arXiv subjects

Juntao Yang

Publications and source records attributed to Juntao Yang.

11 recordsLinked to original sources

arXiv2026

DA-NBV: A Direction-Aware Next-Best-View Planner for Efficient 3D Reconstruction of Ships at Sea

Accurate 3D reconstruction of ships at sea is important for maritime supervision, damage assessment, and autonomous maritime operations. Although 3D reconstruction has advanced considerably, high-quality data acquisition still largely relies on manually designed trajectories or skilled operators, resulting in high costs and limited scalability. Next-best-view (NBV) planning automates this process by selecting subsequent viewpoints based on the current state. However, existing NBV policies mainly model spatial occupancy while overlooking directional observation history. This limitation is particularly problematic for ships: their complex superstructures and severe self-occlusions require observations from multiple viewpoints, and insufficient directional coverage often yields incomplete reconstructions. These challenges are further amplified at sea, where wave-induced heave, roll, and pitch continuously alter the ship's pose and surface visibility. Meanwhile, wind disturbances and limited onboard power impose stricter requirements on scanning efficiency. To address these challenges, we propose DA-NBV, a direction-aware NBV policy that augments the conventional occupancy state with directional observation statistics. We introduce a learnable Position Advantage Field (PAF) that uses directional information to guide viewpoint selection. The policy further adopts a locally constrained action space and a nonlinear coverage-shaping reward to improve scanning efficiency. We also develop the ship-oriented SeaShip-3D dataset and a configurable sea-state simulation environment. Experiments under varying heave, roll, and pitch conditions show that DA-NBV improves reconstruction completeness by approximately 3 percentage points and reduces Chamfer distance by 43% while achieving higher path efficiency.

cs.RO↗

arXiv2026

Sequential Physics-Constrained Neural Operator Forward Modeling for the $\textit{Norne}$ Reservoir System

We develop a comprehensive mathematical and computational framework for sequential surrogate modeling of three-phase black-oil reservoir dynamics using neural operators, with particular emphasis on Fourier Neural Operators (FNO) and their physics-informed variant (PINO). The application focus is the Norne benchmark reservoir, defined on a heterogeneous $46\times112\times22$ grid ($N=113,344$ cells), with a production history spanning $T=30$ timesteps covering 3298 days. Our theoretical contributions are organized around four interlocking problems: (1) functional-analytic formulation in a product-Sobolev-space setting, including well-posedness of the implicit timestep map and sharp local Lipschitz estimates; (2) covariate shift quantification, proving that the Wasserstein-2 distance grows as $W_2 \leq \varepsilon(L^n-1)/(L-1)$, with exponential population-risk discrepancy for $L>1$; (3) physics-constrained spectral stability, showing PINO training with $\lambda_R \geq \lambda^*_R$ reduces the learned Jacobian spectral radius to $\rho_F + C\lambda_R^{-1/2}$, yielding uniform-in-time rollout error $|\delta_n| \leq \varepsilon/(1-\rho)$; and (4) $K$-step TBPTT gradient analysis, deriving geometric bias decay $O(\rho^K)$, optimal window $K^ = O(\log(T/\sigma^2))$, and Adam convergence $O(1/\sqrt{t}) + O(\rho^{K^*})$. Empirical validation confirms all theoretical predictions: autoregressive PINO surrogates sustain $R^2>0.99$ (oil), $R^2>0.90$ (gas), $R^2\approx 0.80$ (pressure), and monotonically improving $R^2$ (water) across the full 3298-day horizon, trained on eight NVIDIA B200 GPUs in under one hour. A 1000-member ensemble runs in under one minute on a single B200 GPU, giving a ${\sim}10^4\times$ wall-clock speedup over the OPM finite-volume simulator.

cs.LG↗

arXiv2026

NeuralFVM: Neural-physics-based Finite Volume Method for Turbulent Flows Using the $k$-$\omega$ Model

