Sparse estimation in kriging for functional data.
Saved in:
| Title: | Sparse estimation in kriging for functional data. |
|---|---|
| Authors: | Matsui, Hidetoshi1 (AUTHOR) hmatsui@biwako.shiga-u.ac.jp, Yamamoto, Kohei2 (AUTHOR) s6023148@st.shiga-u.ac.jp, Yamakawa, Yuya3 (AUTHOR) yuya@i.kyoto-u.ac.jp |
| Source: | Stochastic Environmental Research & Risk Assessment. Jun2025, Vol. 39 Issue 6, p2413-2425. 13p. |
| Subjects: | Error functions, Functional analysis, Data analysis, Kriging, Forecasting, Algorithms |
| Abstract: | We introduce a sparse estimation in ordinary and universal kriging for functional data. The kriging for functional data predicts a feature given as a function at a location where the data are not observed by a linear combination of data observed at other locations. To estimate the weights of the linear combination, we apply the lasso-type regularization in the minimization problem of the integrated expected squared error of the function. We derive an algorithm to derive an estimator using an augmented Lagrange method. In addition, tuning parameters included in the estimation procedure are selected by cross-validation. Since the proposed method can shrink some of the weights of the linear combination to exactly zero, we can investigate which locations are necessary or unnecessary to predict the feature. Simulation and real data analysis show that the proposed method can predict a function at an unobserved location using the data observed from nearby locations. [ABSTRACT FROM AUTHOR] |
| Copyright of Stochastic Environmental Research & Risk Assessment is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | We introduce a sparse estimation in ordinary and universal kriging for functional data. The kriging for functional data predicts a feature given as a function at a location where the data are not observed by a linear combination of data observed at other locations. To estimate the weights of the linear combination, we apply the lasso-type regularization in the minimization problem of the integrated expected squared error of the function. We derive an algorithm to derive an estimator using an augmented Lagrange method. In addition, tuning parameters included in the estimation procedure are selected by cross-validation. Since the proposed method can shrink some of the weights of the linear combination to exactly zero, we can investigate which locations are necessary or unnecessary to predict the feature. Simulation and real data analysis show that the proposed method can predict a function at an unobserved location using the data observed from nearby locations. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 14363240 |
| DOI: | 10.1007/s00477-025-02976-4 |
