Reducing spatial autocorrelation in the dynamic simulation of urban growth using eigenvector spatial filtering

•We integrate CA with eigenvector spatial filtering to construct two new models.•We derive spatially varying land transition rules in Suzhou from 2009 to 2014.•We simulate urban growth in Suzhou between 2009–2014 and 2014–2019.•The introduction of eigenvector spatial filtering helps eliminate spatial autocorrelation.•The simulation accuracy of urban end-state and urban growth is improved.