gWaveNet: Classification of Gravity Waves from Noisy Satellite Data using Custom Kernel Integrated Deep Learning Method
Seraj Al Mahmud Mostafa, Omar Faruque, Chenxi Wang, Jia Yue, Sanjay Purushotham, Jianwu Wang
TL;DR
This paper addresses the challenge of detecting atmospheric gravity waves in noisy satellite night-band images with limited ground truth. It introduces gWaveNet, a 15-layer CNN that incorporates a novel checkerboard kernel in the first layer to enhance gravity-wave pattern recognition without denoising. The results show that a trainable 7x7 checkerboard kernel achieves state-of-the-art performance (training accuracy around 98%, test accuracy around 94%, F1 ~93.7%), outperforming several baselines including ViT and VGG16, with strong ablation evidence for kernel size and trainability. The work demonstrates a generalizable hybrid approach for gravity-wave detection in noisy remote-sensing data and provides open-source code for broader application and future extensions such as multi-angular data and localization tasks.
Abstract
Atmospheric gravity waves occur in the Earths atmosphere caused by an interplay between gravity and buoyancy forces. These waves have profound impacts on various aspects of the atmosphere, including the patterns of precipitation, cloud formation, ozone distribution, aerosols, and pollutant dispersion. Therefore, understanding gravity waves is essential to comprehend and monitor changes in a wide range of atmospheric behaviors. Limited studies have been conducted to identify gravity waves from satellite data using machine learning techniques. Particularly, without applying noise removal techniques, it remains an underexplored area of research. This study presents a novel kernel design aimed at identifying gravity waves within satellite images. The proposed kernel is seamlessly integrated into a deep convolutional neural network, denoted as gWaveNet. Our proposed model exhibits impressive proficiency in detecting images containing gravity waves from noisy satellite data without any feature engineering. The empirical results show our model outperforms related approaches by achieving over 98% training accuracy and over 94% test accuracy which is known to be the best result for gravity waves detection up to the time of this work. We open sourced our code at https://rb.gy/qn68ku.