arXiv subjects

Yinling Zhang

Publications and source records attributed to Yinling Zhang.

11 recordsLinked to original sources

arXiv2026

Causation-guided mechanism identification and interpretable reduced-order modeling of damage-driving grain-boundary stress in creep

GB local stress is central to the initiation and evolution of long-term creep damage in polycrystalline superalloys. Owing to the high-dimensional nonlinear relationships between the GB stress response and multiple crystallographic, microstructural, and micromechanical characteristics, it remains challenging to identify the key characteristics governing GB stress and to elucidate their mechanisms of influence. Dislocation-climb-affected crystal-plasticity finite-element simulations of minimal grain clusters are combined with an integrated causation-guided machine-learning framework, in which mechanics-informed descriptors are analyzed by causation entropy (CE) to identify governing mechanisms and then distilled into a reduced-order regression form for interpretable prediction of GB normal stress. Unlike conventional black-box surrogate models, the proposed framework combines physically meaningful descriptors, CE-based mechanism identification, and an explicit compact regression form, enabling the dominant physical variables and their effects on GB normal stress to be directly interpreted. Among 18 physically motivated characteristics, the GB inclination angle, the slip transmission, the climb-related Schmid-type indicator, and the elastic-modulus mismatch are found to be dominant, revealing the coupled roles of interfacial geometry, crystallographic compatibility, creep stress relaxation, and micromechanical contrast. The identified characteristics hierarchy and functional representation remain effective under multiaxial loading and can be extended to tricrystal systems through physically interpretable nonlocal augmentation when a purely local description becomes insufficient, demonstrating strong physical consistency and robust generalizability across physical conditions.

cond-mat.mtrl-sci↗

arXiv2026

Quantitative Video World Model Evaluation for Geometric-Consistency

Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and motion remains challenging. Most existing video evaluation pipelines rely heavily on human judgment or learned graders, which can be subjective and weakly diagnostic for geometric failures. We introduce PDI-Bench (Perspective Distortion Index), a quantitative framework for auditing geometric coherence in generated videos. Given a generated clip, we obtain object-centric observations via segmentation and point tracking (e.g., SAM 2, MegaSaM, and CoTracker3), lift them to 3D world-space coordinates via monocular reconstruction, and compute a set of projective-geometry residuals capturing three failure dimensions: scale-depth alignment, 3D motion consistency, and 3D structural rigidity. To support systematic evaluation, we build PDI-Dataset, covering diverse scenarios designed to stress these geometric constraints. Across state-of-the-art video generators, PDI reveals consistent geometry-specific failure modes that are not captured by common perceptual metrics, and provides a diagnostic signal for progress toward physically grounded video generation and physical world model. Our code and dataset can be found at https://pdi-bench.github.io/.

cs.CV↗

arXiv2025

A Physics-Informed Variational Inference Framework for Identifying Attributions of Extreme Stress Events in Low-Grain Polycrystals

Polycrystalline metal failure often begins with stress concentration at grain boundaries. Identifying which microstructural features trigger these events is important but challenging because these extreme damage events are rare and the failure mechanisms involve multiple complex processes across scales. Most existing inference methods focus on average behavior rather than rare events, whereas standard sample-based methods are computationally expensive for high-dimensional complex systems. In this paper, we develop a new variational inference framework that integrates a recently developed computationally efficient physics-informed statistical model with extreme value statistics to significantly facilitate the identification of material failure attributions. First, we reformulate the objective to emphasize observed exceedances by incorporating extreme-value theory into the likelihood, thereby highlighting tail behavior. Second, we constrain inference via a physics-informed statistical model that characterizes microstructure-stress relationships, which uniquely provides physically consistent predictions for these rare events. Third, mixture models in a reduced latent space are developed to capture the non-Gaussian characteristics of microstructural features, allowing the identification of multiple underlying mechanisms. In both controlled and realistic experimental tests for the bicrystal configuration, the framework achieves reliable extreme-event prediction and reveals the microstructural features associated with material failure, providing physical insights for material design with uncertainty quantification.

