Uncertainty quantification in extreme learning machine: Analytical developments, variance estimates and confidence intervals

Guignard, Fabian; Amato, Federico; Kanevski, Mikhaïl

doi:10.1016/j.neucom.2021.04.027

Cited by 12 publications

(24 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To enable variance estimation of the ELM modelling, the algorithm is retrained M times and averaged [18], resulting in a particular case of ELM ensembles [34,36]. Denoting the m−th prediction as fm (x 0 ) for m = 1, .…”

Section: Extreme Learning Machinementioning

confidence: 99%

“…Considering the input variables as deterministic, the use of several ELMs allows to develop distribution-free estimates of variance in homoskedastic (constant noise variance) and heteroskedastic (non-constant noise variance) settings. Several estimates are proposed in [18]. In this paper, the heteroskedastic estimate σ2…”

Section: Extreme Learning Machinementioning

confidence: 99%

“…BR and its related noise variance estimate σ2 ε will be used in the spatio-temporal prediction variance estimation procedure. Those variance estimates are also provided for regularised ELM and are computed using the UncELMe python package (see [18] for more details on their derivation and implementation).…”

Section: Extreme Learning Machinementioning

confidence: 99%

“…where σ2 S2,k (s 0 ) is the heteroskedastic estimate σ2 S2 of the modelled regression function of the k th spatial coefficient map, at the input point s 0 . The choice of the estimate is motivated by the convenient trade-off between computational efficiency and estimation effectiveness of σ2 S2 , see [18].…”

Section: Spatio-temporal Model Variance Estimationmentioning

confidence: 99%

“…More specifically, the wind speed data are decomposed into temporally referenced basis functions and their corresponding spatially distributed coefficients. The latter are spatially modelled using the Extreme Learning Machine (ELM) algorithm, a ML model for which a methodology to estimate model variance was introduced in [18]. This will enable the estimation of both model and prediction uncertainty without any assumption on data distributional patterns.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Spatio-temporal estimation of wind speed and wind power using machine learning: predictions, uncertainty and technical potential

Amato,

Guignard,

Walch

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The growth of wind generation capacities in the past decades has shown that wind energy can contribute to the energy transition in many parts of the world. Being highly variable and complex to model, the quantification of the spatio-temporal variation of wind power and the related uncertainty is highly relevant for energy planners and policy-makers. Machine Learning has become a popular tool to perform wind-speed and power predictions. However, the existing approaches have several limitations. These include (i) insufficient consideration of spatio-temporal correlations in wind-speed data, (ii) a lack of existing methodologies to quantify the uncertainty of wind speed prediction

show abstract

Section: Extreme Learning Machinementioning

confidence: 99%

Section: Extreme Learning Machinementioning

confidence: 99%

Section: Extreme Learning Machinementioning

confidence: 99%

Section: Spatio-temporal Model Variance Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Spatio-temporal estimation of wind speed and wind power using machine learning: predictions, uncertainty and technical potential

Amato,

Guignard,

Walch

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Introduction

Guignard

2022

On Spatio-Temporal Data Modelling and Uncertainty Quantification Using Machine Learning and Information Theory

View full text Add to dashboard Cite

Spatio-temporal estimation of wind speed and wind power using extreme learning machines: predictions, uncertainty and technical potential

Amato

Guignard

Walch

et al. 2022

Stoch Environ Res Risk Assess

Self Cite

View full text Add to dashboard Cite

With wind power providing an increasing amount of electricity worldwide, the quantification of its spatio-temporal variations and the related uncertainty is crucial for energy planners and policy-makers. Here, we propose a methodological framework which (1) uses machine learning to reconstruct a spatio-temporal field of wind speed on a regular grid from spatially irregularly distributed measurements and (2) transforms the wind speed to wind power estimates. Estimates of both model and prediction uncertainties, and of their propagation after transforming wind speed to power, are provided without any assumptions on data distributions. The methodology is applied to study hourly wind power potential on a grid of $$250\times 250$$ 250 × 250 m$$^{2}$$ 2 for turbines of 100 m hub height in Switzerland, generating the first dataset of its type for the country. We show that the average annual power generation per turbine is 4.4 GWh. Results suggest that around 12,000 wind turbines could be installed on all 19,617 km$$^{2}$$ 2 of available area in Switzerland resulting in a maximum technical wind potential of 53 TWh. To achieve the Swiss expansion goals of wind power for 2050, around 1000 turbines would be sufficient, corresponding to only 8% of the maximum estimated potential.

show abstract

Uncertainty quantification in extreme learning machine: Analytical developments, variance estimates and confidence intervals

Cited by 12 publications

References 24 publications

Spatio-temporal estimation of wind speed and wind power using machine learning: predictions, uncertainty and technical potential

Spatio-temporal estimation of wind speed and wind power using machine learning: predictions, uncertainty and technical potential

Introduction

Spatio-temporal estimation of wind speed and wind power using extreme learning machines: predictions, uncertainty and technical potential

Contact Info

Product

Resources

About