Search for: All records

Abstract The ability to control the electrode interfaces in an electrochemical energy storage system is essential for achieving the desired electrochemical performance. However, achieving this ability requires an in-depth understanding of the detailed interfacial nanostructures of the electrode under electrochemical operating conditions. In-situ transmission electron microscopy (TEM) is one of the most powerful techniques for revealing electrochemical energy storage mechanisms with high spatiotemporal resolution and high sensitivity in complex electrochemical environments. These attributes play a unique role in understanding how ion transport inside electrode nanomaterials and across interfaces under the dynamic conditions within working batteries. This review aims to gain an in-depth insight into the latest developments of in-situ TEM imaging techniques for probing the interfacial nanostructures of electrochemical energy storage systems, including atomic-scale structural imaging, strain field imaging, electron holography, and integrated differential phase contrast imaging. Significant examples will be described to highlight the fundamental understanding of atomic-scale and nanoscale mechanisms from employing state-of-the-art imaging techniques to visualize structural evolution, ionic valence state changes, and strain mapping, ion transport dynamics. The review concludes by providing a perspective discussion of future directions of the development and application of in-situ TEM techniques in the field of electrochemical energy storage systems. 

ABSTRACT Stress drop is a fundamental parameter related to earthquake source physics, but is hard to measure accurately. To better understand how different factors influence stress-drop measurements, we compare two different methods using the Ridgecrest stress-drop validation data set: spectral decomposition (SD) and spectral ratio (SR), each with different processing options. We also examine the influence of spectral complexity on source parameter measurement. Applying the SD method, we find that frequency bandwidth and time-window length could influence spectral magnitude calibration, while depth-dependent attenuation is important to correctly map stress-drop variations. For the SR method, we find that the selected source model has limited influence on the measurements; however, the Boatwright model tends to produce smaller standard deviation and larger magnitude dependence than the Brune model. Variance reduction threshold, frequency bandwidth, and time-window length, if chosen within an appropriate parameter range, have limited influence on source parameter measurement. For both methods, wave type, attenuation correction, and spectral complexity strongly influence the result. The scale factor that quantifies the magnitude dependence of stress drop show large variations with different processing options, and earthquakes with complex source spectra deviating from the Brune-type source models tend to have larger scale factor than earthquakes without complexity. Based on these detailed comparisons, we make a few specific suggestions for data processing workflows that could help future studies of source parameters and interpretations. 

Automated interpretation of ultrasound imaging of the heart (echocardiograms) could improve the detection and treatment of aortic stenosis (AS), a deadly heart disease. However, existing deep learning pipelines for assessing AS from echocardiograms have two key limitations. First, most methods rely on limited 2D cineloops, thereby ignoring widely available Spectral Doppler imaging that contains important complementary information about pressure gradients and blood flow abnormalities associated with AS. Second, obtaining labeled data is difficult. There are often far more unlabeled echocardiogram recordings available, but these remain underutilized by existing methods. To overcome these limitations, we introduce Semi-supervised Multimodal Multiple-Instance Learning (SMMIL), a new deep learning framework for automatic interpretation for structural heart diseases like AS. During training, SMMIL can combine a smaller labeled set and an abundant unlabeled set of both 2D and Doppler modalities to improve its classifier. When deployed, SMMIL can combine information from all available images to produce an accurate study-level diagnosis of this life-threatening condition. Experiments demonstrate that SMMIL outperforms recent alternatives, including two medical foundation models. 

Automated interpretation of ultrasound imaging of the heart (echocardiograms) could improve the detection and treatment of aortic stenosis (AS), a deadly heart disease. However, existing deep learning pipelines for assessing AS from echocardiograms have two key limitations. First, most methods rely on limited 2D cineloops, thereby ignoring widely available Spectral Doppler imaging that contains important complementary information about pressure gradients and blood flow abnormalities associated with AS. Second, obtaining labeled data is difficult. There are often far more unlabeled echocardiogram recordings available, but these remain underutilized by existing methods. To overcome these limitations, we introduce Semi-supervised Multimodal Multiple-Instance Learning (SMMIL), a new deep learning framework for automatic interpretation for structural heart diseases like AS. During training, SMMIL can combine a smaller labeled set and an abundant unlabeled set of both 2D and Doppler modalities to improve its classifier. When deployed, SMMIL can combine information from all available images to produce an accurate study-level diagnosis of this life-threatening condition. Experiments demonstrate that SMMIL outperforms recent alternatives, including two medical foundation models. 

Physics-guided machine learning (PGML) has become a prevalent approach in studying scientific systems due to its ability to integrate scientific theories for enhancing machine learning (ML) models. However, most PGML approaches are tailored to isolated and relatively simple tasks, which limits their applicability to complex systems involving multiple interacting processes and numerous influencing features. In this paper, we propose a Physics-Guided Foundation Model (PGFM) that combines pre-trained ML models and physics-based models and leverages their complementary strengths to improve the modeling of multiple coupled processes. To effectively conduct pre-training, we construct a simulated environmental system that encompasses a wide range of influencing features and various simulated variables generated by physics-based models. The model is pre-trained in this system to adaptively select important feature interactions guided by multi-task objectives. We then fine-tune the model for each specific task using true observations, while maintaining consistency with established physical theories, such as the principles of mass and energy conservation. We demonstrate the effectiveness of this methodology in modeling water temperature and dissolved oxygen dynamics in real-world lakes. The proposed PGFM is also broadly applicable to a range of scientific fields where physics-based models are being used.