stat.AP↗

arXiv2025

Adaptive Confidence-Wise Loss for Improved Lens Structure Segmentation in AS-OCT

Precise lens structure segmentation is essential for the design of intraocular lenses (IOLs) in cataract surgery. Existing deep segmentation networks typically weight all pixels equally under cross-entropy (CE) loss, overlooking the fact that sub-regions of lens structures are inhomogeneous (e.g., some regions perform better than others) and that boundary regions often suffer from poor segmentation calibration at the pixel level. Clinically, experts annotate different sub-regions of lens structures with varying confidence levels, considering factors such as sub-region proportions, ambiguous boundaries, and lens structure shapes. Motivated by this observation, we propose an Adaptive Confidence-Wise (ACW) loss to group each lens structure sub-region into different confidence sub-regions via a confidence threshold from the unique region aspect, aiming to exploit the potential of expert annotation confidence prior. Specifically, ACW clusters each target region into low-confidence and high-confidence groups and then applies a region-weighted loss to reweigh each confidence group. Moreover, we design an adaptive confidence threshold optimization algorithm to adjust the confidence threshold of ACW dynamically. Additionally, to better quantify the miscalibration errors in boundary region segmentation, we propose a new metric, termed Boundary Expected Calibration Error (BECE). Extensive experiments on a clinical lens structure AS-OCT dataset and other multi-structure datasets demonstrate that our ACW significantly outperforms competitive segmentation loss methods across different deep segmentation networks (e.g., MedSAM). Notably, our method surpasses CE with 6.13% IoU gain, 4.33% DSC increase, and 4.79% BECE reduction in lens structure segmentation under U-Net. The code of this paper is available at https://github.com/XiaoLing12138/Adaptive-Confidence-Wise-Loss.

cs.CV↗

arXiv2025

A Simple Intermediate Coupled MJO-ENSO Model: Multiscale Interactions and ENSO Complexity

The Madden-Julian Oscillation (MJO) and the El Niño-Southern Oscillation (ENSO) are two dominant modes of tropical climate variability, each with profound global weather impacts. While their individual dynamics have been widely studied, their coupled interactions, particularly in the context of ENSO complexity, including spatial diversity (Central Pacific vs. Eastern Pacific events), temporal evolution (single-year and multi-year events), and intensity variations (moderate to extreme events), have received limited attention in modeling studies. In this paper, a simple intermediate coupled MJO-ENSO model is developed to address critical gaps in understanding their bidirectional feedback and its role in modulating ENSO complexity. The model integrates multiscale processes, bridging intraseasonal (MJO), interannual (ENSO), and decadal (Walker circulation) variability. Key mechanisms include: (1) interannual SST modulating MJO through latent heat and background states, (2) MJO-induced wind forcing triggering diverse ENSO events, and (3) decadal variability modulating the strength and occurrence frequency of Eastern Pacific and Central Pacific events. Effective stochastic parameterizations are incorporated to improve the characterization of multiscale MJO-ENSO interactions and the emergence of intermittency and extremes. The model captures several crucial observed MJO and ENSO features, including non-Gaussian statistics, seasonal cycles, energy spectra, and spatial event patterns. It also reproduces critical MJO-ENSO interactions: warm pool edge extension, convective activity adjustments that modulate SST, and ENSO's dependence on MJO-driven easterly and westerly wind anomalies. The model provides a useful tool to analyze long-term variations. It also advances the understanding of ENSO extreme events and their remote impacts, as well as seasonal forecasting and climate resilience.

physics.ao-ph↗

arXiv2025

CGKN: A Deep Learning Framework for Modeling Complex Dynamical Systems and Efficient Data Assimilation

