A New Machine Learning Algorithm for Numerical Prediction of Near-Earth Environment Sensors along the Inland of East Antarctica
Accurate short-term small-area meteorological forecasts are essential to ensure the safety of operations and equipment operations in the Antarctic interior. This study proposes a deep learning-based multi-input neural network model to address this problem. The newly proposed model is predicted by co...
Published in: | Sensors |
---|---|
Main Authors: | , , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/s21030755 |
id |
ftmdpi:oai:mdpi.com:/1424-8220/21/3/755/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/1424-8220/21/3/755/ 2023-08-20T04:00:16+02:00 A New Machine Learning Algorithm for Numerical Prediction of Near-Earth Environment Sensors along the Inland of East Antarctica Yuchen Wang Yinke Dou Wangxiao Yang Jingxue Guo Xiaomin Chang Minghu Ding Xueyuan Tang 2021-01-23 application/pdf https://doi.org/10.3390/s21030755 EN eng Multidisciplinary Digital Publishing Institute Remote Sensors https://dx.doi.org/10.3390/s21030755 https://creativecommons.org/licenses/by/4.0/ Sensors; Volume 21; Issue 3; Pages: 755 neural network East Antarctica multi-sensor LSTM Text 2021 ftmdpi https://doi.org/10.3390/s21030755 2023-08-01T00:55:30Z Accurate short-term small-area meteorological forecasts are essential to ensure the safety of operations and equipment operations in the Antarctic interior. This study proposes a deep learning-based multi-input neural network model to address this problem. The newly proposed model is predicted by combining a stacked autoencoder and a long- and short-term memory network. The self-stacking autoencoder maximises the features and removes redundancy from the target weather station’s sensor data and extracts temporal features from the sensor data using a long- and short-term memory network. The proposed new model evaluates the prediction performance and generalisation capability at four observation sites at different East Antarctic latitudes (including the Antarctic maximum and the coastal region). The performance of five deep learning networks is compared through five evaluation metrics, and the optimal form of input combination is discussed. The results show that the prediction capability of the model outperforms the other models. It provides a new method for short-term meteorological prediction in a small inland Antarctic region. Text Antarc* Antarctic Antarctica East Antarctica MDPI Open Access Publishing Antarctic East Antarctica The Antarctic Sensors 21 3 755 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
neural network East Antarctica multi-sensor LSTM |
spellingShingle |
neural network East Antarctica multi-sensor LSTM Yuchen Wang Yinke Dou Wangxiao Yang Jingxue Guo Xiaomin Chang Minghu Ding Xueyuan Tang A New Machine Learning Algorithm for Numerical Prediction of Near-Earth Environment Sensors along the Inland of East Antarctica |
topic_facet |
neural network East Antarctica multi-sensor LSTM |
description |
Accurate short-term small-area meteorological forecasts are essential to ensure the safety of operations and equipment operations in the Antarctic interior. This study proposes a deep learning-based multi-input neural network model to address this problem. The newly proposed model is predicted by combining a stacked autoencoder and a long- and short-term memory network. The self-stacking autoencoder maximises the features and removes redundancy from the target weather station’s sensor data and extracts temporal features from the sensor data using a long- and short-term memory network. The proposed new model evaluates the prediction performance and generalisation capability at four observation sites at different East Antarctic latitudes (including the Antarctic maximum and the coastal region). The performance of five deep learning networks is compared through five evaluation metrics, and the optimal form of input combination is discussed. The results show that the prediction capability of the model outperforms the other models. It provides a new method for short-term meteorological prediction in a small inland Antarctic region. |
format |
Text |
author |
Yuchen Wang Yinke Dou Wangxiao Yang Jingxue Guo Xiaomin Chang Minghu Ding Xueyuan Tang |
author_facet |
Yuchen Wang Yinke Dou Wangxiao Yang Jingxue Guo Xiaomin Chang Minghu Ding Xueyuan Tang |
author_sort |
Yuchen Wang |
title |
A New Machine Learning Algorithm for Numerical Prediction of Near-Earth Environment Sensors along the Inland of East Antarctica |
title_short |
A New Machine Learning Algorithm for Numerical Prediction of Near-Earth Environment Sensors along the Inland of East Antarctica |
title_full |
A New Machine Learning Algorithm for Numerical Prediction of Near-Earth Environment Sensors along the Inland of East Antarctica |
title_fullStr |
A New Machine Learning Algorithm for Numerical Prediction of Near-Earth Environment Sensors along the Inland of East Antarctica |
title_full_unstemmed |
A New Machine Learning Algorithm for Numerical Prediction of Near-Earth Environment Sensors along the Inland of East Antarctica |
title_sort |
new machine learning algorithm for numerical prediction of near-earth environment sensors along the inland of east antarctica |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/s21030755 |
geographic |
Antarctic East Antarctica The Antarctic |
geographic_facet |
Antarctic East Antarctica The Antarctic |
genre |
Antarc* Antarctic Antarctica East Antarctica |
genre_facet |
Antarc* Antarctic Antarctica East Antarctica |
op_source |
Sensors; Volume 21; Issue 3; Pages: 755 |
op_relation |
Remote Sensors https://dx.doi.org/10.3390/s21030755 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/s21030755 |
container_title |
Sensors |
container_volume |
21 |
container_issue |
3 |
container_start_page |
755 |
_version_ |
1774717346444738560 |