skip to main content


Search for: All records

Creators/Authors contains: "Jia"

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. Abstract

    Accurate and cost-effective quantification of the carbon cycle for agroecosystems at decision-relevant scales is critical to mitigating climate change and ensuring sustainable food production. However, conventional process-based or data-driven modeling approaches alone have large prediction uncertainties due to the complex biogeochemical processes to model and the lack of observations to constrain many key state and flux variables. Here we propose a Knowledge-Guided Machine Learning (KGML) framework that addresses the above challenges by integrating knowledge embedded in a process-based model, high-resolution remote sensing observations, and machine learning (ML) techniques. Using the U.S. Corn Belt as a testbed, we demonstrate that KGML can outperform conventional process-based and black-box ML models in quantifying carbon cycle dynamics. Our high-resolution approach quantitatively reveals 86% more spatial detail of soil organic carbon changes than conventional coarse-resolution approaches. Moreover, we outline a protocol for improving KGML via various paths, which can be generalized to develop hybrid models to better predict complex earth system dynamics.

     
    more » « less
    Free, publicly-accessible full text available December 1, 2025
  2. Free, publicly-accessible full text available June 30, 2025
  3. Free, publicly-accessible full text available May 31, 2025
  4. Fairness-awareness has emerged as an essential building block for the responsible use of artificial intelligence in real applications. In many cases, inequity in performance is due to the change in distribution over different regions. While techniques have been developed to improve the transferability of fairness, a solution to the problem is not always feasible with no samples from the new regions, which is a bottleneck for pure data-driven attempts. Fortunately, physics-based mechanistic models have been studied for many problems with major social impacts. We propose SimFair, a physics-guided fairness-aware learning framework, which bridges the data limitation by integrating physical-rule-based simulation and inverse modeling into the training design. Using temperature prediction as an example, we demonstrate the effectiveness of the proposed SimFair in fairness preservation.

     
    more » « less
    Free, publicly-accessible full text available March 25, 2025
  5. Abstract

    Natural materials typically exhibit irregular and non-periodic architectures, endowing them with compelling functionalities such as body protection, camouflage, and mechanical stress modulation. Among these functionalities, mechanical stress modulation is crucial for homeostasis regulation and tissue remodeling. Here, we uncover the relationship between stress modulation functionality and the irregularity of bio-inspired architected materials by a generative computational framework. This framework optimizes the spatial distribution of a limited set of basic building blocks and uses these blocks to assemble irregular materials with heterogeneous, disordered microstructures. Despite being irregular and non-periodic, the assembled materials display spatially varying properties that precisely modulate stress distribution towards target values in various control regions and load cases, echoing the robust stress modulation capability of natural materials. The performance of the generated irregular architected materials is experimentally validated with 3D printed physical samples — a good agreement with target stress distribution is observed. Owing to its capability to redirect loads while keeping a proper amount of stress to stimulate bone repair, we demonstrate the potential application of the stress-programmable architected materials as support in orthopedic femur restoration.

     
    more » « less
  6. Ben-Tabou, Smadar (Ed.)
    Free, publicly-accessible full text available April 24, 2025
  7. Free, publicly-accessible full text available April 1, 2025
  8. Abstract

    The two most important wave modes responsible for energetic electron scattering to the Earth's ionosphere are electromagnetic ion cyclotron (EMIC) waves and whistler‐mode waves. These wave modes operate in different energy ranges: whistler‐mode waves are mostly effective in scattering sub‐relativistic electrons, whereas EMIC waves predominately scatter relativistic electrons. In this study, we report the direct observations of energetic electron (from 50 keV to 2.5 MeV) scattering driven by the combined effect of whistler‐mode and EMIC waves using ELFIN measurements. We analyze five events showing EMIC‐driven relativistic electron precipitation accompanied by bursts of whistler‐driven precipitation over a wide energy range. These events reveal an enhancement of relativistic electron precipitation by EMIC waves during intervals of whistler‐mode precipitation compared to intervals of EMIC‐only precipitation. We discuss a possible mechanism responsible for such precipitation. We suggest that below the minimum resonance energy (Emin) of EMIC waves, the whistler‐mode wave may both scatter electrons into the loss‐cone and accelerate them to higher energy (1–3 MeV). Electrons accelerated aboveEminresonate with EMIC waves that, in turn, quickly scatter those electrons into the loss‐cone. This enhances relativistic electron precipitation beyond what EMIC waves alone could achieve. We present theoretical support for this mechanism, along with observational evidence from the ELFIN mission. We discuss methodologies for further observational investigations of this combined whistler‐mode and EMIC precipitation.

     
    more » « less
    Free, publicly-accessible full text available May 1, 2025
  9. Accurate prediction of water flow is of utmost importance, particularly for ensuring water supply and informing early actions for floods and droughts. Existing flow prediction methods rely on the input of weather drivers, which hinders their applicability to monitoring small headwater streams due to the limited spatial resolution of existing weather datasets. This paper introduces a new dataset with frequent imagery on streams for water monitoring tasks. Our objective is to automatically predict streamflow for each stream site using frequent images taken at a sub-hourly scale. To overcome the challenge of limited labels for certain stream sites, we employ knowledge transfer from well-observed sites to poorly-observed sites via domain adaptation. As each stream site involves highly variable time series data over long periods, we introduce a novel method STCGAN (Spatial-Temporal Cycle Generative Adversarial Network), which incorporates temporal context by conditioning on the sequence's time and learns overall trends of stream flow variation. It integrates the predictive modeling of streamflow with the cyclic generative process and enhances the prediction with data augmentation using generated synthetic samples. Our experiments demonstrate superior performance of the proposed method using data collected from the West Brook area located in western Massachusetts, US. The proposed method can be further extended to selectively combine information from multiple well-observed stream sites, leading to improved overall performance. 
    more » « less