# A surrogate model for estimating extreme tower loads on wind turbines based on random forest proximities

## TL;DR

This paper introduces a random forest-based surrogate model to estimate extreme tower loads on wind turbines from operational signals, aiding design and safety assessments without relying on traditional regression methods.

## Contribution

The paper presents a novel surrogate modeling approach using random forest proximities to estimate extreme loads, improving adaptability in high-dimensional, sparse data environments.

## Key findings

- Effective estimation of tower loads from operational data
- Model outperforms traditional regression-based surrogates
- Applicable to real-world wind turbine data

## Abstract

In the present paper we present a surrogate model, which can be used to estimate extreme tower loads on a wind turbine from a number of signals and a suitable simulation tool. Due to the requirements of the International Electrotechnical Commission (IEC) Standard 61400-1, assessing extreme tower loads on wind turbines constitutes a key component of the design phase. The proposed model imputes tower loads by matching observed signals with simulated quantities using proximities induced by random forests. In this way the algorithm's adaptability to high-dimensional and sparse settings is exploited without using regression-based surrogate loads (which may display misleading probabilistic characteristics). Finally, the model is applied to estimate tower loads on an operating wind turbine from data on its operational statistics.