Towards real-time assessment of infrasound event detection capability using deep learning-based transmission loss estimation

2025-06-03

AI Summary

To address the high computational cost, lack of real-time assessment capability, and poor long-range compatibility in modeling infrasound propagation loss for the International Monitoring System (IMS), this paper proposes a deep learning model integrating wind and temperature profiles up to 130 km altitude. Methodologically, it introduces the first hybrid architecture combining convolutional and recurrent layers to capture spatial–range coupling dependencies in atmospheric parameters, augmented by a dual uncertainty quantification framework accounting for both epistemic and aleatoric uncertainties. Trained on ECMWF reanalysis data and parabolic equation simulations, the model achieves a mean prediction error of only 4 dB in propagation loss. It successfully generalizes to the 2022 Hunga Tonga–Hunga Haʻapai volcanic eruption—enabling real-time detection threshold estimation under unseen atmospheric conditions and frequency bands. This significantly enhances the timeliness and robustness of verification monitoring for the Comprehensive Nuclear-Test-Ban Treaty.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate modeling of infrasound transmission loss is essential for evaluating the performance of the International Monitoring System, enabling the effective design and maintenance of infrasound stations to support compliance of the Comprehensive Nuclear-Test-Ban Treaty. State-of-the-art propagation modeling tools enable transmission loss to be finely simulated using atmospheric models. However, the computational cost prohibits the exploration of a large parameter space in operational monitoring applications. To address this, recent studies made use of a deep learning algorithm capable of making transmission loss predictions almost instantaneously. However, the use of nudged atmospheric models leads to an incomplete representation of the medium, and the absence of temperature as an input makes the algorithm incompatible with long range propagation. In this study, we address these limitations by using both wind and temperature fields as inputs to a neural network, simulated up to 130 km altitude and 4,000 km distance. We also optimize several aspects of the neural network architecture. We exploit convolutional and recurrent layers to capture spatially and range-dependent features embedded in realistic atmospheric models, improving the overall performance. The neural network reaches an average error of 4 dB compared to full parabolic equation simulations and provides epistemic and data-related uncertainty estimates. Its evaluation on the 2022 Hunga Tonga-Hunga Ha'apai volcanic eruption demonstrates its prediction capability using atmospheric conditions and frequencies not included in the training. This represents a significant step towards near real-time assessment of International Monitoring System detection thresholds of explosive sources.

Problem

• Real-time infrasound detection using deep learning
• Improving transmission loss prediction accuracy
• Enhancing International Monitoring System performance

Innovation

• Uses wind and temperature fields as neural network inputs
• Combines convolutional and recurrent layers for feature capture
• Achieves 4 dB error vs full simulations with uncertainty estimates