Back to Search
Start Over
A Machine Learning-Based Approach for Spatial Estimation Using the Spatial Features of Coordinate Information
- Source :
- ISPRS International Journal of Geo-Information, Vol 9, Iss 587, p 587 (2020), ISPRS International Journal of Geo-Information, Volume 9, Issue 10
- Publication Year :
- 2020
- Publisher :
- MDPI AG, 2020.
-
Abstract
- With the development of machine learning technology, research cases for spatial estimation through machine learning approach (MLA) in addition to the traditional geostatistical techniques are increasing. MLA has the advantage that spatial estimation is possible without stationary hypotheses of data, but it is possible for the prediction results to ignore spatial autocorrelation. In recent studies, it was considered by using a distance matrix instead of raw coordinates. Although, the performance of spatial estimation could be improved through this approach, the computational complexity of MLA increased rapidly as the number of sample points increased. In this study, we developed a method to reduce the computational complexity of MLA while considering spatial autocorrelation. Principal component analysis is applied to it for extracting spatial features and reducing dimension of inputs. To verify the proposed approach, indicator Kriging was used as a benchmark model, and each performance of MLA was compared when using raw coordinates, distance vector, and spatial features extracted from distance vector as inputs. The proposed approach improved the performance compared to previous MLA and showed similar performance compared with Kriging. We confirmed that extracted features have characteristics of rigid classification in spatial estimation<br />on this basis, we conclude that the model could improve performance.
- Subjects :
- 010504 meteorology & atmospheric sciences
Computational complexity theory
Computer science
spatial feature
principal component analysis
Geography, Planning and Development
lcsh:G1-922
010502 geochemistry & geophysics
Machine learning
computer.software_genre
01 natural sciences
Dimension (vector space)
Kriging
spatial estimation
Earth and Planetary Sciences (miscellaneous)
Computers in Earth Sciences
Spatial analysis
0105 earth and related environmental sciences
Basis (linear algebra)
business.industry
Random forest
machine learning
Distance matrix
Principal component analysis
Artificial intelligence
business
computer
random forest
lcsh:Geography (General)
Subjects
Details
- Language :
- English
- ISSN :
- 22209964
- Volume :
- 9
- Issue :
- 587
- Database :
- OpenAIRE
- Journal :
- ISPRS International Journal of Geo-Information
- Accession number :
- edsair.doi.dedup.....192b28e5aab61fbfb6089d08e5789554