Deep learning is widely used to predict complex dynamical systems in many scientific and engineering areas. However, the black-box nature of these deep learning models presents significant challenges for carrying out simultaneous data assimilation (DA), which is a crucial technique for state estimation, model identification, and reconstructing missing data. Integrating ensemble-based DA methods with nonlinear deep learning models is computationally expensive and may suffer from large sampling errors. To address these challenges, we introduce a deep learning framework designed to simultaneously provide accurate forecasts and efficient DA. It is named Conditional Gaussian Koopman Network (CGKN), which transforms general nonlinear systems into nonlinear neural differential equations with conditional Gaussian structures. CGKN aims to retain essential nonlinear components while applying systematic and minimal simplifications to facilitate the development of analytic formulae for nonlinear DA. This allows for seamless integration of DA performance into the deep learning training process, eliminating the need for empirical tuning as required in ensemble methods. CGKN compensates for structural simplifications by lifting the dimension of the system, which is motivated by Koopman theory. Nevertheless, CGKN exploits special nonlinear dynamics within the lifted space. This enables the model to capture extreme events and strong non-Gaussian features in joint and marginal distributions with appropriate uncertainty quantification. We demonstrate the effectiveness of CGKN for both prediction and DA on three strongly nonlinear and non-Gaussian turbulent systems: the projected stochastic Burgers-Sivashinsky equation, the Lorenz 96 system, and the El Niño-Southern Oscillation. The results justify the robustness and computational efficiency of CGKN.

cs.LG↗

arXiv2024

A Stochastic Conceptual Model for the Coupled ENSO and MJO

Understanding the interactions between the El Nino-Southern Oscillation (ENSO) and the Madden-Julian Oscillation (MJO) is essential to studying climate variabilities and predicting extreme weather events. Here, we develop a stochastic conceptual model for describing the coupled ENSO-MJO phenomenon. The model adopts a three-box representation of the interannual ocean component to characterize the ENSO diversity. For the intraseasonal atmospheric component, a low-order Fourier representation is used to describe the eastward propagation of the MJO. We incorporate a simple decadal process to account for modulations in the background state that influence the predominant types of El Nino events. In addition to dynamical coupling through wind forcing and latent heat, state-dependent noise is introduced to characterize the statistical interactions among these multiscale processes, improving the simulation of extreme events. The model successfully reproduces the observed non-Gaussian statistics of ENSO diversity and MJO spectra while capturing the interactions between wind, MJO, and ENSO.

physics.ao-ph↗

arXiv2024

A Physics-Informed Auto-Learning Framework for Developing Stochastic Conceptual Models for ENSO Diversity

Understanding ENSO dynamics has tremendously improved over the past decades. However, one aspect still poorly understood or represented in conceptual models is the ENSO diversity in spatial pattern, peak intensity, and temporal evolution. In this paper, a physics-informed auto-learning framework is developed to derive ENSO stochastic conceptual models with varying degrees of freedom. The framework is computationally efficient and easy to apply. Once the state vector of the target model is set, causal inference is exploited to build the right-hand side of the equations based on a mathematical function library. Fundamentally different from standard nonlinear regression, the auto-learning framework provides a parsimonious model by retaining only terms that improve the dynamical consistency with observations. It can also identify crucial latent variables and provide physical explanations. Exploiting a realistic six-dimensional reference recharge oscillator-based ENSO model, a hierarchy of three- to six-dimensional models is derived using the auto-learning framework and is systematically validated by a unified set of validation criteria assessing the dynamical and statistical features of the ENSO diversity. It is shown that the minimum model characterizing ENSO diversity is four-dimensional, with three interannual variables describing the western Pacific thermocline depth, the eastern and central Pacific sea surface temperatures (SSTs), and one intraseasonal variable for westerly wind events. Without the intraseasonal variable, the resulting three-dimensional model underestimates extreme events and is too regular. The limited number of weak nonlinearities in the model are essential in reproducing the observed extreme El Niños and nonlinear relationship between the eastern and western Pacific SSTs.

math.DS↗

arXiv2023

Data-Driven Statistical Reduced-Order Modeling and Quantification of Polycrystal Mechanics Leading to Porosity-Based Ductile Damage