In this work, we develop a neural-physics solver based on finite volume method (FVM), namely NeuralFVM, for turbulent flows by implementing the standard $k$-$\omega$ model designed for efficient Graphics Processing Unit (GPU) execution. The governing equations for fluid flow and heat transfer are reformulated as local tensor operations using convolution-based stencil operators, which enables compatibility with deep learning libraries while preserving the conservative properties of the FVM. A key challenge in implementing the turbulent model within such a framework is the treatment of the stiff destruction terms in the $k$ and $\omega$ transport equations. To address this issue, an operator-splitting strategy is introduced in which the stiff destruction terms are handled semi-implicitly while the remaining terms are advanced explicitly. This formulation avoids global matrix assembly and allows the entire solver to be implemented using local tensor operations. In addition, the pressure-velocity coupling is solved using a convolution-based geometric multigrid algorithm embedded within a neural network architecture. The resulting NeuralFVM solver is validated through comparison with simulations conducted using the commercial CFD software ANSYS Fluent for several channel-flow configurations and an indoor airflow scenario. The results demonstrate close agreement in velocity, temperature, and turbulence quantities, confirming the accuracy of the proposed approach. The developed GPU framework achieves a speedup of around 19-46 times compared with its Central Processing Unit (CPU) counterpart under different meshes. Moreover, the proposed solver naturally integrates with machine learning workflows, providing a promising foundation for future data-driven turbulence modeling and optimization.

physics.flu-dyn↗

arXiv2025

XAI4Extremes: An interpretable machine learning framework for understanding extreme-weather precursors under climate change

Extreme weather events are increasing in frequency and intensity due to climate change. This, in turn, is exacting a significant toll in communities worldwide. While prediction skills are increasing with advances in numerical weather prediction and artificial intelligence tools, extreme weather still present challenges. More specifically, identifying the precursors of such extreme weather events and how these precursors may evolve under climate change remain unclear. In this paper, we propose to use post-hoc interpretability methods to construct relevance weather maps that show the key extreme-weather precursors identified by deep learning models. We then compare this machine view with existing domain knowledge to understand whether deep learning models identified patterns in data that may enrich our understanding of extreme-weather precursors. We finally bin these relevant maps into different multi-year time periods to understand the role that climate change is having on these precursors. The experiments are carried out on Indochina heatwaves, but the methodology can be readily extended to other extreme weather events worldwide.

cs.LG↗

arXiv2025

CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraints

Accurate and efficient climate simulations are crucial for understanding Earth's evolving climate. However, current general circulation models (GCMs) face challenges in capturing unresolved physical processes, such as cloud and convection. A common solution is to adopt cloud resolving models, that provide more accurate results than the standard subgrid parametrisation schemes typically used in GCMs. However, cloud resolving models, also referred to as super paramtetrizations, remain computationally prohibitive. Hybrid modeling, which integrates deep learning with equation-based GCMs, offers a promising alternative but often struggles with long-term stability and accuracy issues. In this work, we find that water vapor oversaturation during condensation is a key factor compromising the stability of hybrid models. To address this, we introduce CondensNet, a novel neural network architecture that embeds a self-adaptive physical constraint to correct unphysical condensation processes. CondensNet effectively mitigates water vapor oversaturation, enhancing simulation stability while maintaining accuracy and improving computational efficiency compared to super parameterization schemes. We integrate CondensNet into a GCM to form PCNN-GCM (Physics-Constrained Neural Network GCM), a hybrid deep learning framework designed for long-term stable climate simulations in real-world conditions, including ocean and land. PCNN-GCM represents a significant milestone in hybrid climate modeling, as it shows a novel way to incorporate physical constraints adaptively, paving the way for accurate, lightweight, and stable long-term climate simulations.

physics.ao-ph↗

arXiv2024

PneumoLLM: Harnessing the Power of Large Language Model for Pneumoconiosis Diagnosis

