Automatic Regional Interpretation and Forecasting System Supported by Machine Learning
Open Access
- 21 June 2021
- journal article
- research article
- Published by MDPI AG in Atmosphere
- Vol. 12 (6), 793
- https://doi.org/10.3390/atmos12060793
Abstract
The Model Output Statistics (MOS) model is a dynamic statistical weather forecast model based on multiple linear regression technology. It is greatly affected by the selection of parameters and predictors, especially when the weather changes drastically, or extreme weather occurs. We improved the traditional MOS model with the machine learning method to enhance the capabilities of self-learning and generalization. Simultaneously, multi-source meteorological data were used as the input to the model to improve the data quality. In the experiment, we selected the four areas of Nanjing, Beijing, Chengdu, and Guangzhou for verification, with the numerical weather prediction (NWP) products and observation data from automatic weather stations (AWSs) used to predict the temperature and wind speed in the next 24 h. From the experiment, it can be seen that the accuracy of the prediction values and speed of the method were improved by the ML-MOS. Finally, we compared the ML-MOS model with neural networks and support vector machine (SVM), the results show that the prediction result of the ML-MOS model is better than that of the above two models.Funding Information
- National Natural Science Foundation of China (No. 61371119)
- Blue project of Jiangsu Province. (00000000)
This publication has 8 references indexed in Scilit:
- Subseasonal Forecast Skill over the Northern Polar Region in Boreal WinterJournal of Climate, 2020
- Calibration of Machine Learning–Based Probabilistic Hail Predictions for Operational ForecastingWeather and Forecasting, 2020
- S2S reboot: An argument for greater inclusion of machine learning in subseasonal to seasonal forecastsWires Climate Change, 2018
- Predicting weather forecast uncertainty with machine learningQuarterly Journal of the Royal Meteorological Society, 2018
- Winter Precipitation Forecast in the European and Mediterranean Regions Using Cluster AnalysisGeophysical Research Letters, 2017
- Convolutional LSTM Networks for Subcellular Localization of ProteinsPublished by Springer Science and Business Media LLC ,2015
- Probabilistic Weather Prediction with an Analog EnsembleMonthly Weather Review, 2013
- Computer Forecasts of Maximum and Minimum TemperaturesJournal of Applied Meteorology, 1970