Searcharxiv⌕ Search

arXiv subjects

Jianguo Hou

Publications and source records attributed to Jianguo Hou.

4 recordsLinked to original sources

Score-based neural ordinary differential equations for reaction-diffusions

A diffusion equation can be rewritten as a transport equation driven by the score function of the evolving density. Conventional probability-flow formulations, which move particles deterministically with this score-driven velocity, typically conserve total mass. In this work, we develop a Lagrangian method for reaction-diffusion equations in which each particle carries a position and a physical weight. The characteristic ODEs incorporate source terms into the evolution of the log-density and its gradient, while particle weights track changes in mass. We combine this representation with a learned velocity field and weighted particle training to approximate these dynamics. For non-increasing reaction rates, a relative-entropy inequality supports the mass-normalized self-consistency residual as the training objective. This objective can control the error of the induced density when the growth rate is bounded. The algorithm divides the time interval into short windows. In each window, a frozen velocity generates the particle data for a regression of the network velocity. We draw the particles from period-adapted initial sampling distributions and weight them in the loss partly by their predicted future mass, because the reaction can make regions with little initial mass important later. We numerically investigate the method on the Ornstein-Uhlenbeck (OU) equation with a linear source term, Fisher-KPP equations, and Wasserstein-Fisher-Rao gradient flows.

math.NA↗

A Deep Learning Approach to Predicting Ventilator Parameters for Mechanically Ventilated Septic Patients

We develop a deep learning approach to predicting a set of ventilator parameters for a mechanically ventilated septic patient using a long and short term memory (LSTM) recurrent neural network (RNN) model. We focus on short-term predictions of a set of ventilator parameters for the septic patient in emergency intensive care unit (EICU). The short-term predictability of the model provides attending physicians with early warnings to make timely adjustment to the treatment of the patient in the EICU. The patient specific deep learning model can be trained on any given critically ill patient, making it an intelligent aide for physicians to use in emergent medical situations.

q-bio.QM↗

A First-principles Prediction of Two-Dimensional Superconductivity in Pristine B2C Single layer

Based on first-principles lattice dynamics and electron-phonon coupling calculations, B2C sheet is predicted to be a two-dimensional (2D) phonon-mediated superconductor with a relatively high transition temperature (Tc). The electron-phonon coupling parameter calculated is 0.92, and it is mainly contributed by low frequency out-of-plane phonon modes and electronic states with a π character. When the Coulomb pseudopotential is set to 0.10, the estimated temperature Tc is 19.2 K. To be best of our knowledge, B2C is the first pristine 2D superconductor with a Tc higher than the boiling point of liquid helium.

cond-mat.mtrl-sci↗

CO2 dissociation activated through electron attachment on reduced rutile TiO2(110)-1x1 surface

Converting CO$_2$ to useful compounds through the solar photocatalytic reduction has been one of the most promising strategies for artificial carbon recycling. The highly relevant photocatalytic substrate for CO$_2$ conversion has been the popular TiO$_2$ surfaces. However, the lack of accurate fundamental parameters that determine the CO$_2$ reduction on TiO$_2$ has limited our ability to control these complicated photocatalysis processes. We have systematically studied the reduction of CO2 at specific sites of the rutile TiO$_2$(110)-1x1 surface using scanning tunneling microscopy at 80 K. The dissociation of CO2 molecules is found to be activated by one electron attachment process and its energy threshold, corresponding to the CO$_2^{\dot-}$/CO$_2$ redox potential, is unambiguously determined to be 2.3 eV higher than the onset of the TiO$_2$ conduction band. The dissociation rate as a function of electron injection energy is also provided. Such information can be used as practical guidelines for the design of effective catalysts for CO$_2$ photoreduction.

physics.chem-ph↗