The conventional pretraining-and-finetuning paradigm, while effective for common diseases with ample data, faces challenges in diagnosing data-scarce occupational diseases like pneumoconiosis. Recently, large language models (LLMs) have exhibits unprecedented ability when conducting multiple tasks in dialogue, bringing opportunities to diagnosis. A common strategy might involve using adapter layers for vision-language alignment and diagnosis in a dialogic manner. Yet, this approach often requires optimization of extensive learnable parameters in the text branch and the dialogue head, potentially diminishing the LLMs' efficacy, especially with limited training data. In our work, we innovate by eliminating the text branch and substituting the dialogue head with a classification head. This approach presents a more effective method for harnessing LLMs in diagnosis with fewer learnable parameters. Furthermore, to balance the retention of detailed image information with progression towards accurate diagnosis, we introduce the contextual multi-token engine. This engine is specialized in adaptively generating diagnostic tokens. Additionally, we propose the information emitter module, which unidirectionally emits information from image tokens to diagnosis tokens. Comprehensive experiments validate the superiority of our methods and the effectiveness of proposed modules. Our codes can be found at https://github.com/CodeMonsterPHD/PneumoLLM/tree/main.

eess.IV↗

arXiv2024

Multilevel Markov Chain Monte Carlo for Bayesian inverse problems for Navier Stokes equation with Lagrangian Observations

In this paper, we extend our work to the Bayesian inverse problems for inferring unknown forcing and initial condition of the forward Navier-Stokes equation coupled with tracer equation with noisy Lagrangian observation on the positions of the tracers. We consider the Navier-Stokes equations in the two dimensional periodic torus with a tracer equation which is a simple ordinary differential equation. We developed rigorously the theory for the case of the uniform prior where the forcing and the initial condition depend linearly on a countable set of random variables which are uniformly distributed in a compact interval. Numerical experiment using the MLMCMC method produces approximations for posterior expectation of quantities of interest which are in agreement with the theoretical optimal convergence rate established.

math.NA↗

arXiv2023

A Hybrid Two-level MCMC Framework to Accelerate Posterior Mean Estimation with Deep Learning Surrogates for Bayesian Inverse Problems

Bayesian inverse problems arise in various scientific and engineering domains, and solving them can be computationally demanding. This is especially the case for problems governed by partial differential equations, where the repeated evaluation of the forward operator is extremely expensive. Recent advances in Deep Learning (DL)-based surrogate models have shown promising potential to accelerate the solution of such problems. However, despite their ability to learn from complex data, DL-based surrogate models generally cannot match the accuracy of high-fidelity numerical models, which limits their practical applicability. We propose a novel hybrid two-level Markov Chain Monte Carlo (MCMC) method that combines the strengths of DL-based surrogate models and high-fidelity numerical solvers to {compute the posterior mean of Quantities of Interest (QoI) in} Bayesian inverse problems governed by partial differential equations. The intuition is to leverage the evaluation speed of a DL-based surrogate model as the base chain, and correct its errors using a limited number of high-fidelity numerical model evaluations in a correction chain; hence its name hybrid two-level MCMC method. Through a detailed theoretical analysis, we show that our approach can achieve the same accuracy as a pure numerical MCMC method while requiring only a small fraction of the computational cost. The theoretical analysis is further supported by several numerical experiments, namely a Poisson, a non-linear reaction-diffusion, and a Navier-Stokes equation. The proposed hybrid framework can be generalized to other approaches such as the ensemble Kalman filter and sequential Monte Carlo methods.

