skip to main content

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Thursday, February 13 until 2:00 AM ET on Friday, February 14 due to maintenance. We apologize for the inconvenience.


Search for: All records

Creators/Authors contains: "Liu, G."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Free, publicly-accessible full text available December 29, 2025
  2. Free, publicly-accessible full text available December 27, 2025
  3. Graph neural networks (GNNs) are proficient machine learning models in handling irregularly structured data. Nevertheless, their generic formulation falls short when applied to the analysis of brain connectomes in Alzheimer’s Disease (AD), necessitating the incorporation of domain-specific knowledge to achieve optimal model performance. The integration of AD-related expertise into GNNs presents a significant challenge. Current methodologies reliant on manual design often demand substantial expertise from external domain specialists to guide the development of novel models, thereby consuming considerable time and resources. To mitigate the need for manual curation, this paper introduces a novel self-guided knowledge-infused multimodal GNN to autonomously integrate domain knowledge into the model development process. We propose to conceptualize existing domain knowledge as natural language, and devise a specialized multimodal GNN framework tailored to leverage this uncurated knowledge to direct the learning of the GNN submodule, thereby enhancing its efficacy and improving prediction interpretability. To assess the effectiveness of our framework, we compile a comprehensive literature dataset comprising recent peer-reviewed publications on AD. By integrating this literature dataset with several real-world AD datasets, our experimental results illustrate the effectiveness of the proposed method in extracting curated knowledge and offering explanations on graphs for domain-specific applications. Furthermore, our approach successfully utilizes the extracted information to enhance the performance of the GNN. 
    more » « less
    Free, publicly-accessible full text available October 4, 2025
  4. The MRI-derived brain network serves as a pivotal instrument in elucidating both the structural and functional aspects of the brain, encompassing the ramifications of diseases and developmental processes. However, prevailing methodologies, often focusing on synchronous BOLD signals from functional MRI (fMRI), may not capture directional influences among brain regions and rarely tackle temporal functional dynamics. In this study, we first construct the brain-effective network via the dynamic causal model. Subsequently, we introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE). This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks via an ordinary differential equation (ODE) model, which characterizes spatial-temporal brain dynamics. Our framework is validated on several clinical phenotype prediction tasks using two independent publicly available datasets (HCP and OASIS). The experimental results clearly demonstrate the advantages of our model compared to several state-of-the-art methods. 
    more » « less
    Free, publicly-accessible full text available October 4, 2025
  5. Multimodal medical image synthesis is an important task. Previous efforts mainly focus on the task domain of medical image synthesis using the complete source data and have achieved great success. However, data collection with completeness in real life might be prohibitive due to high expenses or other difficulties, particularly in brain imaging studies. In this paper, we address the challenging and important problem of medical image synthesis from incomplete multimodal data sources. We propose to learn the modal-wise representations and synthesize the targets accordingly. Particularly, a surrogate sampler is derived to generate the target representations from incomplete observations, based on which an interpretable attention-redistribution network is designed. The experimental results synthesizing PET images from MRI images demonstrate that the proposed method can solve different missing data scenarios and outperforms related baselines consistently. 
    more » « less
    Free, publicly-accessible full text available May 27, 2025
  6. Coupled partial differential equations (PDEs) are key tasks in modeling the complex dynamics of many physical processes. Recently, neural operators have shown the ability to solve PDEs by learning the integral kernel directly in Fourier/Wavelet space, so the difficulty for solving the coupled PDEs depends on dealing with the coupled mappings between the functions. Towards this end, we propose a coupled multiwavelets neural operator (CMWNO) learning scheme by decoupling the coupled integral kernels during the multiwavelet decomposition and reconstruction procedures in the Wavelet space. The proposed model achieves significantly higher accuracy compared to previous learning-based solvers in solving the coupled PDEs including Gray-Scott (GS) equations and the non-local mean field game (MFG) problem. According to our experimental results, the proposed model exhibits a 2ˆ „ 4ˆ improvement relative L2 error compared to the best results from the state-of-the-art models. 
    more » « less
  7. Abstract

    Aquifers supporting irrigated agriculture are a resource of global importance. Many of these systems, however, are experiencing significant pumping‐induced stress that threatens their continued viability as a water source for irrigation. Reductions in pumping are often the only option to extend the lifespans of these aquifers and the agricultural production they support. The impact of reductions depends on a quantity known as “net inflow” or “capture.” We use data from a network of wells in the western Kansas portions of the High Plains aquifer in the central United States to demonstrate the importance of net inflow, how it can be estimated in the field, how it might vary in response to pumping reductions, and why use of “net inflow” may be preferred over “capture” in certain contexts. Net inflow has remained approximately constant over much of western Kansas for at least the last 15 to 25 years, thereby allowing it to serve as a target for sustainability efforts. The percent pumping reduction required to reach net inflow (i.e., stabilize water levels for the near term [years to a few decades]) can vary greatly over this region, which has important implications for groundwater management. However, the reduction does appear practically achievable (less than 30%) in many areas. The field‐determined net inflow can play an important role in calibration of regional groundwater models; failure to reproduce its magnitude and temporal variations should prompt further calibration. Although net inflow is a universally applicable concept, the reliability of field estimates is greatest in seasonally pumped aquifers.

     
    more » « less
  8. null (Ed.)