# Research on a Rainfall Prediction Model in Guizhou Based on Raindrop Spectra

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Data Sources

#### 2.1. Spectral Parameter Calculation

#### 2.1.1. Data Quality and Methods

^{−3}mm

^{−1}, and is calculated as follows,

_{ij}represents the number of particles in i-th diameter bin and the number of particles in the j-th velocity bin; A is the sampling base area of RSD, equalling to 5400 mm

^{2}; $\Delta T$ is the sampling time 60 s; V

_{j}is the velocity value of the sampled particle in m/s.

#### 2.1.2. Radar Reflectivity Factor

^{6}/m

^{3}, is calculated as follows,

#### 2.1.3. Precipitation Intensity

_{i}represents the diameter of the sampled particle, N(D

_{i}) is the number of particles at the current particle diameter and particle velocity [16].

#### 2.1.4. Average Diameter

#### 2.1.5. Mass-Weighted Average Diameter

#### 2.1.6. Average Volume Diameter

#### 2.1.7. M-P Distribution and GAMMA Distribution

_{0}is in mm

^{−1}m

^{−3}, and the particle scale parameter $\lambda $ is in mm

^{−1}[17].

#### 2.2. Raindrop Size Distribution Analysis

#### 2.2.1. Particles Are Distributed and Proportion

#### 2.2.2. Particle Number Density and Proportion of Precipitation Intensity

#### 2.2.3. Z-I Relationship

#### 2.2.4. Raindrop Size Distribution Fitting

#### 2.2.5. Particle Diameter Fitting

## 3. Neural Networks Predict Precipitation

#### 3.1. Predicting Neural Network Configuration

#### 3.1.1. Prediction Network Structure

#### 3.1.2. Prediction Dataset Construction

_{1}, X

_{2}, X

_{3}…X

_{N}corresponds to Y

_{1}, Y

_{2}, Y

_{3}…Y

_{N}. And the input dataset of the neural network is constructed based on two datasets above. Since precipitation is a continuous process in time and the intensity is also continuously changed. When constructing the dataset need to consider the input feature values to form a continuous time series. However, the prediction value considering the convergence speed and training accuracy of the neural network uses the accumulation of the time series as the input.

