Browsing by Author "Daw, Arka"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Beyond Discriminative Regions: Saliency Maps as Alternatives to CAMs for Weakly Supervised Semantic Segmentation
    Maruf, M.; Daw, Arka; Dutta, Amartya; Bu, Jie; Karpatne, Anuj (2023)
  • Thumbnail Image
    MEMTRACK: A Deep Learning-Based Approach to Microrobot Tracking in Dense and Low-Contrast Environments
    Sawhney, Medha; Karmarkar, Bhas; Leaman, Eric J.; Daw, Arka; Karpatne, Anuj; Behkam, Bahareh (2023)
    Tracking microrobots is challenging, considering their minute size and high speed. As the field progresses towards developing microrobots for biomedical applications and conducting mechanistic studies in physiologically relevant media (e.g., collagen), this challenge is exacerbated by the dense surrounding environments with feature size and shape comparable to microrobots. Herein, we report Motion Enhanced Multi-level Tracker (MEMTrack), a robust pipeline for detecting and tracking microrobots using synthetic motion features, deep learning-based object detection, and a modified Simple Online and Real-time Tracking (SORT) algorithm with interpolation for tracking. Our object detection approach combines different models based on the object’s motion pattern. We trained and validated our model using bacterial micro-motors in collagen (tissue phantom) and tested it in collagen and aqueous media. We demonstrate that MEMTrack accurately tracks even the most challenging bacteria missed by skilled human annotators, achieving precision and recall of 77% and 48% in collagen and 94% and 35% in liquid media, respectively. Moreover, we show that MEMTrack can quantify average bacteria speed with no statistically significant difference from the laboriously-produced manual tracking data. MEMTrack represents a significant contribution to microrobot localization and tracking, and opens the potential for vision-based deep learning approaches to microrobot control in dense and low-contrast settings. All source code for training and testing MEMTrack and reproducing the results of the paper have been made publicly available https://github.com/sawhney-medha/MEMTrack.
  • Thumbnail Image
    Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling
    Daw, Arka; Bu, Jie; Wang, Sifan; Perdikaris, Paris; Karpatne, Anuj (2022)
    Despite the success of physics-informed neural networks (PINNs) in approximating partial differential equations (PDEs), PINNs can sometimes fail to converge to the correct solution in problems involving complicated PDEs. This is reflected in several recent studies on characterizing the “failure modes” of PINNs, although a thorough understanding of the connection between PINN failure modes and sampling strategies is missing. In this paper, we provide a novel perspective of failure modes of PINNs by hypothesizing that training PINNs relies on successful “propagation” of solution from initial and/or boundary condition points to interior points. We show that PINNs with poor sampling strategies can get stuck at trivial solutions if there are propagation failures, characterized by highly imbalanced PDE residual fields. To mitigate propagation failures, we propose a novel Retain-Resample-Release sampling (R3) algorithm that can incrementally accumulate collocation points in regions of high PDE residuals with little to no computational overhead. We provide an extension of R3 sampling to respect the principle of causality while solving timedependent PDEs. We theoretically analyze the behavior of R3 sampling and empirically demonstrate its efficacy and efficiency in comparison with baselines on a variety of PDE problems.
  • Thumbnail Image
    Physics-aware Architecture of Neural Networks for Uncertainty Quantification: Application in Lake Temperature Modeling
    Daw, Arka; Karpatne, Anuj (SIGKDD, 2019-08-05)
    In this paper, we explore a novel direction of research in theory-guided data science to develop physics-aware architectures of artificial neural networks (ANNs), where scientific knowledge is baked in the construction of ANN models. While previous efforts in theory-guided data science have used physics-based loss functions to guide the learning of neural network models to generalizable and physically consistent solutions, they do no guarantee that the model predictions will be physically consistent on unseen test instances, especially after slightly perturbing the trained model, as explored in dropout using testing methods for uncertainty quantification (UQ). On the other hand, our physics-aware ANN architecture hard-wires physical relationships in the ANN design, thus resulting in model predictions which always comply with known physics, even after performing dropout during testing for UQ. We provide some initial results to illustrate the effectiveness of our physics-aware neural network architecture in the context of lake temperature modeling, and show that our approach shows significantly lower physical inconsistency as compared to baseline methods.
  • Thumbnail Image
    Physics-Informed Discriminator (PID) for Conditional Generative Adversarial Nets
    Daw, Arka; Maruf, M.; Karpatne, Anuj (NeurIPS, 2020-12-11)
    We propose a novel method of incorporating physical knowledge as an additional input to the discriminator of a conditional Generative Adversarial Net (cGAN). Our proposed approach, termed as Physics-informed Discriminator for cGAN (cGAN-PID), is more aligned to the adversarial learning idea of cGAN as opposed to existing methods on incorporating physical knowledge in GANs by adding physics based loss functions as additional terms in the optimization objective of GAN. We evaluate the performance of our model on two toy datasets and demonstrate that our proposed cGAN-PID can be used as an alternative to the existing techniques.
  • Thumbnail Image
    Physics-informed Machine Learning with Uncertainty Quantification
    Daw, Arka (Virginia Tech, 2024-02-12)
    Physics Informed Machine Learning (PIML) has emerged as the forefront of research in scientific machine learning with the key motivation of systematically coupling machine learning (ML) methods with prior domain knowledge often available in the form of physics supervision. Uncertainty quantification (UQ) is an important goal in many scientific use-cases, where the obtaining reliable ML model predictions and accessing the potential risks associated with them is crucial. In this thesis, we propose novel methodologies in three key areas for improving uncertainty quantification for PIML. First, we propose to explicitly infuse the physics prior in the form of monotonicity constraints through architectural modifications in neural networks for quantifying uncertainty. Second, we demonstrate a more general framework for quantifying uncertainty with PIML that is compatible with generic forms of physics supervision such as PDEs and closed form equations. Lastly, we study the limitations of physics-based loss in the context of Physics-informed Neural Networks (PINNs), and develop an efficient sampling strategy to mitigate the failure modes.
  • Thumbnail Image
    Source Identification and Field Reconstruction of Advection-Diffusion Process from Sparse Sensor Measurements
    Daw, Arka; Karpatne, Anuj; Yeo, Kyongmin; Klein, Levente (Conference on Neural Information Processing Systems, 2022-11-11)
    Inferring the source information of greenhouse gases, such as methane, from spatially sparse sensor observations is an essential element in mitigating climate change. While it is well understood that the complex behavior of the atmospheric dispersion of such pollutants is governed by the Advection-Diffusion equation, it is difficult to directly apply the governing equations to identify the source information because of the spatially sparse observations, i.e., the pollution concentration is known only at the sensor locations. Here, we develop a multi-task learning framework that can provide high-fidelity reconstruction of the concentration field and identify emission characteristics of the pollution sources such as their location, emission strength, etc. from sparse sensor observations. We demonstrate that our proposed framework is able to achieve accurate reconstruction of the methane concentrations from sparse sensor measurements as well as precisely pin-point the location and emission strength of these pollution sources.