# Automatic Regional Interpretation and Forecasting System Supported by Machine Learning

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

- (1)
- A multi-source meteorological data processing method based on accurate and meticulous interpolation of grid data and data regionalization is proposed.
- (2)
- Two types of automatic regional interpretation and forecasting models under holonomic and non-holonomic subsets are designed.

## 2. Preliminary Knowledge

#### 2.1. MOS Model Principle

#### 2.2. ML-MOS Model

## 3. ML-MOS Model Design and Implementation

#### 3.1. Multi-Source Meteorological Data Processing Method

#### 3.1.1. Accurate and Meticulous Interpolation of Grid Data

**Definition 1.**

**Definition 2.**

#### 3.1.2. Accurate and Meticulous Interpolation of Grid Data

#### 3.2. Two Types of Automatic Regional Interpretation and Forecasting Models

#### 3.2.1. Regional Forecast under the Condition of Holonomic Factor Subset

#### 3.2.2. Regional Forecast under the Condition of Non-Holonomic Factor Subset

#### 3.3. Two Types of Automatic Regional Interpretation and Forecasting Models

## 4. Experiment and Analysis

#### 4.1. Data Source and Preprocessing

- (1)
- Default data processing of the AWSs. In the AWS observation data, due to abnormal problems such as equipment and data transmission links, the data at some moments were missing. We used the time series of the input data, based on the data correlation of the previous and next moments, and used the median padding to fill in the default data.
- (2)
- Normalized input elements: Since the dimensions of each element are not consistent, such as pressure measured in hPa, east–west wind (U) measured in m/s, and 2 m temperature measured in °C, inputting unnormalized data directly into the ML-MOS model will adversely affect the generalization ability of the model. We normalized each element separately to solve the problem of incomparability caused by dimensionless disunity among the elements.

#### 4.2. ML-MOS Model Training and Evaluation

#### 4.3. Experimental Results and Analysis

#### 4.3.1. Parameter Selection

#### 4.3.2. Results and Analysis

- (1)
- Neural networks

- (2)
- SVM

## 5. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Jian, S.; Zhuo, C.; Li, H.; Simeng, Q.; Xin, W.; Limin, Y.; Wei, X. Application of Artificial Intelligence Technology to Numerical Weather Prediction. J. Appl. Meteorol. Sci.
**2021**, 32, 1–11. [Google Scholar] - Gedzelman, S. Calculating the Weather: Meteorology in the 20th Century. (book reviews). J. R. Soc. Med.
**1992**, 85, 271–273. [Google Scholar] - Huan-zhu, L.; Shen-rong, Z.; Zhi-shan, L.; Cui-guang, Z.; Yuan-qin, Y.; Yu-hua, L. Objective Element Forecasts at NMC—A MOS System. J. Appl. Meteorol. Sci.
**2004**, 2, 181–191. [Google Scholar] - Dai, K.; Zhu, J.Y.; Bi, B.G. The Review of Statistical Post-process Technologies for Quantitative Precipitation Forecast of Ensemble Prediction System. Acta Meteorol. Sin.
**2018**, 76, 493–510. [Google Scholar] - Chunxiang, S.; Yang, P.; Junxia, G.; Bin, X.; Shuai, H.; Zhi, Z.; Lei, Z.; Shuai, S.; Zhiwei, J. A Review of Multi-source Meteorological Data Fusion Products. Acta Meteorol. Sin.
**2019**, 77, 774–783. [Google Scholar] - Ghaderi, A.; Sanandaji, B.; Ghaderi, F. Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting. arXiv
**2017**, arXiv:1707.08110. [Google Scholar] - Hernández, E.; Sanchez-Anguix, V.; Julian, V.; Palanca, J.; Duque, N. Rainfall Prediction: A Deep Learning Approach. In Proceedings of the International Conference on Hybrid Artificial Intelligence Systems, Seville, Spain, 18–20 April 2016. [Google Scholar]
- Shi, X.J.; Chen, Z.R.; Wang, H.; Yeung, D.-Y.; Wong, W.-K.; Woo, W.-C. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. Proc. NIPS
**2015**. [Google Scholar] [CrossRef] [Green Version] - Totz, S.; Tziperman, E.; Coumou, D.; Pfeiffer, K.; Cohen, J. Winter Precipitation Forecast in the European and Mediterranean Regions Using Cluster Analysis. Geophys. Res. Lett.
**2017**, 44, 12418–12426. [Google Scholar] [CrossRef] [Green Version] - Cohen, J.; Coumou, D.; Hwang, J.; Mackey, L.; Orenstein, P.; Totz, S.; Tziperman, E. S2S reboot: An argument for Greater Inclusion of Machine Learning in Subseasonal to Seasonal Forecasts. WIREs Clim. Chang.
**2019**, 10, e00567. [Google Scholar] [CrossRef] [Green Version] - Racah, E.; Beckham, C.; Maharaj, T.; Kahou, S.E.; Prabhat; Pal, C. ExtremeWeather: A Large-scale Climate Dataset for Semi-supervised Detection, Localization, and Understanding of Extreme Weather Events. arXiv
**2017**, arXiv:1612.02095. [Google Scholar] - Lin, H. Subseasonal Forecast Skill over the Northern Polar Region in Boreal Winter. J. Clim.
**2020**, 33, 1935–1951. [Google Scholar] [CrossRef] - Amanda, B.; Nathan, S.; Gagne, D.J., II; McCorkle, S.; McGovern, A. Calibration of Machine Learning–Based Probabilistic Hail Predictions for Operational Forecasting. Weather Forecast.
**2020**, 35, 149–168. [Google Scholar] - Scher, S.; Messori, G. Predicting weather forecast uncertainty with machine learning. Q. J. R. Meteorol. Soc.
**2018**, 144, 2830–2841. [Google Scholar] [CrossRef] - Klein, W.H.; Lewis, F. Computer forecasts of maximum and minimum temperatures. J. Appl. Meteor.
**1970**, 9, 350–359. [Google Scholar] [CrossRef] [Green Version] - Congwu, H.; Baozhang, C.; Chaoqun, M.; Tijian, W. WRF-CMAQ-MOS Studies Based on Extremely Randomized Trees. Acta Meteorol. Sin.
**2018**, 76, 779–789. [Google Scholar] - Di, C.; Yu-ying, C.; Jin-ren, M.; Jing-xin, N.; Qiang, L. Influence of MOS Methods of Different Time Scale on Temperature Forecast in Ningxia. Arid Land Geogr.
**2019**, 42, 94–102. [Google Scholar] - Xiao, Q.Y.; Hu, F.; Fang, S.J. Model Output Statistics and Wind Power Numerical Prediction. Resour. Sci.
**2017**, 39, 116–124. [Google Scholar] - Fang, K.N.; Wu, J.B.; Zhu, J.P. A Review of Technologies on Random Forests. Stat. Inf. Forum
**2011**, 3, 32–38. [Google Scholar] - Delle Monache, L.; Eckel, F.A.; Rife, D.L.; Nagarajan, B.; Searight, K. Probabilistic Weather Prediction with an Analog Ensemble. Mon. Weather Rev.
**2013**, 141, 3498–3516. [Google Scholar] [CrossRef] [Green Version]

