Investigating the time dynamics of wind speed in complex terrains by using the Fisher–Shannon method

Guignard, Fabian; Lovallo, Michele; Laib, Mohamed; Golay, Jean; Kanevski, Mikhaïl; Helbig, Nora; Telesca, Luciano

doi:10.1016/j.physa.2019.02.048

Cited by 15 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The concept of Fisher Information (FI) was introduced in the statistical theory estimation (Fisher, 1925), while the special case of FI of a location parameter of a parametric distribution was termed FIM (Frieden, 1990). Subsequently, FIM has been used to describe physical systems (Frieden, 1990;Boumali and Labidi, 2018), and has been applied for time series analysis in physiology (Martin et al, 1999), geophysics (Telesca et al, 2011;Balasis et al, 2016), ecology (Ba et al, 2020), meteorology (Pierini et al, 2016;Guignard et al, 2019b), hydrology (Pierini et al, 2011(Pierini et al, , 2015Lovallo et al, 2013), and social behaviour (Li et al, 2020). For continuous one dimensional variable X with probability density function (pdf) f(x) the FIM I X is defined as (Vignat and Bercher, 2003)…”

Section: The Fisher-shannon Methodsmentioning

confidence: 99%

Fisher Shannon analysis of drought/wetness episodes along a rainfall gradient in Northeast Brazil

Silva

Menezes

Telesca

et al. 2020

Intl Journal of Climatology

Self Cite

View full text Add to dashboard Cite

We applied the informational approach of the Fisher-Shannon method to study the time series of Standardized Precipitation Index (SPI) derived from monthly rainfall data at 133 gauging stations in Northeast (NE) Brazil. The climate in the study region ranges from tropical humid in the coastal area Zona de Mata to tropical semiarid inland Sertão, passing through a sub-humid transition region Agreste. The time span is from 1962 to 2012, and SPI was calculated for 1, 3, 6, and 12-month time scales. We calculate information quantifiers Shannon entropy power (SEP) and Fisher information measure (FIM) that quantify signal disorder and structural organization, respectively, and define its position in the Fisher Shannon plane (FS). We find that the SPI-1 series that describes short term dry/wet conditions display a higher degree of organization (higher FIM) and a lower degree of disorder (lower SEP) than SPI's that describe medium and long term conditions (SPI-3, SPI-6, and SPI-12). By analysing the spatial distribution of information quantifiers, we find that short term dry/wet conditions (SPI-1) show the lowest disorder and highest organization degree in the deep inland Sertão region and highest disorder and lowest organization degree in the coastal Zona de Mata region, while long term conditions (SPI-12) show the opposite trend. For medium-term conditions (SPI-3 and SPI-6), the SEP is highest and FIM lowest in the transition sub-humid Agreste region. Our findings indicate that information theory-based methods, particularly FS have the potential to discriminate among different climatic regimes.

show abstract

Section: The Fisher-shannon Methodsmentioning

confidence: 99%

Fisher Shannon analysis of drought/wetness episodes along a rainfall gradient in Northeast Brazil

Silva

Menezes

Telesca

et al. 2020

Intl Journal of Climatology

Self Cite

View full text Add to dashboard Cite

show abstract

“…Wind speed has been proven to be extremely dependent on local orographic characteristics (Guignard et al 2019), which can be assessed by applying convolutional filters to extract primary or secondary topographic features from a Digital Elevation Model (DEM) (Laib and Kanevski 2019). In this study, we adopted the 13-dimensional input space proposed in Robert et al (2013) to model wind speed using ML.…”

Section: Study Area and Data Availabilitymentioning

confidence: 99%

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

“…Wind speed has been proven to be extremely dependent on local orographic characteristics [19], which can be assessed by applying convolutional filters to extract primary or secondary topographic features from a Digital Elevation Model (DEM) [32]. In this study, we adopted the 13-dimensional input space proposed in [50] to model wind speed using ML.…”

Section: Germanymentioning

confidence: 99%

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

Investigating the time dynamics of wind speed in complex terrains by using the Fisher–Shannon method

Cited by 15 publications

References 33 publications

Fisher Shannon analysis of drought/wetness episodes along a rainfall gradient in Northeast Brazil

Fisher Shannon analysis of drought/wetness episodes along a rainfall gradient in Northeast Brazil

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

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

Contact Info

Product

Resources

About