arXiv subjects

Ximing Wu

Publications and source records attributed to Ximing Wu.

3 recordsLinked to original sources

arXiv2025

A Summer Meridional Subsurface Temperature Dipole Mode in the South China Sea

The ocean heat content variability in the South China Sea (SCS) plays a pivotal role in regional climate and extreme weather events, such as tropical cyclones. Using high-resolution ocean reanalysis data, we show that the SCS exhibits a summer subsurface temperature dipole mode that controls the interannual variability of ocean heat content in the upper SCS. This dipole mode manifests as warm anomalies in the north and cold anomalies in the south during strong monsoon years, and a reversed pattern during weak monsoons years. The monsoon variability is linked to large-scale climate variability associated with El Ni\~no-Southern Oscillation transitions. Heat budget analysis indicates that this dipole pattern is primarily driven by vertical heat transport linked to opposite wind stress curl anomalies in the northern and southern basin. Accompanying the vertical heat transports is a shallow meridional overturning circulation that redistributes heat between the northern and southern SCS.

physics.ao-ph↗

arXiv2024

DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation

Accurately segmenting lesions in ultrasound images is challenging due to the difficulty in distinguishing boundaries between lesions and surrounding tissues. While deep learning has improved segmentation accuracy, there is limited focus on boundary quality and its relationship with body structures. To address this, we introduce UBBS-Net, a dual-branch deep neural network that learns the relationship between body and boundary for improved segmentation. We also propose a feature fusion module to integrate body and boundary information. Evaluated on three public datasets, UBBS-Net outperforms existing methods, achieving Dice Similarity Coefficients of 81.05% for breast cancer, 76.41% for brachial plexus nerves, and 87.75% for infantile hemangioma segmentation. Our results demonstrate the effectiveness of UBBS-Net for ultrasound image segmentation. The code is available at https://github.com/apple1986/DBF-Net.

eess.IV↗

arXiv2022

Hierarchical Gaussian Process Models for Regression Discontinuity/Kink under Sharp and Fuzzy Designs

We propose nonparametric Bayesian estimators for causal inference exploiting Regression Discontinuity/Kink (RD/RK) under sharp and fuzzy designs. Our estimators are based on Gaussian Process (GP) regression and classification. The GP methods are powerful probabilistic machine learning approaches that are advantageous in terms of derivative estimation and uncertainty quantification, facilitating RK estimation and inference of RD/RK models. These estimators are extended to hierarchical GP models with an intermediate Bayesian neural network layer and can be characterized as hybrid deep learning models. Monte Carlo simulations show that our estimators perform comparably to and sometimes better than competing estimators in terms of precision, coverage and interval length. The hierarchical GP models considerably improve upon one-layer GP models. We apply the proposed methods to estimate the incumbency advantage of US house elections. Our estimations suggest a significant incumbency advantage in terms of both vote share and probability of winning in the next elections. Lastly we present an extension to accommodate covariate adjustment.

stat.ML↗