Redirigiendo al acceso original de articulo en 18 segundos...
ARTÍCULO
TITULO

Incorporating Spatial Autocorrelation in Machine Learning Models Using Spatial Lag and Eigenvector Spatial Filtering Features

Xiaojian Liu    
Ourania Kounadi and Raul Zurita-Milla    

Resumen

Applications of machine-learning-based approaches in the geosciences have witnessed a substantial increase over the past few years. Here we present an approach that accounts for spatial autocorrelation by introducing spatial features to the models. In particular, we explore two types of spatial features, namely spatial lag and eigenvector spatial filtering (ESF). These features are used within the widely used random forest (RF) method, and their effect is illustrated on two public datasets of varying sizes (Meuse and California housing datasets). The least absolute shrinkage and selection operator (LASSO) is used to determine the best subset of spatial features, and nested cross-validation is used for hyper-parameter tuning and performance evaluation. We utilize Moran?s I and local indicators of spatial association (LISA) to assess how spatial autocorrelation is captured at both global and local scales. Our results show that RF models combined with either spatial lag or ESF features yield lower errors (up to 33% different) and reduce the global spatial autocorrelation of the residuals (up to 95% decrease in Moran?s I) compared to the RF model with no spatial features. The local autocorrelation patterns of the residuals are weakened as well. Compared to benchmark geographically weighted regression (GWR) models, the RF models with spatial features yielded more accurate models with similar levels of global and local autocorrelation in the prediction residuals. This study reveals the effectiveness of spatial features in capturing spatial autocorrelation and provides a generic machine-learning modelling workflow for spatial prediction.

 Artículos similares

       
 
Xinyi Lai and Chao Gao    
The spatiotemporal patterns of residential and supporting service facilities are critical to effective urban planning. However, with growing urban sprawl and congestion, the spatial distribution patterns and evolutionary characteristics of these areas sh... ver más

 
Ji Young Cho and Joori Suh    
Recent advancements in virtual reality (VR) technology have enabled its integration into learning diverse aspects of spatial components and relationships in the field of spatial design, as well as designing, communicating, collaborating, and managing com... ver más
Revista: Buildings

 
Higor Costa de Brito, Iana Alexandra Alves Rufino, Mauro Normando Macedo Barros Filho and Ronaldo Amâncio Meneses    
In the face of urban expansion, ensuring sustainable water consumption is paramount. This study aims to develop a domestic water demand forecast model that considers population heterogeneity and the urban area distribution in a city in the Brazilian Semi... ver más
Revista: Urban Science

 
Yadi Wang, David Levinson     Pág. 469 - 496
The traditional mobility-oriented travel-time saving benefit assessment method has been repeatedly questioned for numerous intrinsic flaws, motivating the search for alternative benefit assessment approaches. Although a wealth of literature confirms the ... ver más

 
Fengping Liu, Xu Wang, Yuhu Chang, Ye Xu, Yinan Zheng, Ning Sun and Wei Li    
This study analyzed the multivariate drought risks for the Wei River basin by characterizing the interdependence between the standardized precipitation index (SPI) and the standardized precipitation evapotranspiration index (SPEI). Both parametric and no... ver más
Revista: Water