Geographically neural network weighted regression for the accurate estimation of spatial non-stationarity

ABSTRACT Geographically weighted regression (GWR) is a classic and widely used approach to model spatial non-stationarity. However, the approach makes no precise expressions of its weighting kernels and is insufficient to estimate complex geographical processes. To resolve these problems, we proposed a geographically neural network weighted regression (GNNWR) model that combines ordinary least squares (OLS) and neural networks to estimate spatial non-stationarity based on a concept similar to GWR. Specifically, we designed a spatially weighted neural network (SWNN) to represent the nonstationary weight matrix in GNNWR and developed two case studies to examine the effectiveness of GNNWR. The first case used simulated datasets, and the second case, environmental observations from the coastal areas of Zhejiang. The results showed that GNNWR achieved better fitting accuracy and more adequate prediction than OLS and GWR. In addition, GNNWR is applicable to addressing spatial non-stationarity in various domains with complex geographical processes.

[1]  Shin'ichi Tamura,et al.  Capabilities of a four-layered feedforward neural network: four layers versus three , 1997, IEEE Trans. Neural Networks.

[2]  A. Stewart Fotheringham,et al.  Geographical and Temporal Weighted Regression (GTWR) , 2015 .

[3]  Zhenhong Du,et al.  Extending geographically and temporally weighted regression to account for both spatiotemporal heterogeneity and seasonal variations in coastal seas , 2018, Ecol. Informatics.

[4]  Baraq Ghaleb,et al.  STF-RNN: Space Time Features-based Recurrent Neural Network for predicting people next location , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[5]  Yee Leung,et al.  Statistical Tests for Spatial Nonstationarity Based on the Geographically Weighted Regression Model , 2000 .

[6]  Zhenhong Du,et al.  Red tide time series forecasting by combining ARIMA and deep belief network , 2017, Knowl. Based Syst..

[7]  Zhenhong Du,et al.  A spatiotemporal regression-kriging model for space-time interpolation: a case study of chlorophyll-a prediction in the coastal areas of Zhejiang, China , 2018, Int. J. Geogr. Inf. Sci..

[8]  A. Stewart Fotheringham,et al.  Local Spatiotemporal Modeling of House Prices: A Mixed Model Approach , 2016 .

[9]  B. Minasny,et al.  Spatiotemporal monthly rainfall forecasts for south-eastern and eastern Australia using climatic indices , 2016, Theoretical and Applied Climatology.

[10]  N. Musaoglu,et al.  CLASSIFICATION OF MULTI-SPECTRAL , MULTI-TEMPORAL AND MULTI-SENSOR IMAGES USING PRINCIPAL COMPONENTS ANALYSIS AND ARTIFICIAL NEURAL NETWORKS : BEYKOZ CASE , 2004 .

[11]  J. Tu.  Spatially varying relationships between land use and water quality across an urbanization gradient explored by geographically weighted regression. , 2011 .

[12]  Hyung-Sup Jung,et al.  Data Mining Approaches for Landslide Susceptibility Mapping in Umyeonsan, Seoul, South Korea , 2017 .

[13]  Qiqing Wang,et al.  Landslide susceptibility mapping at Gongliu county, China using artificial neural network and weight of evidence models , 2016, Geosciences Journal.

[14]  S. Fotheringham,et al.  Modeling the spatial variation of the explanatory factors of human-caused wildfires in Spain using geographically weighted logistic regression , 2014 .

[15]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[16]  A. Fotheringham,et al.  Exploring, modelling and predicting spatiotemporal variations in house prices , 2015 .

[17]  Yang Liu,et al.  Estimating ground-level PM2.5 in China using satellite remote sensing. , 2014, Environmental science & technology.

[18]  Chris Brunsdon,et al.  Geographically Weighted Regression: The Analysis of Spatially Varying Relationships , 2002 .

[19]  Liang-pei Zhang,et al.  Point-surface fusion of station measurements and satellite observations for mapping PM 2.5 distribution in China: Methods and assessment , 2016, 1607.02976.

[20]  Silvio Savarese,et al.  Social LSTM: Human Trajectory Prediction in Crowded Spaces , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Zhenhong Du,et al.  Ecosystem health assessment in coastal waters by considering spatio-temporal variations with intense anthropogenic disturbance , 2017, Environ. Model. Softw..

[22]  M. Charlton,et al.  Geographically Weighted Regression: A Natural Evolution of the Expansion Method for Spatial Data Analysis , 1998 .

[23]  A S Fotheringham,et al.  Geographically weighted Poisson regression for disease association mapping , 2005, Statistics in medicine.

[24]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  A. Stewart Fotheringham,et al.  Geographically Weighted Regression: A Method for Exploring Spatial Nonstationarity , 2010 .

[26]  Martin Charlton,et al.  The Use of Geographically Weighted Regression for Spatial Prediction: An Evaluation of Models Using Simulated Data Sets , 2010 .

[27]  John Tenhunen,et al.  Application of a geographically‐weighted regression analysis to estimate net primary production of Chinese forest ecosystems , 2005 .

[28]  Rongrong Li,et al.  A geographically and temporally weighted autoregressive model with application to housing prices , 2014, Int. J. Geogr. Inf. Sci..

[29]  Bo Wu,et al.  Geographically and temporally weighted regression for modeling spatio-temporal variation in house prices , 2010, Int. J. Geogr. Inf. Sci..

[30]  Giles M. Foody,et al.  Spatial non-stationarity in the relationships between land cover and surface temperature in an urban heat island and its impacts on thermally sensitive populations , 2012 .

[31]  E. Rubiola,et al.  The $\Omega $ Counter, a Frequency Counter Based on the Linear Regression , 2015, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[32]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..