#### 3.2. Prediction Result Evaluation

#### 3.2.1. Prediction of Convective Cloud Precipitation Process

#### 3.2.2. Prediction of Stratiform Cloud Precipitation Process

## 4. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Wu, J.-S.; Jin, L.; Nong, J.-F. Forecast Research and Applying of BP Neural Network Based on Genetic Algorithms. Math. Pract. Theory
**2021**, 47, 843–853. [Google Scholar] - Huang, X.; Yin, J.; Ma, L.; Huang, Z. Comprehensive Statistical Analysis of Rain Drop Size Distribution Parameters and Their Application to Weather Radar Measurement in Nanjing. Atmos. Sci.
**2019**, 43, 691–704. [Google Scholar] - Lin, H.-B.; You, Q.-L.; Jiao, Y.; Min, J.-Z. Spatial and Temporal Characteristics of the Precipitation over the Tibetan Plateau from 1961 to 2010 Based on High Resolution Grid-observation Dataset. J. Nat. Resour.
**2015**, 30, 271–281. [Google Scholar] - Shen, G.; Gao, A.; Li, J. Application of Raindrop Spectrum and Dual Polarization Radar Data to a Heavy Rain Process. Meteorological
**2021**, 47, 737–745. [Google Scholar] - Cai, Z.; Liu, J.; Liao, A.; Liao, M.; Liu, H.; Wang, H.; Ma, T.; Zhuo, P. Analysis of characteristics of raindrops based on distrometers. J. Adv. Sci. Technol. Water Resour.
**2021**, 41, 93–98. [Google Scholar] - Zeng, G.; Guo, Z.; Zhou, Q.; Zhang, H.; Chen, X.; Guo, J. Application evaluation of dual polarization radar quantitative precipitation estimation algorithm based on laser raindrop spectrum. Meteorol. Res. Appl.
**2021**, 42, 95–100. [Google Scholar] - Zea, L.R.; Nesbitt, S.W.; Ladino, A.; Hardin, J.C.; Varble, A. Raindrop Size Spectrum in Deep Convective Regions of the Americas. Atmosphere
**2021**, 12, 979. [Google Scholar] [CrossRef] - Mercier, F.; Chazottes, A.; Barthès, L.; Mallet, C. 4-D-VAR assimilation of disdrometer data and radar spectral reflectivities for raindrop size distribution and vertical wind retrievals. Atmos. Meas. Tech.
**2016**, 9, 3145–3163. [Google Scholar] [CrossRef] - Zhu, P.; Li, S.; Xiao, J.; Xu, L.; Jin, S. Study on Extrapolation Technique of Weather Radar Echo and lts Application to Nowcasting. Meteorological
**2008**, 34, 3–9. [Google Scholar] - Liu, G.; Tang, Y.; Ban, R.; Lu, X.; Deng, R.; Huang, F.; Yang, Y. Brief Discuss on the conceptual model forecasting tool of the Maximum and minimum temperatures Sudden change. Meteorol. Res. Appl.
**2009**, 30, 22–24+108. [Google Scholar] - Cheng, C.; Chen, M.; Wang, J.; Cao, F.; Yang, H. Short-term quantitative precipitation forecastexperiments based on blending of nowcasting with numerical weather prediction. Acta Meteorol. Sin.
**2013**, 71, 397–415. [Google Scholar] - Elshaboury, N.; Elshourbagy, M.; Al-Sakkaf, A.; Abdelkader, E.M. Rainfall forecasting in arid regions using an ensemble of artificial neural networks. J. Phys. Conf. Ser.
**2021**, 1900, 012015. [Google Scholar] [CrossRef] - Sharadqah, S.; Mansour, A.M.; Obeidat, M.A.; Marbello, R.; Perez, S.M. Nonlinear Rainfall Yearly Prediction based on Autoregressive Artificial Neural Networks Model in Central Jordan using Data Records, 1938–2018. Int. J. Adv. Comput. Sci. Appl.
**2021**, 12, 240–247. [Google Scholar] [CrossRef] - Gunathilake, M.B.; Senerath, T.; Rathnayake, U. Artificial neural network based PERSIANN data sets in evaluation of hydrologic utility of precipitation estimations in a tropical watershed of Sri Lanka. AIMS Geosci.
**2021**, 7, 478–489. [Google Scholar] [CrossRef] - Zhang, S.; Wei, Z.-Y.; Zhang, Y.-B. Forecasting Rainfall with Recurrent Neural Network. Water-Sav. Irrig.
**2017**, 5, 63–66+71. [Google Scholar] - Pruppacher, H.R.; Klett, J.D.; Wang, P.K. Microphysics of Clouds and Precipitation; Springer: Berlin/Heidelberg, Germany, 1998. [Google Scholar]
- Marshall, J.S.; Palmer, W.M.K. The Distribution of Raindrops with Size. J. Atmos. Sci.
**1948**, 5, 165–166. [Google Scholar] [CrossRef] - Ulbrich, C.W. Natural variations in the analytical form of the raindrop size distribution. J. Clim. Appl. Meteorol.
**1983**, 22, 1764–1775. [Google Scholar] [CrossRef]

