Tropical Cyclone Detection from the Thermal Infrared Sensor IASI Data Using the Deep Learning Model YOLOv3
International audience Tropical cyclone (TC) detection is essential to mitigate natural disasters, as TCs can cause significant damage to life, infrastructure and economy. In this study, we applied the deep learning object detection model YOLOv3 to detect TCs in the North Atlantic Basin, using data...
Published in: | Atmosphere |
---|---|
Main Authors: | , , , , , |
Other Authors: | , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
HAL CCSD
2023
|
Subjects: | |
Online Access: | https://insu.hal.science/insu-03955381 https://insu.hal.science/insu-03955381/document https://insu.hal.science/insu-03955381/file/atmosphere-14-00215.pdf https://doi.org/10.3390/atmos14020215 |
id |
ftsorbonneuniv:oai:HAL:insu-03955381v1 |
---|---|
record_format |
openpolar |
spelling |
ftsorbonneuniv:oai:HAL:insu-03955381v1 2024-05-19T07:45:16+00:00 Tropical Cyclone Detection from the Thermal Infrared Sensor IASI Data Using the Deep Learning Model YOLOv3 Lam, Lisa George, Maya Gardoll, Sébastien Safieddine, Sarah Whitburn, Simon Clerbaux, Cathy TROPO - LATMOS Laboratoire Atmosphères, Milieux, Observations Spatiales (LATMOS) Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS) Institut Pierre-Simon-Laplace (IPSL (FR_636)) École normale supérieure - Paris (ENS-PSL) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-École polytechnique (X)-Centre National d'Études Spatiales Toulouse (CNES)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité) Spectroscopy, Quantum Chemistry and Atmospheric Remote Sensing (SQUARES) Université libre de Bruxelles (ULB) 2023-01-19 https://insu.hal.science/insu-03955381 https://insu.hal.science/insu-03955381/document https://insu.hal.science/insu-03955381/file/atmosphere-14-00215.pdf https://doi.org/10.3390/atmos14020215 en eng HAL CCSD MDPI info:eu-repo/semantics/altIdentifier/doi/10.3390/atmos14020215 insu-03955381 https://insu.hal.science/insu-03955381 https://insu.hal.science/insu-03955381/document https://insu.hal.science/insu-03955381/file/atmosphere-14-00215.pdf doi:10.3390/atmos14020215 http://creativecommons.org/licenses/by-nc/ info:eu-repo/semantics/OpenAccess ISSN: 2073-4433 EISSN: 2073-4433 Atmosphere https://insu.hal.science/insu-03955381 Atmosphere, 2023, 14 (2), pp.215. ⟨10.3390/atmos14020215⟩ tropical cyclone machine learning deep learning convolutional neural networks autoencoder IASI [SDU.STU.ME]Sciences of the Universe [physics]/Earth Sciences/Meteorology [SDU.STU.CL]Sciences of the Universe [physics]/Earth Sciences/Climatology info:eu-repo/semantics/article Journal articles 2023 ftsorbonneuniv https://doi.org/10.3390/atmos14020215 2024-04-25T03:48:50Z International audience Tropical cyclone (TC) detection is essential to mitigate natural disasters, as TCs can cause significant damage to life, infrastructure and economy. In this study, we applied the deep learning object detection model YOLOv3 to detect TCs in the North Atlantic Basin, using data from the Thermal InfraRed (TIR) Atmospheric Sounding Interferometer (IASI) onboard the Metop satellites. IASI measures the outgoing TIR radiation of the Earth-Atmosphere. For the first time, we provide a proof of concept of the possibility of constructing images required by YOLOv3 from a TIR remote sensor that is not an imager. We constructed a dataset by selecting 50 IASI radiance channels and using them to create images, which we labeled by constructing bounding boxes around TCs using the hurricane database HURDAT2. We trained the YOLOv3 on two settings, first with three "best" selected channels, then using an autoencoder to exploit all 50 channels. We assessed its performance with the Average Precision (AP) metric at two different intersection over union (IoU) thresholds (0.1 and 0.5). The model achieved promising results with AP at IoU threshold 0.1 of 78.31%. Lower performance was achieved with IoU threshold 0.5 (31.05%), showing the model lacks precision regarding the size and position of the predicted boxes. Despite that, we show YOLOv3 demonstrates great potential for TC detection using TIR instruments data. Article in Journal/Newspaper North Atlantic HAL Sorbonne Université Atmosphere 14 2 215 |
institution |
Open Polar |
collection |
HAL Sorbonne Université |
op_collection_id |
ftsorbonneuniv |
language |
English |
topic |
tropical cyclone machine learning deep learning convolutional neural networks autoencoder IASI [SDU.STU.ME]Sciences of the Universe [physics]/Earth Sciences/Meteorology [SDU.STU.CL]Sciences of the Universe [physics]/Earth Sciences/Climatology |
spellingShingle |
