An Experimental Evaluation of Kernel Density Estimation to Choose Categorical Map Colours

ABSTRACTWhen selecting categorical map colours, colour conventions should be respected to leverage semantic–colour resonance to facilitate cartographic communication. Given a set of sample colours, kernel density estimation (KDE) can be used to estimate each colour's probability density (appropriateness) to represent the category. How to couple bandwidth and kernel to estimate better appropriateness remains unknown. To fill this gap, an experiment was designed to explore best pairs of bandwidth and kernel capturing users' assessments. We gathered six groups of colour samples from 10 well-accepted land use atlases and 30 randomly sampled test colours; we then applied KDE to estimate the appropriateness of test colours using all possible pairs of bandwidth and kernel, and invited participants to score each test colour. Results show that pair of rule-of-thumb bandwidth and Gaussian kernel yields the best estimates. Our findings are generalizable to diverse colours and can serve as a complement to design colours.KEYWORDS: Map colour designcategorical colourskernel density estimationcolour conventionsexperimental evaluation Disclosure StatementNo potential conflict of interest was reported by the author(s).Data Availability StatementData are available from the authors upon request.Additional informationFundingThis work was supported by the National Natural Science Foundation of China (grant numbers 41971417 and 41930104).Notes on contributorsMingguang WuMingguang WU is currently a professor at department of geographic information science, Nanjing Normal University, China. He has a PhD in Geography and Geographic Information Science from the Information Engineering University, China. His professional skills and interests in cartography are symbol design and spatio-temporal mapping.Ziming ChengZiming Cheng is currently pursuing a PhD degree at the College of Geographic Sciences, Nanjing Normal University. His primary research focuses on cartography and the visualization of geographic information.Wei ChengWei Cheng is currently a GIS software engineer at Nanjing NARI Information & Communication Technology Co., Ltd., China. His professional skills in cartography are the visualization of geographic information and mapping software development.