國立高雄大學圖資館 |

Language: English

Back

On spatio-temporal data modelling and uncertainty quantification using machine learning and information theory

Record Type:	Electronic resources : Monograph/item
Title/Author:	On spatio-temporal data modelling and uncertainty quantification using machine learning and information theoryby Fabian Guignard.
Author:	Guignard, Fabian.
Published:	Cham :Springer International Publishing :2022.
Description:	xviii, 158 p. :ill. (some col.), digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Uncertainty (Information theory)
Online resource:	https://doi.org/10.1007/978-3-030-95231-0
ISBN:	9783030952310$q(electronic bk.)

On spatio-temporal data modelling and uncertainty quantification using machine learning and information theory
Guignard, Fabian.

On spatio-temporal data modelling and uncertainty quantification using machine learning and information theory[electronic resource] /by Fabian Guignard. - Cham :Springer International Publishing :2022. - xviii, 158 p. :ill. (some col.), digital ;24 cm. - Springer theses,2190-5061. - Springer theses..

Introduction -- Study Area and Data Sets -- Advanced Exploratory Data Analysis -- Fisher-Shannon Analysis -- Spatio-Temporal Prediction with Machine Learning -- Uncertainty Quantification with Extreme Learning Machine -- Spatio-Temporal Modelling using Extreme Learning Machine -- Conclusions, Perspectives and Recommendations.

The gathering and storage of data indexed in space and time are experiencing unprecedented growth, demanding for advanced and adapted tools to analyse them. This thesis deals with the exploration and modelling of complex high-frequency and non-stationary spatio-temporal data. It proposes an efficient framework in modelling with machine learning algorithms spatio-temporal fields measured on irregular monitoring networks, accounting for high dimensional input space and large data sets. The uncertainty quantification is enabled by specifying this framework with the extreme learning machine, a particular type of artificial neural network for which analytical results, variance estimation and confidence intervals are developed. Particular attention is also paid to a highly versatile exploratory data analysis tool based on information theory, the Fisher-Shannon analysis, which can be used to assess the complexity of distributional properties of temporal, spatial and spatio-temporal data sets. Examples of the proposed methodologies are concentrated on data from environmental sciences, with an emphasis on wind speed modelling in complex mountainous terrain and the resulting renewable energy assessment. The contributions of this thesis can find a large number of applications in several research domains where exploration, understanding, clustering, interpolation and forecasting of complex phenomena are of utmost importance.

ISBN: 9783030952310$q(electronic bk.)

Standard No.: 10.1007/978-3-030-95231-0doiSubjects--Topical Terms:

206405
Uncertainty (Information theory)

LC Class. No.: Q375 / .G85 2022

Dewey Class. No.: 003.54

On spatio-temporal data modelling and uncertainty quantification using machine learning and information theory
LDR:02856nmm a2200337 a 4500 001 622517
003 DE-He213
005 20220312171657.0
006 m d
007 cr nn 008maaau
008 221209s2022 sz s 0 eng d
020 $a 9783030952310$q(electronic bk.)
020 $a 9783030952303$q(paper)
024 7 $a 10.1007/978-3-030-95231-0 $2 doi
035 $a 978-3-030-95231-0
040 $a GP $c GP
041 0 $a eng
050 4 $a Q375 $b .G85 2022
072 7 $a R $2 bicssc
072 7 $a SCI000000 $2 bisacsh
072 7 $a R $2 thema
082 0 4 $a 003.54 $2 23
090 $a Q375 $b .G951 2022
100 1 $a Guignard, Fabian. $3 924340
245 1 0 $a On spatio-temporal data modelling and uncertainty quantification using machine learning and information theory $h [electronic resource] / $c by Fabian Guignard.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a xviii, 158 p. : $b ill. (some col.), digital ; $c 24 cm.
490 1 $a Springer theses, $x 2190-5061
505 0 $a Introduction -- Study Area and Data Sets -- Advanced Exploratory Data Analysis -- Fisher-Shannon Analysis -- Spatio-Temporal Prediction with Machine Learning -- Uncertainty Quantification with Extreme Learning Machine -- Spatio-Temporal Modelling using Extreme Learning Machine -- Conclusions, Perspectives and Recommendations.
520 $a The gathering and storage of data indexed in space and time are experiencing unprecedented growth, demanding for advanced and adapted tools to analyse them. This thesis deals with the exploration and modelling of complex high-frequency and non-stationary spatio-temporal data. It proposes an efficient framework in modelling with machine learning algorithms spatio-temporal fields measured on irregular monitoring networks, accounting for high dimensional input space and large data sets. The uncertainty quantification is enabled by specifying this framework with the extreme learning machine, a particular type of artificial neural network for which analytical results, variance estimation and confidence intervals are developed. Particular attention is also paid to a highly versatile exploratory data analysis tool based on information theory, the Fisher-Shannon analysis, which can be used to assess the complexity of distributional properties of temporal, spatial and spatio-temporal data sets. Examples of the proposed methodologies are concentrated on data from environmental sciences, with an emphasis on wind speed modelling in complex mountainous terrain and the resulting renewable energy assessment. The contributions of this thesis can find a large number of applications in several research domains where exploration, understanding, clustering, interpolation and forecasting of complex phenomena are of utmost importance.
650 0 $a Uncertainty (Information theory) $3 206405
650 0 $a Machine learning. $3 188639
650 0 $a Predicate calculus. $3 760596
650 1 4 $a Earth and Environmental Sciences. $3 919207
650 2 4 $a Computer Modelling. $3 913151
650 2 4 $a Renewable Energy. $3 918996
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Springer theses. $3 557607
856 4 0 $u https://doi.org/10.1007/978-3-030-95231-0
950 $a Earth and Environmental Science (SpringerNature-11646)