tropical cyclone machine learning deep learning convolutional neural networks autoencoder IASI [SDU.STU.ME]Sciences of the Universe [physics]/Earth Sciences/Meteorology [SDU.STU.CL]Sciences of the Universe [physics]/Earth Sciences/Climatology Lam, Lisa George, Maya Gardoll, Sébastien Safieddine, Sarah Whitburn, Simon Clerbaux, Cathy Tropical Cyclone Detection from the Thermal Infrared Sensor IASI Data Using the Deep Learning Model YOLOv3 |
topic_facet |
tropical cyclone machine learning deep learning convolutional neural networks autoencoder IASI [SDU.STU.ME]Sciences of the Universe [physics]/Earth Sciences/Meteorology [SDU.STU.CL]Sciences of the Universe [physics]/Earth Sciences/Climatology |
description |
International audience Tropical cyclone (TC) detection is essential to mitigate natural disasters, as TCs can cause significant damage to life, infrastructure and economy. In this study, we applied the deep learning object detection model YOLOv3 to detect TCs in the North Atlantic Basin, using data from the Thermal InfraRed (TIR) Atmospheric Sounding Interferometer (IASI) onboard the Metop satellites. IASI measures the outgoing TIR radiation of the Earth-Atmosphere. For the first time, we provide a proof of concept of the possibility of constructing images required by YOLOv3 from a TIR remote sensor that is not an imager. We constructed a dataset by selecting 50 IASI radiance channels and using them to create images, which we labeled by constructing bounding boxes around TCs using the hurricane database HURDAT2. We trained the YOLOv3 on two settings, first with three "best" selected channels, then using an autoencoder to exploit all 50 channels. We assessed its performance with the Average Precision (AP) metric at two different intersection over union (IoU) thresholds (0.1 and 0.5). The model achieved promising results with AP at IoU threshold 0.1 of 78.31%. Lower performance was achieved with IoU threshold 0.5 (31.05%), showing the model lacks precision regarding the size and position of the predicted boxes. Despite that, we show YOLOv3 demonstrates great potential for TC detection using TIR instruments data. |
author2 |
TROPO - LATMOS Laboratoire Atmosphères, Milieux, Observations Spatiales (LATMOS) Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS) Institut Pierre-Simon-Laplace (IPSL (FR_636)) École normale supérieure - Paris (ENS-PSL) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-École polytechnique (X)-Centre National d'Études Spatiales Toulouse (CNES)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité) Spectroscopy, Quantum Chemistry and Atmospheric Remote Sensing (SQUARES) Université libre de Bruxelles (ULB) |
format |
Article in Journal/Newspaper |
author |
Lam, Lisa George, Maya Gardoll, Sébastien Safieddine, Sarah Whitburn, Simon Clerbaux, Cathy |
author_facet |
Lam, Lisa George, Maya Gardoll, Sébastien Safieddine, Sarah Whitburn, Simon Clerbaux, Cathy |
author_sort |
Lam, Lisa |
title |
Tropical Cyclone Detection from the Thermal Infrared Sensor IASI Data Using the Deep Learning Model YOLOv3 |
title_short |
Tropical Cyclone Detection from the Thermal Infrared Sensor IASI Data Using the Deep Learning Model YOLOv3 |
title_full |
Tropical Cyclone Detection from the Thermal Infrared Sensor IASI Data Using the Deep Learning Model YOLOv3 |
title_fullStr |
Tropical Cyclone Detection from the Thermal Infrared Sensor IASI Data Using the Deep Learning Model YOLOv3 |
title_full_unstemmed |
Tropical Cyclone Detection from the Thermal Infrared Sensor IASI Data Using the Deep Learning Model YOLOv3 |
title_sort |
tropical cyclone detection from the thermal infrared sensor iasi data using the deep learning model yolov3 |
publisher |
HAL CCSD |
publishDate |
2023 |
url |
https://insu.hal.science/insu-03955381 https://insu.hal.science/insu-03955381/document https://insu.hal.science/insu-03955381/file/atmosphere-14-00215.pdf https://doi.org/10.3390/atmos14020215 |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_source |
ISSN: 2073-4433 EISSN: 2073-4433 Atmosphere https://insu.hal.science/insu-03955381 Atmosphere, 2023, 14 (2), pp.215. ⟨10.3390/atmos14020215⟩ |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.3390/atmos14020215 insu-03955381 https://insu.hal.science/insu-03955381 https://insu.hal.science/insu-03955381/document https://insu.hal.science/insu-03955381/file/atmosphere-14-00215.pdf doi:10.3390/atmos14020215 |
op_rights |
http://creativecommons.org/licenses/by-nc/ info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.3390/atmos14020215 |
container_title |
Atmosphere |
container_volume |
14 |
container_issue |
2 |
container_start_page |
215 |
_version_ |
1799485271850352640 |