Hybrid GRU–Random Forest Model for Accurate Atmospheric Duct Detection with Incomplete Sounding Data

Atmospheric data forecasting traditionally relies on physical models, which simulate atmospheric motion and change by solving atmospheric dynamics, thermodynamics, and radiative transfer processes. However, numerical models often involve significant computational demands and time constraints. In thi...

Full description

Saved in:
Bibliographic Details
Main Authors: Yi Yan, Linjing Guo, Jiangting Li, Zhouxiang Yu, Shuji Sun, Tong Xu, Haisheng Zhao, Lixin Guo
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/22/4308
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267115713462272
author Yi Yan
Linjing Guo
Jiangting Li
Zhouxiang Yu
Shuji Sun
Tong Xu
Haisheng Zhao
Lixin Guo
author_facet Yi Yan
Linjing Guo
Jiangting Li
Zhouxiang Yu
Shuji Sun
Tong Xu
Haisheng Zhao
Lixin Guo
author_sort Yi Yan
collection DOAJ
description Atmospheric data forecasting traditionally relies on physical models, which simulate atmospheric motion and change by solving atmospheric dynamics, thermodynamics, and radiative transfer processes. However, numerical models often involve significant computational demands and time constraints. In this study, we analyze the performance of Gated Recurrent Units (GRU) and Long Short-Term Memory networks (LSTM) using over two decades of sounding data from the Xisha Island Observatory in the South China Sea. We propose a hybrid model that combines GRU and Random Forest (RF) in series, which predicts the presence of atmospheric ducts from limited data. The results demonstrate that GRU achieves prediction accuracy comparable to LSTM with 10% to 20% shorter running times. The prediction accuracy of the GRU-RF model reaches 0.92. This model effectively predicts the presence of atmospheric ducts in certain height regions, even with low data accuracy or missing data, highlighting its potential for improving efficiency in atmospheric forecasting.
format Article
id doaj-art-bfdc677fe53c49c0b103cd07b83b9e13
institution OA Journals
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-bfdc677fe53c49c0b103cd07b83b9e132025-08-20T01:53:56ZengMDPI AGRemote Sensing2072-42922024-11-011622430810.3390/rs16224308Hybrid GRU–Random Forest Model for Accurate Atmospheric Duct Detection with Incomplete Sounding DataYi Yan0Linjing Guo1Jiangting Li2Zhouxiang Yu3Shuji Sun4Tong Xu5Haisheng Zhao6Lixin Guo7School of Physics, Xidian University, Xi’an 710071, ChinaSchool of Physics, Xidian University, Xi’an 710071, ChinaSchool of Physics, Xidian University, Xi’an 710071, ChinaSchool of Physics, Xidian University, Xi’an 710071, ChinaChina Institute of Radio Wave Propagation, Qingdao 266107, ChinaChina Institute of Radio Wave Propagation, Qingdao 266107, ChinaChina Institute of Radio Wave Propagation, Qingdao 266107, ChinaSchool of Physics, Xidian University, Xi’an 710071, ChinaAtmospheric data forecasting traditionally relies on physical models, which simulate atmospheric motion and change by solving atmospheric dynamics, thermodynamics, and radiative transfer processes. However, numerical models often involve significant computational demands and time constraints. In this study, we analyze the performance of Gated Recurrent Units (GRU) and Long Short-Term Memory networks (LSTM) using over two decades of sounding data from the Xisha Island Observatory in the South China Sea. We propose a hybrid model that combines GRU and Random Forest (RF) in series, which predicts the presence of atmospheric ducts from limited data. The results demonstrate that GRU achieves prediction accuracy comparable to LSTM with 10% to 20% shorter running times. The prediction accuracy of the GRU-RF model reaches 0.92. This model effectively predicts the presence of atmospheric ducts in certain height regions, even with low data accuracy or missing data, highlighting its potential for improving efficiency in atmospheric forecasting.https://www.mdpi.com/2072-4292/16/22/4308atmospheric data forecastingGRULSTMRFatmospheric duct prediction
spellingShingle Yi Yan
Linjing Guo
Jiangting Li
Zhouxiang Yu
Shuji Sun
Tong Xu
Haisheng Zhao
Lixin Guo
Hybrid GRU–Random Forest Model for Accurate Atmospheric Duct Detection with Incomplete Sounding Data
Remote Sensing
atmospheric data forecasting
GRU
LSTM
RF
atmospheric duct prediction
title Hybrid GRU–Random Forest Model for Accurate Atmospheric Duct Detection with Incomplete Sounding Data
title_full Hybrid GRU–Random Forest Model for Accurate Atmospheric Duct Detection with Incomplete Sounding Data
title_fullStr Hybrid GRU–Random Forest Model for Accurate Atmospheric Duct Detection with Incomplete Sounding Data
title_full_unstemmed Hybrid GRU–Random Forest Model for Accurate Atmospheric Duct Detection with Incomplete Sounding Data
title_short Hybrid GRU–Random Forest Model for Accurate Atmospheric Duct Detection with Incomplete Sounding Data
title_sort hybrid gru random forest model for accurate atmospheric duct detection with incomplete sounding data
topic atmospheric data forecasting
GRU
LSTM
RF
atmospheric duct prediction
url https://www.mdpi.com/2072-4292/16/22/4308
work_keys_str_mv AT yiyan hybridgrurandomforestmodelforaccurateatmosphericductdetectionwithincompletesoundingdata
AT linjingguo hybridgrurandomforestmodelforaccurateatmosphericductdetectionwithincompletesoundingdata
AT jiangtingli hybridgrurandomforestmodelforaccurateatmosphericductdetectionwithincompletesoundingdata
AT zhouxiangyu hybridgrurandomforestmodelforaccurateatmosphericductdetectionwithincompletesoundingdata
AT shujisun hybridgrurandomforestmodelforaccurateatmosphericductdetectionwithincompletesoundingdata
AT tongxu hybridgrurandomforestmodelforaccurateatmosphericductdetectionwithincompletesoundingdata
AT haishengzhao hybridgrurandomforestmodelforaccurateatmosphericductdetectionwithincompletesoundingdata
AT lixinguo hybridgrurandomforestmodelforaccurateatmosphericductdetectionwithincompletesoundingdata