Department of Earth System Science Ministry of Education Key Laboratory for Earth System Modeling Institute for Global Change Studies Tsinghua University Beijing China
Auto-generated profile, based on publicly available information
Shuyi Zhou
Department of Earth System Science Ministry of Education Key Laboratory for Earth System Modeling Institute for Global Change Studies Tsinghua University Beijing China
Modeling the evolution of physical dynamics is a foundational problem in science and engineering, and it is regarded as the modeling of an operator mapping between infinite-dimensional functional spaces. Operator learning methods, learning the underlying infinite-dimensional operator in a high-dimensional latent space, have shown significant potential in modeling physical dynamics. However, there remains insufficient research on how to approximate an infinite-dimensional operator using a finite-dimensional parameter space. Inappropriate dimensionality representation of the underlying operator leads to convergence difficulties, decreasing generalization capability, and violating the physical consistency. To address the problem, we present Neural Manifold Operator (NMO) to learn the invariant subspace with the intrinsic dimension to parameterize infinite-dimensional underlying operators. NMO achieves state-of-the-art performance in statistical and physical metrics and gains 23.35% average improvement on three real-world scenarios and four equation-governed scenarios across a wide range of multi-disciplinary fields. Our paradigm has demonstrated universal effectiveness across various model structure implementations, including Multi-Layer Perceptron, Convolutional Neural Networks, and Transformers. Experimentally, we prove that the intrinsic dimension calculated by our paradigm is the optimal dimensional representation of the underlying operators. We release our code at https://github.com/AI4EarthLab/Neural-Manifold-Operators.
Grounded on the social exchange theory (SET), social cognitive theory (SCT), and self-determination theory (SDT), this study aims to explore the mediating role of self-efficacy (SE) and work engagement (WE) on the effect of social support (SS) on job satisfaction (JS) among Chinese ethnic minority kindergarten teachers (KTs). The results show that: (1) SS has a directly significant effect on JS; (2) WE mediates the relationship between SS and JS; and (3) SE mediates the relationship between SS and WE. Although the mediation of SE on the relationship between SS and JS is not found, the posited multiple mediations of SE and WE on the relationship between SS and JS are totally accepted. The results reveal that SS mainland Chinese ethnic minority KTs received can not only have a direct effect on JS but also have an indirect impact through the one-path mediating role of WE and the chain mediating role of SE and WE. The results suggest that governments, supervisors, and sponsors should work together to provide ethnic minority KTs with more prioritized SS from both cultural psychology and financial material and opportunities for facilitating professional knowledge and skills in order to enhance their SE, inspire their WE, and eventually accumulate their JS.
High‐resolution sea surface velocity (SSV) is crucial for advancing our understanding of ocean sub‐mesoscale processes, energy cascades, etc. The recently launched Surface Water and Ocean Topography (SWOT) satellite measures sea surface height with a sub‐mesoscale resolved resolution. Based on geostrophic balance, the so‐called geostrophic velocity in SWOT is estimated. Although the SWOT‐derived velocity is not true geostrophic velocity as it does not consider the separation of balanced and unbalanced motions, it offers valuable insights into both geostrophic and ageostrophic velocities. Here we propose a machine learning‐based model to infer the SSV using SWOT and drifter data. The result demonstrates the error between the geostrophic velocities from SWOT and the total velocities from the drifter are reduced by about 50%. Furthermore, the kinetic energy of inferred velocities aligns more closely with reanalysis data, particularly at low latitudes. This study thus presents a promising approach for inferring global SSV using SWOT data.
Ocean motions at mesoscales (∼100 km) and below actively trigger air‐sea interactions by inducing anomalies of sea surface temperature (SST) and currents. Despite extensive research on oceanic submesoscale (O (0.1–10) km) processes, observational understanding of submesoscale air‐sea interactions remains limited. Using high‐resolution wind data from the Surface Water and Ocean Topography satellite and SST data from the Advanced Very High Resolution Radiometer, we investigate the wind response to submesoscale SST anomalies in five strong boundary current regions over the globe. Based on 3,054 samples obtained by identifying SST fronts and matching wind fields, we calculate and analyze the submesoscale coupling coefficient that measures the intensity of the response. The mean of the coefficients from the five regions is 0.51 m s −1 °C −1 . Comparison shows a pronounced regional variability of the coefficient, with a factor of up to 1.56. This study provides an observational guide for high‐resolution coupled model simulation validation.