SpatioTemporal Random Forest and SpatioTemporal Stacking Tree: A novel spatially explicit ensemble learning approach to modeling non-linearity in spatiotemporal non-stationarity

A wide variety of spatially explicit modeling algorithms has recently mushroomed in geoinformation research. These algorithms establish local models with data from spatially confined subsets, thereby offering a new impetus for addressing the issue of spatiotemporal non-stationarity. However, a signi...

Full description

Saved in:
Bibliographic Details
Main Authors: Yun Luo, Shiliang Su
Format: Article
Language:English
Published: Elsevier 2025-02-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843224006733
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850189662014930944
author Yun Luo
Shiliang Su
author_facet Yun Luo
Shiliang Su
author_sort Yun Luo
collection DOAJ
description A wide variety of spatially explicit modeling algorithms has recently mushroomed in geoinformation research. These algorithms establish local models with data from spatially confined subsets, thereby offering a new impetus for addressing the issue of spatiotemporal non-stationarity. However, a significant challenge persists in literature that local models are primarily predicated on linear assumptions, limiting their capacity to capture the non-linear relationships prevalent in real-world geographical phenomena. This study remedies this gap through proposing a novel approach that integrates the bagging and stacking approaches of ensemble learning into the spatially explicit modeling framework. We specifically develop the SpatioTemporal Random Forest (STRF) and SpatioTemporal Stacking Tree (STST) algorithms11 Python package link: https://github.com/46319943/GeoRegression., which capture and interpret the non-linearity in the spatial and temporal context more effectively. Additionally, we introduce the ‘local importance score’ and ‘spatiotemporally accumulated local effects’ as novel interpretable metrics for visualizing and unraveling the dynamics of non-stationarity in spatial analyses. Simulation and real data experiments validate that the STRF and STST outperform over traditional spatially explicit modeling algorithms to a large content. This study contributes to the methodological innovation of spatially explicit modeling by bringing the nonlinearity in spatiotemporal non-stationarity to the fore.
format Article
id doaj-art-7adaf8fa26eb420a8c999230cf82bb84
institution OA Journals
issn 1569-8432
language English
publishDate 2025-02-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-7adaf8fa26eb420a8c999230cf82bb842025-08-20T02:15:33ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-02-0113610431510.1016/j.jag.2024.104315SpatioTemporal Random Forest and SpatioTemporal Stacking Tree: A novel spatially explicit ensemble learning approach to modeling non-linearity in spatiotemporal non-stationarityYun Luo0Shiliang Su1Urban Computing and Visualization Lab, School of Resource and Environmental Sciences, Wuhan University, Wuhan, ChinaUrban Computing and Visualization Lab, School of Resource and Environmental Sciences, Wuhan University, Wuhan, China; Hubei Luojia Laboratory, Wuhan, China; Corresponding author at: Address: No.129 Luoyu Rd, Wuhan, Hubei Province, China.A wide variety of spatially explicit modeling algorithms has recently mushroomed in geoinformation research. These algorithms establish local models with data from spatially confined subsets, thereby offering a new impetus for addressing the issue of spatiotemporal non-stationarity. However, a significant challenge persists in literature that local models are primarily predicated on linear assumptions, limiting their capacity to capture the non-linear relationships prevalent in real-world geographical phenomena. This study remedies this gap through proposing a novel approach that integrates the bagging and stacking approaches of ensemble learning into the spatially explicit modeling framework. We specifically develop the SpatioTemporal Random Forest (STRF) and SpatioTemporal Stacking Tree (STST) algorithms11 Python package link: https://github.com/46319943/GeoRegression., which capture and interpret the non-linearity in the spatial and temporal context more effectively. Additionally, we introduce the ‘local importance score’ and ‘spatiotemporally accumulated local effects’ as novel interpretable metrics for visualizing and unraveling the dynamics of non-stationarity in spatial analyses. Simulation and real data experiments validate that the STRF and STST outperform over traditional spatially explicit modeling algorithms to a large content. This study contributes to the methodological innovation of spatially explicit modeling by bringing the nonlinearity in spatiotemporal non-stationarity to the fore.http://www.sciencedirect.com/science/article/pii/S1569843224006733Spatially explicit modelingMachine learningSpatiotemporal random forestSpatiotemporal stacking treeEnsemble learningSpatiotemporal non-stationarity
spellingShingle Yun Luo
Shiliang Su
SpatioTemporal Random Forest and SpatioTemporal Stacking Tree: A novel spatially explicit ensemble learning approach to modeling non-linearity in spatiotemporal non-stationarity
International Journal of Applied Earth Observations and Geoinformation
Spatially explicit modeling
Machine learning
Spatiotemporal random forest
Spatiotemporal stacking tree
Ensemble learning
Spatiotemporal non-stationarity
title SpatioTemporal Random Forest and SpatioTemporal Stacking Tree: A novel spatially explicit ensemble learning approach to modeling non-linearity in spatiotemporal non-stationarity
title_full SpatioTemporal Random Forest and SpatioTemporal Stacking Tree: A novel spatially explicit ensemble learning approach to modeling non-linearity in spatiotemporal non-stationarity
title_fullStr SpatioTemporal Random Forest and SpatioTemporal Stacking Tree: A novel spatially explicit ensemble learning approach to modeling non-linearity in spatiotemporal non-stationarity
title_full_unstemmed SpatioTemporal Random Forest and SpatioTemporal Stacking Tree: A novel spatially explicit ensemble learning approach to modeling non-linearity in spatiotemporal non-stationarity
title_short SpatioTemporal Random Forest and SpatioTemporal Stacking Tree: A novel spatially explicit ensemble learning approach to modeling non-linearity in spatiotemporal non-stationarity
title_sort spatiotemporal random forest and spatiotemporal stacking tree a novel spatially explicit ensemble learning approach to modeling non linearity in spatiotemporal non stationarity
topic Spatially explicit modeling
Machine learning
Spatiotemporal random forest
Spatiotemporal stacking tree
Ensemble learning
Spatiotemporal non-stationarity
url http://www.sciencedirect.com/science/article/pii/S1569843224006733
work_keys_str_mv AT yunluo spatiotemporalrandomforestandspatiotemporalstackingtreeanovelspatiallyexplicitensemblelearningapproachtomodelingnonlinearityinspatiotemporalnonstationarity
AT shiliangsu spatiotemporalrandomforestandspatiotemporalstackingtreeanovelspatiallyexplicitensemblelearningapproachtomodelingnonlinearityinspatiotemporalnonstationarity