Predicting the process of porosity-based ductile damage in polycrystalline metallic materials is an essential practical topic. Ductile damage and its precursors are represented by extreme values in stress and material state quantities, the spatial PDF of which are highly non-Gaussian with strong fat tails. Traditional deterministic forecasts using physical models often fail to capture the statistics of structural evolution during material deformation. This study proposes a data-driven statistical reduced-order modeling framework to provide a probabilistic forecast of the deformation process leading to porosity-based ductile damage, with uncertainty quantification. The framework starts with computing the time evolution of the leading moments of specific state variables from full-field polycrystal simulations. Then a sparse model identification algorithm based on causation entropy, including essential physical constraints, is used to discover the governing equations of these moments. An approximate solution of the time evolution of the PDF is obtained from the predicted moments exploiting the maximum entropy principle. Numerical experiments based on polycrystal realizations show that the model can characterize the time evolution of the non-Gaussian PDF of the von Mises stress and quantify the probability of extreme events. The learning process also reveals that the mean stress interacts with higher-order moments and extreme events in a strongly nonlinear and multiplicative fashion. In addition, the calibrated moment equations provide a reasonably accurate forecast when applied to the realizations outside the training data set, indicating the robustness of the model and the skill for extrapolation. Finally, an information-based measurement shows that the leading four moments are sufficient to characterize the crucial non-Gaussian features throughout the entire deformation history.

cond-mat.mtrl-sci↗

arXiv2022

Rigorous Derivation of Stochastic Conceptual Models for the El Niño-Southern Oscillation from a Spatially-Extended Dynamical System

El Niño-Southern Oscillation (ENSO) is the most predominant interannual variability in the tropics, significantly impacting global weather and climate. In this paper, a framework of low-order conceptual models for the ENSO is systematically derived from a spatially-extended stochastic dynamical system with full mathematical rigor. The spatially-extended stochastic dynamical system has a linear, deterministic, and stable dynamical core. It also exploits a simple stochastic process with multiplicative noise to parameterize the intraseasonal wind burst activities. A principal component analysis based on the eigenvalue decomposition method is applied to provide a low-order conceptual model that succeeds in characterizing the large-scale dynamical and non-Gaussian statistical features of the eastern Pacific El Niño events. Despite the low dimensionality, the conceptual modeling framework contains outputs for all the atmosphere, ocean, and sea surface temperature components with detailed spatiotemporal patterns. This contrasts with many existing conceptual models focusing only on a small set of specified state variables. The stochastic versions of many state-of-the-art low-order models, such as the recharge-discharge and the delayed oscillators, become special cases within this framework. The rigorous derivation of such low-order models provides a unique way to connect models with different spatiotemporal complexities. The framework also facilitates understanding the instantaneous and memory effects of stochastic noise in contributing to the large-scale dynamics of the ENSO.

physics.geo-ph↗

arXiv2022

A Causality-Based Learning Approach for Discovering the Underlying Dynamics of Complex Systems from Partial Observations with Stochastic Parameterization

Discovering the underlying dynamics of complex systems from data is an important practical topic. Constrained optimization algorithms are widely utilized and lead to many successes. Yet, such purely data-driven methods may bring about incorrect physics in the presence of random noise and cannot easily handle the situation with incomplete data. In this paper, a new iterative learning algorithm for complex turbulent systems with partial observations is developed that alternates between identifying model structures, recovering unobserved variables, and estimating parameters. First, a causality-based learning approach is utilized for the sparse identification of model structures, which takes into account certain physics knowledge that is pre-learned from data. It has unique advantages in coping with indirect coupling between features and is robust to the stochastic noise. A practical algorithm is designed to facilitate the causal inference for high-dimensional systems. Next, a systematic nonlinear stochastic parameterization is built to characterize the time evolution of the unobserved variables. Closed analytic formula via an efficient nonlinear data assimilation is exploited to sample the trajectories of the unobserved variables, which are then treated as synthetic observations to advance a rapid parameter estimation. Furthermore, the localization of the state variable dependence and the physics constraints are incorporated into the learning procedure, which mitigate the curse of dimensionality and prevent the finite time blow-up issue. Numerical experiments show that the new algorithm succeeds in identifying the model structure and providing suitable stochastic parameterizations for many complex nonlinear systems with chaotic dynamics, spatiotemporal multiscale structures, intermittency, and extreme events.

math.DS↗