Predicting power outages caused by extratropical storms

Tervo, Roope; Láng, Ilona; Jung, Alexander; Mäkelä, Antti

doi:https://doi.org/10.5194/nhess-21-607-2021

Articles | Volume 21, issue 2

https://doi.org/10.5194/nhess-21-607-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/nhess-21-607-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 21, issue 2

Research article

|

11 Feb 2021

Research article |

| 11 Feb 2021

Predicting power outages caused by extratropical storms

Roope Tervo, Ilona Láng, Alexander Jung, and Antti Mäkelä

Data sets

ERA5 hourly data on pressure levels from 1979 to present H. Hersbach, B. Bell, P. Berrisford, G. Biavati, A. Horányi, J. Muñoz Sabater, J. Nicolas, C. Peubey, R. Radu, I. Rozum, D. Schepers, A. Simmons, C. Soci, D. Dee, and J.-N. Thépaut https://doi.org/10.24381/cds.bd0915c6

The National Forest Inventory (NFI) K. Korhonen, T. Packalen, and A. Kangas http://kartta.luke.fi/index-en.html

Model code and software

SASSE polygon process R. Tervo https://doi.org/10.5281/zenodo.4525234

SmartMet Server setup for ERA5 R. Tervo and T. Sirviö https://doi.org/10.5281/zenodo.4525236

Short summary

Predicting the number of power outages caused by extratropical storms is a key challenge for power grid operators. We introduce a novel method to predict the storm severity for the power grid employing ERA5 reanalysis data combined with a forest inventory. The storms are first identified from the data and then classified using several machine-learning methods. While there is plenty of room to improve, the results are already usable, with support vector classifier providing the best performance.