TY - JOUR
T1 - Modelling InSAR-derived hillslope velocities with multivariate statistics
T2 - A first attempt to generate interpretable predictions
AU - He, Kun
AU - Tanyas, H.
AU - Chang, Ling
AU - Hu, Xiewen
AU - Luo, Gang
AU - Lombardo, L.
N1 - Funding Information:
The Geospatial Computing Platform of the Center of Expertise in Big Geodata Science (CRIB) (https://crib.utwente.nl) is used for the processing of Sentinel-1 data. We thank Dr. Serkan Girgin for his support in providing the necessary computing infrastructure. The authors gratefully acknowledge support from the National Key R&D Program of China (2022YFC3005704), the National Natural Science Foundation of China (42277143), and the China Scholarship Council (NO. 202107000060).
Funding Information:
The Geospatial Computing Platform of the Center of Expertise in Big Geodata Science (CRIB) ( https://crib.utwente.nl ) is used for the processing of Sentinel-1 data. We thank Dr. Serkan Girgin for his support in providing the necessary computing infrastructure. The authors gratefully acknowledge support from the National Key R&D Program of China ( 2022YFC3005704 ), the National Natural Science Foundation of China ( 42277143 ), and the China Scholarship Council (NO. 202107000060).
Publisher Copyright:
© 2023 The Authors
PY - 2023/5/1
Y1 - 2023/5/1
N2 - Spatiotemporal patterns of earth surface deformation are influenced by a combination of the geologic, topographic, seismic, anthropogenic, meteorological and climatic conditions specific to any landscape of interest. These have been mostly modelled through machine learning tools. However, these influences are yet to be explored and exploited to train interpretable data-driven models and then make predictions on the deformation one may expect in space or time. This work explored this aspect by proposing the first multivariate model dedicated to InSAR-derived deformation data. The results we obtain are promising for we suitably retrieved the signal of environmental predictors, from which we then estimated the mean line of sight velocities for a number of hillslopes affected by seismic shaking. The importance of such models resides in its potential for opening an entirely new research line for slope instability modelling.
AB - Spatiotemporal patterns of earth surface deformation are influenced by a combination of the geologic, topographic, seismic, anthropogenic, meteorological and climatic conditions specific to any landscape of interest. These have been mostly modelled through machine learning tools. However, these influences are yet to be explored and exploited to train interpretable data-driven models and then make predictions on the deformation one may expect in space or time. This work explored this aspect by proposing the first multivariate model dedicated to InSAR-derived deformation data. The results we obtain are promising for we suitably retrieved the signal of environmental predictors, from which we then estimated the mean line of sight velocities for a number of hillslopes affected by seismic shaking. The importance of such models resides in its potential for opening an entirely new research line for slope instability modelling.
KW - Hillslope deformation
KW - InSAR
KW - Line-of-sight velocity
KW - Multivariate regression
KW - Prediction
KW - Sentinel-1
KW - Spatio-temporal model
KW - UT-Hybrid-D
KW - ITC-ISI-JOURNAL-ARTICLE
KW - ITC-HYBRID
U2 - 10.1016/j.rse.2023.113518
DO - 10.1016/j.rse.2023.113518
M3 - Article
AN - SCOPUS:85149058609
SN - 0034-4257
VL - 289
JO - Remote sensing of environment
JF - Remote sensing of environment
M1 - 113518
ER -