mlsanityData to 14 Oct 2026

Physics-Enhanced TinyML for Real-Time Detection of Ground Magnetic Anomalies

arXiv 2311.11452 ↗First posted 19 Nov 2023cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Space weather phenomena like geomagnetic disturbances (GMDs) and geomagnetically induced currents (GICs) pose significant risks to critical technological infrastructure. While traditional predictive models, grounded in simulation, hold theoretical robustness, they grapple with challenges, notably the assimilation of imprecise data and extensive computational complexities. In recent years, Tiny Machine Learning (TinyML) has been adopted to develop Machine Learning (ML)-enabled magnetometer systems for predicting real-time terrestrial magnetic perturbations as a proxy measure for GIC. While TinyML offers efficient, real-time data processing, its intrinsic limitations prevent the utilization of robust methods with high computational needs. This paper developed a physics-guided TinyML framework to address the above challenges. This framework integrates physics-based regularization at the stages of model training and compression, thereby augmenting the reliability of predictions. The developed pruning scheme within the framework harnesses the inherent physical characteristics of the domain, striking a balance between model size and robustness. The study presents empirical results, drawing a comprehensive comparison between the accuracy and reliability of the developed framework and its traditional counterpart. Such a comparative analysis underscores the prospective applicability of the developed framework in conceptualizing robust, ML-enabled magnetometer systems for real-time space weather forecasting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 72 references that are in the map. First posted on arXiv 19 Nov 2023.

Builds on

19 of 72 references.

References · 19

  1. 2020Knowledge Distillation: A Surveycited by 1,603
  2. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 608
  3. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 603
  4. 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 473
  5. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
  6. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  7. 2020Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systemscited by 164
  8. 2019Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networkscited by 129
  9. 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
  10. 2020Benchmarking TinyML Systems: Challenges and Directioncited by 91
  11. 2019Model Compression with Adversarial Robustness: A Unified Optimization Frameworkcited by 71
  12. 2020Compression of Deep Learning Models for Text: A Surveycited by 64
7 more
  1. 2020Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profilescited by 59
  2. 2021Physics-Guided Deep Learning for Dynamical Systems: A Surveycited by 44
  3. 2020Knowledge Distillation in Deep Learning and its Applicationscited by 29
  4. 2020Going Beyond Classification Accuracy Metrics in Model Compressioncited by 15
  5. 2021Applying physics-based loss functions to neural networks for improved generalizability in mechanics problemscited by 5
  6. 2021Classification of fNIRS Data Under Uncertainty: A Bayesian Neural Network Approachcited by 2
  7. 2022Real-Time Machine Learning Enabled Low-Cost Magnetometer Systemcited by 1

Built on by

Not cited yet.