**Figure 8.**Comparison of actual and predicted values of Nanjing area (

**a**) T

_{max}, (

**b**) T

_{min}and (

**c**) W

_{max}.

**Figure 10.**Comparison of the prediction results of (

**a**) T

_{max}, (

**b**) T

_{min}and (

**c**) W

_{max}with different models.

Source | Type | Name |
---|---|---|

NWP (ECMWF, GRAPES_GFS) | Atmospheric surface elements | Pressure |

Accumulated precipitation in 3 h | ||

Low cloud cover | ||

Total cloud cover | ||

East–west Wind (U) | ||

North–south wind (V) | ||

2 m temperature | ||

Dew-point temperature | ||

Barometric elements | Pressure | |

Temperature | ||

Dew-point temperature | ||

East–west Wind (U) | ||

North–south wind (V) | ||

Geopotential height | ||

Automatic weather station | Observation elements | Pressure |

2 m temperature | ||

2 m humidity | ||

10 m wind speed | ||

Wind direction | ||

Accumulated precipitation in 1 h | ||

Model label | The highest temperature of the day | |

The lowest temperature of the day | ||

The maximum wind speed of the day |

**Table 2.**The RMSE and MAE values corresponding to Nanjing, Beijing, Chengdu, and Guangzhou (holonomic factor subset).

City | T_{max} (°C) | T_{min} (°C) | W_{max} (m/s) | |||
---|---|---|---|---|---|---|

RMSE | MAE | RMSE | MAE | RMSE | MAE | |

Nanjing | 1.75 | 1.43 | 2.02 | 1.81 | 0.48 | 0.42 |

Beijing | 1.62 | 1.52 | 1.68 | 1.42 | 0.42 | 0.38 |

Chengdu | 1.73 | 1.34 | 1.53 | 1.37 | 0.32 | 0.33 |

Guangzhou | 1.65 | 1.41 | 1.62 | 1.40 | 0.39 | 0.36 |

Models | T_{max} (°C) | T_{min} (°C) | W_{max} (m/s) | |||
---|---|---|---|---|---|---|

RMSE | MAE | RMSE | MAE | RMSE | MAE | |

MOS | 3.33 | 2.98 | 3.38 | 2.76 | 0.59 | 0.63 |

Neural Networks | 3.23 | 2.84 | 3.40 | 2.87 | 0.58 | 0.61 |

SVM | 3.41 | 2.92 | 3.04 | 2.76 | 0.64 | 0.68 |

ML-MOS | 1.75 | 1.43 | 2.02 | 1.81 | 0.48 | 0.42 |

**Table 4.**The RMSE and MAE values corresponding to Nanjing, Beijing, Chengdu, and Guangzhou (non-holonomic factor subset).

City | T_{max} (°C) | T_{min} (°C) | W_{max} (m/s) | |||
---|---|---|---|---|---|---|

RMSE | MAE | RMSE | MAE | RMSE | MAE | |

Nanjing | 2.04 | 1.81 | 1.72 | 1.33 | 0.59 | 0.61 |

Beijing | 2.32 | 2.03 | 2.12 | 1.91 | 0.56 | 0.58 |

Chengdu | 2.95 | 2.59 | 1.98 | 1.79 | 0.47 | 0.44 |

Guangzhou | 2.46 | 2.14 | 2.63 | 2.36 | 0.51 | 0.48 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Yan, C.; Feng, J.; Xia, K.; Duan, C.
Automatic Regional Interpretation and Forecasting System Supported by Machine Learning. *Atmosphere* **2021**, *12*, 793.
https://doi.org/10.3390/atmos12060793

**AMA Style**

Yan C, Feng J, Xia K, Duan C.
Automatic Regional Interpretation and Forecasting System Supported by Machine Learning. *Atmosphere*. 2021; 12(6):793.
https://doi.org/10.3390/atmos12060793

**Chicago/Turabian Style**

Yan, Chao, Jing Feng, Kaiwen Xia, and Chaofan Duan.
2021. "Automatic Regional Interpretation and Forecasting System Supported by Machine Learning" *Atmosphere* 12, no. 6: 793.
https://doi.org/10.3390/atmos12060793