A tensor-based approach to unify organization and operation of data for irregular spatio-temporal fields. Issue 9 (2nd September 2022)

• Record Type: Journal Article
• Authors: Li, Dongshuang; Teng, Yuhao; Zhou, Xinxin; Zhang, Jiyi; Luo, Wen; Zhao, Binru; Yu, Zhaoyuan; Yuan, Linwang
• Is Part Of: International journal of geographical information science. Volume 36:Issue 9(2022)
• Page Start: 1885
• Page End: 1904
• Publication Date: 2022-09-02
• Subjects: Irregular spatio-temporal-field data -- tensor analysis -- unified organization -- primitive element -- layered architecture; Geography -- Data processing -- Periodicals; Information storage and retrieval systems -- Periodicals; Géomatique -- Périodiques; Systèmes d'information -- Périodiques; 910.285
• DOI: 10.1080/13658816.2022.2092116
• Languages: English
• ISSNs: 1365-8816

Abstract

Abstract: Irregular geographic spatio-temporal-field data have been rapidly accumulating; however, data organizations and operations for different irregular types are often segregated, leading to systematic drawbacks, such as interface expansion difficulty and high coupling codes in GIS implementations. The paper proposes a unified approach to organizing and operating irregular geographic spatio-temporal-field data. The proposed approach has two components, namely 'concepts and definitions', and 'logical model'. The first component introduces the concept of primitive elements, which are formal sets of data points, to serve as the smallest building blocks in the data organization. We define the corresponding primitive elements for three prevalent irregularity types (including sparse, imbalanced, and heterogeneous). The second component utilizes object-oriented programming to support the implementation of various operators. Additionally, we develop the layered architecture to decouple data organization, operation, and visualization to assure low coupling among layers. For demonstrations, we conduct case studies to show the effectiveness of our approach. Additionally, we conduct experiments to new irregularity types and illustrate the flexibility and scalability of our approach. Comparisons with classic tensor methods and spatio-temporal analysis methods show that our approach has more comprehensive supports for different data types.