math.NA↗

arXiv2022

Determination of building flood risk maps from LiDAR mobile mapping data

With increasing urbanization, flooding is a major challenge for many cities today. Based on forecast precipitation, topography, and pipe networks, flood simulations can provide early warnings for areas and buildings at risk of flooding. Basement windows, doors, and underground garage entrances are common places where floodwater can flow into a building. Some buildings have been prepared or designed considering the threat of flooding, but others have not. Therefore, knowing the heights of these facade openings helps to identify places that are more susceptible to water ingress. However, such data is not yet readily available in most cities. Traditional surveying of the desired targets may be used, but this is a very time-consuming and laborious process. This research presents a new process for the extraction of windows and doors from LiDAR mobile mapping data. Deep learning object detection models are trained to identify these objects. Usually, this requires to provide large amounts of manual annotations. In this paper, we mitigate this problem by leveraging a rule-based method. In a first step, the rule-based method is used to generate pseudo-labels. A semi-supervised learning strategy is then applied with three different levels of supervision. The results show that using only automatically generated pseudo-labels, the learning-based model outperforms the rule-based approach by 14.6% in terms of F1-score. After five hours of human supervision, it is possible to improve the model by another 6.2%. By comparing the detected facade openings' heights with the predicted water levels from a flood simulation model, a map can be produced which assigns per-building flood risk levels. This information can be combined with flood forecasting to provide a more targeted disaster prevention guide for the city's infrastructure and residential buildings.

cs.CV↗

arXiv2021

Dirac fermions in half-metallic ferromagnetic mixed Cr$_{1\textrm{-}x}$M$_x$PSe$_3$ monolayers

The electronic and magnetic properties of pristine CrPSe$_3$ and mixed Cr$_{1\textrm{-}x}$M$_x$PSe$_3$ (M = Zn, Cd, Hg) monolayers were studied using density functional theory including an on-site Coulomb term (DFT$+U$) and tight-binding approach (TBA). While pristine CrPSe$_3$ monolayer has an antiferromagnetic (AFM) ground state, its alloying with MPSe$_3$ may give rise to half-metallic ferromagnet (HMF) with high Curie temperature. The resulting monolayers demonstrate single-spin Dirac cones of mainly Cr-$d$ character located in the first Brillouin zone directly at the Fermi energy. The calculated Fermi velocities of Dirac fermions indicate very high mobility in mixed Cr$_{1\textrm{-}x}$M$_x$PSe$_3$ monolayers, that makes this material appealing for low-dimensional spintronics applications.

cond-mat.mtrl-sci↗

arXiv2021

Electronic, magnetic and optical properties of MnPX$_3$ (X = S, Se) monolayers with and without chalcogen defects: A first-principle study

Based on density functional theory (DFT), we performed first-principle studies on the electronic structure, magnetic state and optical properties of two-dimensional (2D) transition-metal phosphorous trichalcogenide MnPX$_3$ (X=S and Se). The calculated interlayer cleavage energies of MnPX$_3$ monolayers indicate the energetic possibility to be exfoliated from bulk phase, with good dynamical stability confirmed by the absence of the imaginary contributions in the phonon spectra. MnPX$_3$ monolayers are both Néel antiferromagnetic (AFM) semiconductors with direct band gaps falling into the visible optical spectrum. Magnetic interaction parameters were extracted within the Heisenberg model to investigate the origin of the AFM state. Three in-plane magnetic exchange parameters play important role in the robust AFM configuration of Mn ions. The Néel temperatures ($T_\mathrm{N}$) were estimated by means of Monte Carlo simulations, obtaining the theoretical $T_\mathrm{N}$ of $103$\,K and $80$\,K for 2D MnPS$_3$ and MnPSe$_3$, respectively. With high spin state, Mn ions arranged in honeycomb lattices, the spin-degenerated band structures exhibit valley polarisation and was investigated in different biaxial in-plain strains, considering the spin-orbital coupling (SOC). 2D MnPX$_3$ monolayers show excellent performance on the optical properties, and the absorption spectra were discussed in detail to find the transition mechanism. Different amount and configuration of chalcogen vacancy were introduced into the MnPX$_3$ monolayers, and it is found that the electronic structures are heavily affected depending on the vacancy geometric structure, leading to different magnetic state and absorption spectra of defected MnPX$_3$ systems.

cond-mat.mtrl-sci↗