期刊
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
卷 36, 期 11, 页码 2248-2269出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/13658816.2022.2100892
关键词
Geographically convolutional neural network weighted regression; geographically neural network weighted regression; geographically weighted regression; spatial non-stationarity; global spatial proximity grid
类别
资金
- National Natural Science Foundation of China [41922043, 41871287, 42001323]
- National Key Research and Development Program of China [2021YFB3900902]
- Provincial Key R&D Program of Zhejiang [2021C01031]
In this study, a geographically convolutional neural network weighted regression (GCNNWR) model was proposed to estimate spatial non-stationarity. The model improved estimation accuracy and predictive power by introducing a global spatial proximity grid and a spatially weighted convolutional neural network, and maintained better stability and accuracy when the observation distribution was uneven.
Geographically weighted regression (GWR) is a classical method of modeling spatially non-stationary relationships. The geographically neural network weighted regression (GNNWR) model solves the problem of the inaccurate construction of spatial weight kernels using a spatially weighted neural network. However, when the spatial distribution of observations is uneven, the spatial proximity expression in the input of GWR and GNNWR models does not fully represent the impact of the whole research space on the estimating point. Therefore, we established a global spatial proximity grid (GSPG) to express the spatial proximity of each estimating point and proposed a spatially weighted convolutional neural network (SWCNN) to extract the relationship between the GSPG and spatial weights. Finally, we proposed a geographically convolutional neural network weighted regression (GCNNWR) model combining SWCNN and ordinary linear regression (OLR) model to estimate spatial non-stationarity. We used two case studies of simulated data and real environment data to demonstrate the advancements of the GCNNWR model. The GCNNWR model achieved higher estimation accuracy and greater predictive power than the OLR, GWR, multi-scale GWR (MGWR), and GNNWR models. Moreover, the GCNNWR model maintained its better stability and accuracy in estimating spatially non-stationary relationships when the distribution of observations was uneven.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据