Quantile Neural Network apply to meteorological data

This repository aims to use the QRNN (quantile neural network) for forecasting in meteorological data. The libray used is https://github.com/atmtools/typhon developed by The Atmospheric Radiative Transfer Simulator.

Installation

The latest stable release of typhon can be installed using conda (recommended)

conda install -c rttools typhon

or pip

pip install typhon

Table of Content

• Radar reflectivity forecasting

Refence

References

• Taylor, J.W., 2000. A quantile regression neural network approach to estimating the conditional density of multiperiod returns. Journal of Forecasting 19 (4), 299–311.

• Cannon A. J. 2011. Quantile regression neural networks: Implementation in R and application to precipitation downscaling. Computers & Geosciences. 37 (9), 1277–1284.

• Lemke, O., Kluft, L., Mrziglod, J., Pfreundschuh, S., Holl, G., Larsson,R., Yamada, T., Mieslinger, T., and Doerr, J. (2020). atmtools/typhon: Typhon release0.8.0. Avaiable in: https://github.com/atmtools/typhon/tree/v0.8.0. Accessed 13 July 2020.