider the expected facet number of the spherical convex hull of these points. It is shown that, up to terms of lower order, this expectation grows like a constant multiple of$$\log n$$logn. A similar behaviour is obtained for the expected facet number of a homogeneous Poisson point process on$${\mathbb {S}}_{2,+}^d$$S2,+d. The result is compared to the corresponding behaviour of classical Euclidean random polytopes and of spherical random polytopes on a half-sphere.

     
    more » « less
  2. Abstract

    The elliptic flow$$(v_2)$$(v2)of$${\textrm{D}}^{0}$$D0mesons from beauty-hadron decays (non-prompt$${\textrm{D}}^{0})$$D0)was measured in midcentral (30–50%) Pb–Pb collisions at a centre-of-mass energy per nucleon pair$$\sqrt{s_{\textrm{NN}}} = 5.02$$sNN=5.02 TeV with the ALICE detector at the LHC. The$${\textrm{D}}^{0}$$D0mesons were reconstructed at midrapidity$$(|y|<0.8)$$(|y|<0.8)from their hadronic decay$$\mathrm {D^0 \rightarrow K^-\uppi ^+}$$D0K-π+, in the transverse momentum interval$$2< p_{\textrm{T}} < 12$$2<pT<12 GeV/c. The result indicates a positive$$v_2$$v2for non-prompt$${{\textrm{D}}^{0}}$$D0mesons with a significance of 2.7$$\sigma $$σ. The non-prompt$${{\textrm{D}}^{0}}$$D0-meson$$v_2$$v2is lower than that of prompt non-strange D mesons with 3.2$$\sigma $$σsignificance in$$2< p_\textrm{T} < 8~\textrm{GeV}/c$$2<pT<8GeV/c, and compatible with the$$v_2$$v2of beauty-decay electrons. Theoretical calculations of beauty-quark transport in a hydrodynamically expanding medium describe the measurement within uncertainties.

     
    more » « less
  3. Abstract

    We study the structure of the Liouville quantum gravity (LQG) surfaces that are cut out as one explores a conformal loop-ensemble$$\hbox {CLE}_{\kappa '}$$CLEκfor$$\kappa '$$κin (4, 8) that is drawn on an independent$$\gamma $$γ-LQG surface for$$\gamma ^2=16/\kappa '$$γ2=16/κ. The results are similar in flavor to the ones from our companion paper dealing with$$\hbox {CLE}_{\kappa }$$CLEκfor$$\kappa $$κin (8/3, 4), where the loops of the CLE are disjoint and simple. In particular, we encode the combined structure of the LQG surface and the$$\hbox {CLE}_{\kappa '}$$CLEκin terms of stable growth-fragmentation trees or their variants, which also appear in the asymptotic study of peeling processes on decorated planar maps. This has consequences for questions that do a priori not involve LQG surfaces: In our paper entitled “CLE Percolations” described the law of interfaces obtained when coloring the loops of a$$\hbox {CLE}_{\kappa '}$$CLEκindependently into two colors with respective probabilitiespand$$1-p$$1-p. This description was complete up to one missing parameter$$\rho $$ρ. The results of the present paper about CLE on LQG allow us to determine its value in terms ofpand$$\kappa '$$κ. It shows in particular that$$\hbox {CLE}_{\kappa '}$$CLEκand$$\hbox {CLE}_{16/\kappa '}$$CLE16/κare related via a continuum analog of the Edwards-Sokal coupling between$$\hbox {FK}_q$$FKqpercolation and theq-state Potts model (which makes sense even for non-integerqbetween 1 and 4) if and only if$$q=4\cos ^2(4\pi / \kappa ')$$q=4cos2(4π/κ). This provides further evidence for the long-standing belief that$$\hbox {CLE}_{\kappa '}$$CLEκand$$\hbox {CLE}_{16/\kappa '}$$CLE16/κrepresent the scaling limits of$$\hbox {FK}_q$$FKqpercolation and theq-Potts model whenqand$$\kappa '$$κare related in this way. Another consequence of the formula for$$\rho (p,\kappa ')$$ρ(p,κ)is the value of half-plane arm exponents for such divide-and-color models (a.k.a. fuzzy Potts models) that turn out to take a somewhat different form than the usual critical exponents for two-dimensional models.

     
    more » « less
  4. Abstract

    We propose a new observable for the measurement of the forward–backward asymmetry$$(A_{FB})$$(AFB)in Drell–Yan lepton production. At hadron colliders, the$$A_{FB}$$AFBdistribution is sensitive to both the electroweak (EW) fundamental parameter$$\sin ^{2} \theta _{W}$$sin2θW, the weak mixing angle, and the parton distribution functions (PDFs). Hence, the determination of$$\sin ^{2} \theta _{W}$$sin2θWand the updating of PDFs by directly using the same$$A_{FB}$$AFBspectrum are strongly correlated. This correlation would introduce large bias or uncertainty into both precise measurements of EW and PDF sectors. In this article, we show that the sensitivity of$$A_{FB}$$AFBon$$\sin ^{2} \theta _{W}$$sin2θWis dominated by its average value around theZpole region, while the shape (or gradient) of the$$A_{FB}$$AFBspectrum is insensitive to$$\sin ^{2} \theta _{W}$$sin2θWand contains important information on the PDF modeling. Accordingly, a new observable related to the gradient of the spectrum is introduced, and demonstrated to be able to significantly reduce the potential bias on the determination of$$\sin ^{2} \theta _{W}$$sin2θWwhen updating the PDFs using the same$$A_{FB}$$AFBdata.

     
    more » « less
  5. Abstract

    We report on a measurement of Spin Density Matrix Elements (SDMEs) in hard exclusive$$\rho ^0$$ρ0meson muoproduction at COMPASS using 160 GeV/cpolarised$$ \mu ^{+}$$μ+and$$ \mu ^{-}$$μ-beams impinging on a liquid hydrogen target. The measurement covers the kinematic range 5.0 GeV/$$c^2$$c2$$< W<$$<W<17.0 GeV/$$c^2$$c2, 1.0 (GeV/c)$$^2$$2$$< Q^2<$$<Q2<10.0 (GeV/c)$$^2$$2and 0.01 (GeV/c)$$^2$$2$$< p_{\textrm{T}}^2<$$<pT2<0.5 (GeV/c)$$^2$$2. Here,Wdenotes the mass of the final hadronic system,$$Q^2$$Q2the virtuality of the exchanged photon, and$$p_{\textrm{T}}$$pTthe transverse momentum of the$$\rho ^0$$ρ0meson with respect to the virtual-photon direction. The measured non-zero SDMEs for the transitions of transversely polarised virtual photons to longitudinally polarised vector mesons ($$\gamma ^*_T \rightarrow V^{ }_L$$γTVL) indicate a violation ofs-channel helicity conservation. Additionally, we observe a dominant contribution of natural-parity-exchange transitions and a very small contribution of unnatural-parity-exchange transitions, which is compatible with zero within experimental uncertainties. The results provide important input for modelling Generalised Parton Distributions (GPDs). In particular, they may allow one to evaluate in a model-dependent way the role of parton helicity-flip GPDs in exclusive$$\rho ^0$$ρ0production.

     
    more » « less