Open Access
Open access
Remote Sensing, volume 15, issue 14, pages 3493

Towards the Accurate Automatic Detection of Mesoscale Convective Systems in Remote Sensing Data: From Data Mining to Deep Learning Models and Their Applications

Krinitskiy Mikhail 1, 2, 3
, 
Sprygin A. A. 4, 5
, 
Elizarov Svyatoslav 1
, 
Narizhnaya Alexandra 4
, 
Shikhov Andrey 4, 6
, 
Chernokulsky Alexander 4, 7
1
 
2
 
3
 
Moscow Center for Fundamental and Applied Mathematics, Leninskie Gory, 1, Moscow 119991, Russia | 
4
 
5
 
6
 
7
 
Publication type: Journal Article
Publication date: 2023-07-11
Journal: Remote Sensing
Quartile SCImago
Q1
Quartile WOS
Q1
Impact factor: 5
ISSN: 20724292
General Earth and Planetary Sciences
Abstract

Mesoscale convective systems (MCSs) and associated hazardous meteorological phenomena cause considerable economic damage and even loss of lives in the mid-latitudes. The mechanisms behind the formation and intensification of MCSs are still not well understood due to limited observational data and inaccurate climate models. Improving the prediction and understanding of MCSs is a high-priority area in hydrometeorology. One may study MCSs either employing high-resolution atmospheric modeling or through the analysis of remote sensing images which are known to reflect some of the characteristics of MCSs, including high temperature gradients of cloud-top, specific spatial shapes of temperature patterns, etc. However, research on MCSs using remote sensing data is limited by inadequate (in size) databases of satellite-identified MCSs and poorly equipped automated tools for MCS identification and tracking. In this study, we present (a) the GeoAnnotateAssisted tool for fast and convenient visual identification of MCSs in satellite imagery, which is capable of providing AI-generated suggestions of MCS labels; (b) the Dataset of Mesoscale Convective Systems over the European Territory of Russia (DaMesCoS-ETR), which we created using this tool, and (c) the Deep Convolutional Neural Network for the Identification of Mesoscale Convective Systems (MesCoSNet), constructed following the RetinaNet architecture, which is capable of identifying MCSs in Meteosat MSG/SEVIRI data. We demonstrate that our neural network, optimized in terms of its hyperparameters, provides high MCS identification quality (mAP=0.75, true positive rate TPR=0.61) and a well-specified detection uncertainty (false alarm ratio FAR=0.36). Additionally, we demonstrate potential applications of the GeoAnnotateAssisted labelling tool, the DaMesCoS-ETR dataset, and the MesCoSNet neural network in addressing MCS research challenges. Specifically, we present the climatology of axisymmetric MCSs over the European territory of Russia from 2014 to 2020 during summer seasons (May to September), obtained using MesCoSNet with Meteosat MSG/SEVIRI data. The automated identification of MCSs by the MesCoSNet artificial neural network opens up new avenues for previously unattainable MCS research topics.

By date By citations
By date By citations

Citations by journals

1
Remote Sensing
Remote Sensing, 1, 50%
Remote Sensing
1 publication, 50%
Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika)
Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika), 1, 50%
Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika)
1 publication, 50%
1

Citations by publishers

1
Multidisciplinary Digital Publishing Institute (MDPI)
Multidisciplinary Digital Publishing Institute (MDPI), 1, 50%
Multidisciplinary Digital Publishing Institute (MDPI)
1 publication, 50%
Allerton Press, 1, 50%
Allerton Press
1 publication, 50%
1
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Krinitskiy M. et al. Towards the Accurate Automatic Detection of Mesoscale Convective Systems in Remote Sensing Data: From Data Mining to Deep Learning Models and Their Applications // Remote Sensing. 2023. Vol. 15. No. 14. p. 3493.
GOST all authors (up to 50) Copy
Krinitskiy M., Sprygin A. A., Elizarov S., Narizhnaya A., Shikhov A., Chernokulsky A. Towards the Accurate Automatic Detection of Mesoscale Convective Systems in Remote Sensing Data: From Data Mining to Deep Learning Models and Their Applications // Remote Sensing. 2023. Vol. 15. No. 14. p. 3493.
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.3390/rs15143493
UR - https://doi.org/10.3390%2Frs15143493
TI - Towards the Accurate Automatic Detection of Mesoscale Convective Systems in Remote Sensing Data: From Data Mining to Deep Learning Models and Their Applications
T2 - Remote Sensing
AU - Krinitskiy, Mikhail
AU - Sprygin, A. A.
AU - Elizarov, Svyatoslav
AU - Narizhnaya, Alexandra
AU - Shikhov, Andrey
AU - Chernokulsky, Alexander
PY - 2023
DA - 2023/07/11 00:00:00
PB - Multidisciplinary Digital Publishing Institute (MDPI)
SP - 3493
IS - 14
VL - 15
SN - 2072-4292
ER -
BibTex |
Cite this
BibTex Copy
@article{2023_Krinitskiy,
author = {Mikhail Krinitskiy and A. A. Sprygin and Svyatoslav Elizarov and Alexandra Narizhnaya and Andrey Shikhov and Alexander Chernokulsky},
title = {Towards the Accurate Automatic Detection of Mesoscale Convective Systems in Remote Sensing Data: From Data Mining to Deep Learning Models and Their Applications},
journal = {Remote Sensing},
year = {2023},
volume = {15},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
month = {jul},
url = {https://doi.org/10.3390%2Frs15143493},
number = {14},
pages = {3493},
doi = {10.3390/rs15143493}
}
MLA
Cite this
MLA Copy
Krinitskiy, Mikhail, et al. “Towards the Accurate Automatic Detection of Mesoscale Convective Systems in Remote Sensing Data: From Data Mining to Deep Learning Models and Their Applications.” Remote Sensing, vol. 15, no. 14, Jul. 2023, p. 3493. https://doi.org/10.3390%2Frs15143493.
Found error?