**Figure 2.**Particle distribution (

**a**) Dafang (57708) Station, (

**b**) Majiang (57828) Station, (

**c**) Luodian (57916) Station.

**Figure 5.**Average RSD, M-P distribution and Gamma distribution fitting ((

**a**) Dafang (57708) Station (

**b**) Majiang (57828) Station (

**c**) Luodian (57916) Station).

**Figure 7.**Mass-weighted average diameter and average volume diameter change with precipitation intensity.

**Figure 11.**Real-time prediction of convective cloud precipitation process by neural network ((

**a**) 6 min, (

**b**)18 min, (

**c**) 30 min, (

**d**) 60 min, (

**e**) 90 min, (

**f**) 120 min).

**Figure 12.**Real-time prediction of stratiform cloud precipitation process by neural network ((

**a**) 6 min (

**b**) 18 min (

**c**) 30 min (

**d**) 60 min (

**e**) 90 min (

**f**) 120 min).

Site Number | Site Name | Geographic Coordinates | Altitude |
---|---|---|---|

57708 | Dafang | 105.60° E, 27.13° N | 1722.7 m |

57828 | Majang | 107.58° E, 26.50° N | 985.0 m |

57916 | Luodian | 106.76° E, 25.43° N | 441.5 m |

Data | Status | Starting Time | Deadline | Number of Samples |
---|---|---|---|---|

Raindrop spectrometer Weather radar Automatic rain gauge | train | 15 April 2019 0:00/ 3 March 2020 0:04 | 17 July 2019 23:58/ 30 June 2020 23:57 | 49,297 |

inspect | 1 July 2020 0:03 | 16 August 2020 06:05 | 12,126 |

Feature Value | Estimated Values |
---|---|

Radar reflectance intensity (layer 1–3) | A rain gauge measures precipitation |

Particle number density retrieved by RSD | |

Average particle velocity retrieved by RSD | |

Average volume diameter retrieved by RSD |

LSTM Network Parameters | |
---|---|

Activation function | Relu |

Dropout coefficient | 0.5 |

Loss function | Mean Absolute Error |

Dynamic learning rate | Initial learning rate 0.1 |

Patience 50 | |

factor 0.1 | |

Optimizer | Adam |

Training batch size | 32 |

Number of iterations | 2000 |

The test set picks the scale | 20% |

**Table 5.**Prediction and evaluation index of neural network of convective cloud precipitation process.

Neural Networks Prediction Time | Real-Time Correlation Number | MRE | MAE | RMSE |
---|---|---|---|---|

6 min | 0.4763 | 0.6222 | 0.2660 | 0.5807 |

18 min | 0.8617 | 0.5129 | 0.4177 | 0.8843 |

30 min | 0.8874 | 0.5994 | 0.5456 | 1.0824 |

60 min | 0.9287 | 0.3897 | 0.8057 | 1.6419 |

90 min | 0.8203 | 0.4522 | 1.1601 | 2.5705 |

120 min | 0.6061 | 0.4077 | 1.6566 | 3.6103 |

**Table 6.**Prediction and evaluation index of neural network of stratiform cloud precipitation process.

Neural Networks Prediction Time | Real-Time Correlation Number | MRE | MAE | RMSE |
---|---|---|---|---|

6 min | 0.2743 | 0.7921 | 0.1347 | 0.2091 |

18 min | 0.5447 | 0.6970 | 0.2001 | 0.3379 |

30 min | 0.7783 | 0.6551 | 0.2481 | 0.3885 |

60 min | 0.9257 | 0.3312 | 0.2314 | 0.3906 |

90 min | 0.8856 | 0.3346 | 0.2919 | 0.5149 |

120 min | 0.8753 | 0.5496 | 0.3066 | 0.4596 |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2024 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**

Wang, F.; An, X.; Wang, Q.; Li, Z.; Han, L.; Su, D.
Research on a Rainfall Prediction Model in Guizhou Based on Raindrop Spectra. *Atmosphere* **2024**, *15*, 495.
https://doi.org/10.3390/atmos15040495

**AMA Style**

Wang F, An X, Wang Q, Li Z, Han L, Su D.
Research on a Rainfall Prediction Model in Guizhou Based on Raindrop Spectra. *Atmosphere*. 2024; 15(4):495.
https://doi.org/10.3390/atmos15040495

**Chicago/Turabian Style**

Wang, Fuzeng, Xuejiao An, Qiusong Wang, Zixin Li, Lin Han, and Debin Su.
2024. "Research on a Rainfall Prediction Model in Guizhou Based on Raindrop Spectra" *Atmosphere* 15, no. 4: 495.
https://doi.org/10.3390/atmos15040495