The Fast Fourier Transform (FFT) as a statistical tool for time-series analysis

    Research output: Contribution to conference typesPaperResearch

    Abstract

    Many geosciences phenomena show cyclic/periodic behaviour, or can show this under certain conditions, e.g. soil gas concentrations/emissions, earthquakes, droughts and floods, whereas others are anomalous, recurring apparently randomly with regard to time, e.g. earthquakes and volcanic eruptions (under most circumstances). For the cyclic cases, an analysis of past time-series can yield an expectation and perhaps some degree of forecasting, even if only at the level of 'more probable' and 'less probable' times of occurrence. The aim of this short-course is to provide an introduction to and overview of the Discrete/Fast Fourier Transform as a key underpinning technique of time-series analysis to identify and quantify periodic features, as distinct from its more conventional usage in digitisation and signal-analysis. The session will take the key question "Are we looking for cyclic or anomalous phenomena?" as its starting point and will focus on the application of the Fast Fourier Transform, as implemented in many software packages, and interpretation of the output, including assessment of statistical effectsize. It will conclude with an introduction to periodgram approaches for unequal-interval timeseries.
    Original languageEnglish
    Publication statusPublished - 11 Apr 2018
    EventEuropean Geosciences Union (EGU) General Assembly 2018 - Vienna, Austria
    Duration: 9 Apr 201811 Apr 2018
    https://www.egu2018.eu/
    https://egu2018.eu/

    Conference

    ConferenceEuropean Geosciences Union (EGU) General Assembly 2018
    Period9/04/1811/04/18
    Internet address

    Fingerprint

    time series analysis
    Fourier transform
    earthquake
    digitization
    soil gas
    volcanic eruption
    drought
    time series
    software
    analysis

    Cite this

    Crockett, R. G. M. (2018). The Fast Fourier Transform (FFT) as a statistical tool for time-series analysis. Paper presented at European Geosciences Union (EGU) General Assembly 2018, .
    Crockett, Robin G M. / The Fast Fourier Transform (FFT) as a statistical tool for time-series analysis. Paper presented at European Geosciences Union (EGU) General Assembly 2018, .
    @conference{4e5bfdbd8cff47ecb0091d958316aab3,
    title = "The Fast Fourier Transform (FFT) as a statistical tool for time-series analysis",
    abstract = "Many geosciences phenomena show cyclic/periodic behaviour, or can show this under certain conditions, e.g. soil gas concentrations/emissions, earthquakes, droughts and floods, whereas others are anomalous, recurring apparently randomly with regard to time, e.g. earthquakes and volcanic eruptions (under most circumstances). For the cyclic cases, an analysis of past time-series can yield an expectation and perhaps some degree of forecasting, even if only at the level of 'more probable' and 'less probable' times of occurrence. The aim of this short-course is to provide an introduction to and overview of the Discrete/Fast Fourier Transform as a key underpinning technique of time-series analysis to identify and quantify periodic features, as distinct from its more conventional usage in digitisation and signal-analysis. The session will take the key question {"}Are we looking for cyclic or anomalous phenomena?{"} as its starting point and will focus on the application of the Fast Fourier Transform, as implemented in many software packages, and interpretation of the output, including assessment of statistical effectsize. It will conclude with an introduction to periodgram approaches for unequal-interval timeseries.",
    author = "Crockett, {Robin G M}",
    year = "2018",
    month = "4",
    day = "11",
    language = "English",
    note = "European Geosciences Union (EGU) General Assembly 2018 ; Conference date: 09-04-2018 Through 11-04-2018",
    url = "https://www.egu2018.eu/, https://egu2018.eu/",

    }

    Crockett, RGM 2018, 'The Fast Fourier Transform (FFT) as a statistical tool for time-series analysis' Paper presented at European Geosciences Union (EGU) General Assembly 2018, 9/04/18 - 11/04/18, .

    The Fast Fourier Transform (FFT) as a statistical tool for time-series analysis. / Crockett, Robin G M.

    2018. Paper presented at European Geosciences Union (EGU) General Assembly 2018, .

    Research output: Contribution to conference typesPaperResearch

    TY - CONF

    T1 - The Fast Fourier Transform (FFT) as a statistical tool for time-series analysis

    AU - Crockett, Robin G M

    PY - 2018/4/11

    Y1 - 2018/4/11

    N2 - Many geosciences phenomena show cyclic/periodic behaviour, or can show this under certain conditions, e.g. soil gas concentrations/emissions, earthquakes, droughts and floods, whereas others are anomalous, recurring apparently randomly with regard to time, e.g. earthquakes and volcanic eruptions (under most circumstances). For the cyclic cases, an analysis of past time-series can yield an expectation and perhaps some degree of forecasting, even if only at the level of 'more probable' and 'less probable' times of occurrence. The aim of this short-course is to provide an introduction to and overview of the Discrete/Fast Fourier Transform as a key underpinning technique of time-series analysis to identify and quantify periodic features, as distinct from its more conventional usage in digitisation and signal-analysis. The session will take the key question "Are we looking for cyclic or anomalous phenomena?" as its starting point and will focus on the application of the Fast Fourier Transform, as implemented in many software packages, and interpretation of the output, including assessment of statistical effectsize. It will conclude with an introduction to periodgram approaches for unequal-interval timeseries.

    AB - Many geosciences phenomena show cyclic/periodic behaviour, or can show this under certain conditions, e.g. soil gas concentrations/emissions, earthquakes, droughts and floods, whereas others are anomalous, recurring apparently randomly with regard to time, e.g. earthquakes and volcanic eruptions (under most circumstances). For the cyclic cases, an analysis of past time-series can yield an expectation and perhaps some degree of forecasting, even if only at the level of 'more probable' and 'less probable' times of occurrence. The aim of this short-course is to provide an introduction to and overview of the Discrete/Fast Fourier Transform as a key underpinning technique of time-series analysis to identify and quantify periodic features, as distinct from its more conventional usage in digitisation and signal-analysis. The session will take the key question "Are we looking for cyclic or anomalous phenomena?" as its starting point and will focus on the application of the Fast Fourier Transform, as implemented in many software packages, and interpretation of the output, including assessment of statistical effectsize. It will conclude with an introduction to periodgram approaches for unequal-interval timeseries.

    UR - https://egu2018.eu/

    M3 - Paper

    ER -

    Crockett RGM. The Fast Fourier Transform (FFT) as a statistical tool for time-series analysis. 2018. Paper presented at European Geosciences Union (EGU) General Assembly 2018, .