A New Machine Learning Algorithm for Numerical Prediction of Near-Earth Environment Sensors along the Inland of East Antarctica
Open Access
- 23 January 2021
- Vol. 21 (3), 755
- https://doi.org/10.3390/s21030755
Abstract
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.Keywords
Funding Information
- National Key Research and Development Program of China (2018YFB1307504)
This publication has 25 references indexed in Scilit:
- Full-Scale Maneuvering Trials Correction and Motion Modelling Based on Actual Sea and Weather ConditionsSensors, 2020
- Novel calibration method for camera array in spherical arrangementSignal Processing: Image Communication, 2019
- Antarctic Verification of the Australian Numerical Weather Prediction ModelWeather and Forecasting, 2019
- Data Stream Mining Applied to Maximum Wind Forecasting in the Canary IslandsSensors, 2019
- Machine Learning for Long Cycle Maintenance Prediction of Wind TurbineSensors, 2019
- Application of Convolutional Long Short-Term Memory Neural Networks to Signals Collected from a Sensor Network for Autonomous Gas Source Localization in Outdoor EnvironmentsSensors, 2018
- Small UAS-Based Wind Feature Identification System Part 1: Integration and ValidationSensors, 2016
- Comparison between M5′ model tree and neural networks for prediction of significant wave height in Lake SuperiorOcean Engineering, 2009
- Towards ice-core-based synoptic reconstructions of west antarctic climate with artificial neural networksInternational Journal of Climatology, 2005
- A 15‐year West Antarctic climatology from six automatic weather station temperature and pressure recordsJournal of Geophysical Research: Atmospheres, 2004