González, Jorge LópezChapman, TheodoreChen, KathrynNguyen, HannahChambers, LoganMostafa, Seraj Al MahmudWang, JianwuPurushotham, SanjayWang, ChenxiYue, Jia2024-10-282024-10-282022-12González, Jorge López, Theodore Chapman, Kathryn Chen, Hannah Nguyen, Logan Chambers, Seraj A.M. Mostafa, Jianwu Wang, Sanjay Purushotham, Chenxi Wang, and Jia Yue. “Atmospheric Gravity Wave Detection Using Transfer Learning Techniques.” In 2022 IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT), 128–37, 2022. https://doi.org/10.1109/BDCAT56447.2022.00023.https://doi.org/10.1109/BDCAT56447.2022.00023http://hdl.handle.net/11603/367532022 IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT), 06-09 December 2022, Vancouver, WA, USAAtmospheric gravity waves are produced when gravity attempts to restore disturbances through stable layers in the atmosphere. They have a visible effect on many atmospheric phenomena such as global circulation and air turbulence. Despite their importance, however, little research has been conducted on how to detect gravity waves using machine learning algorithms. We faced two major challenges in our research: our raw data had a lot of noise and the labeled dataset was extremely small. In this study, we explored various methods of preprocessing and transfer learning in order to address those challenges. We pre-trained an autoencoder on unlabeled data before training it to classify labeled data. We also created a custom CNN by combining certain pre-trained layers from the InceptionV3 Model trained on ImageNet with custom layers and a custom learning rate scheduler. Experiments show that our best model outperformed the best performing baseline model by 6.36% in terms of test accuracy.10 pagesen-US© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.UMBC Mdeep learningData modelsimage denoisingTransfer learningNoise measurementAtmospheric modelingSatellitesmodel customizationtransfer learningUMBC Big Data Analytics Labatmospheric gravity wavesComputational modelingTrainingText