Fabian Guignard
On Spatio-Temporal Data Modelling and Uncertainty Quantification Using Machine Learning and Information Theory
On Spatio-Temporal Data Modelling and Uncertainty Quantification Using Machine Learning and Information Theory
💎 Earn 541 Points (£5.41) on this item.
YOU SAVE £21.71
- Condition: Brand new
- UK Delivery times: Usually arrives within 2 - 3 working days
- UK Shipping: Fee starts at £2.39. Subject to product weight & dimension
Bulk ordering. Want 15 or more copies? Get a personalised quote and bigger discounts. Learn more about bulk orders.
Couldn't load pickup availability
- More about On Spatio-Temporal Data Modelling and Uncertainty Quantification Using Machine Learning and Information Theory
The growth of data indexed in space and time requires advanced tools to analyze them. This thesis proposes a framework for modeling with machine learning algorithms and uncertainty quantification using the extreme learning machine and Fisher-Shannon analysis. Examples include wind speed modeling and renewable energy assessment in environmental sciences.
Format: Paperback / softback
Length: 158 pages
Publication date: 13 March 2023
Publisher: Springer Nature Switzerland AG
The exponential growth of data indexed in space and time has necessitated the development of advanced and tailored tools to analyze it effectively. This thesis focuses on exploring and modeling complex high-frequency and non-stationary spatio-temporal data. It proposes an efficient framework for modeling spatio-temporal fields measured on irregular monitoring networks, accounting for high-dimensional input spaces and large data sets. The uncertainty quantification is enabled by specifying this framework with the extreme learning machine, a specialized type of artificial neural network for which analytical results, variance estimation, and confidence intervals are developed. Additionally, the thesis emphasizes 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 modeling in complex mountainous terrain and the resulting renewable energy assessment. The contributions of this thesis have broad applications in various research domains where exploration, understanding, clustering, interpolation, and forecasting of complex phenomena are of paramount importance.
Weight: 279g
Dimension: 235 x 155 (mm)
ISBN-13: 9783030952334
Edition number: 1st ed. 2022
This item can be found in:
UK and International shipping information
UK and International shipping information
UK Delivery and returns information:
- Delivery within 2 - 3 days when ordering in the UK.
- Shipping fee for UK customers from £2.39. Fully tracked shipping service available.
- Returns policy: Return within 30 days of receipt for full refund.
International deliveries:
Shulph Ink now ships to Australia, Belgium, Canada, France, Germany, Ireland, Italy, India, Luxembourg Saudi Arabia, Singapore, Spain, Netherlands, New Zealand, United Arab Emirates, United States of America.
- Delivery times: within 5 - 10 days for international orders.
- Shipping fee: charges vary for overseas orders. Only tracked services are available for most international orders. Some countries have untracked shipping options.
- Customs charges: If ordering to addresses outside the United Kingdom, you may or may not incur additional customs and duties fees during local delivery.
