Hexbin

A hexbin map divides an area, such as a geographic region, into multiple hexagonal cells, each coloured based on the number of data points it contains. Hexagons are ideal for creating adjacent, evenly spaced bins that split the space into discrete units. A hexbin visualization effectively displays data density or distribution, allowing quick interpretation of where concentrations of data occur across the area.

Quick details:

What

Discover distribution and rank through hexagonal binning

Why:

Visualize density patterns clearly in geographic or spatial data contexts

History of Hexbin Visualization

Hexbin visualization was first introduced in a 1987 paper by statisticians D.B. Carr and colleagues as a technique to represent two-dimensional data by dividing the space into hexagonal bins and counting data points within each bin. Hexagonal binning was chosen over traditional square bins due to its ability to better capture density with less visual bias, as hexagons tessellate efficiently and provide a smoother, more natural pattern.

The technique has since become popular for creating hexbin heatmaps and hexbin density plots, especially in geographic and spatial data visualization, helping to reveal patterns and clusters in large datasets. This method efficiently reduces overplotting and enhances clarity compared to scatterplots or rectangular histograms, making it a valuable tool in data visualization.

The hexbin approach is widely implemented in software libraries and used for hexagon data visualization across fields like cartography, environmental science, and urban planning.

A hexagonal grid or lattice atop a 2-dimensional field of data and determining data point counts for each hexagon as represented on a map

Source

When to Use a Hexbin?

1

Unbiased density distribution

Use hexbin maps when geographic areas vary widely in size, to avoid the size bias common with choropleth maps. Hexagonal bins break the map into equal-sized units, representing data density fairly and uniformly.

Hexbin Map: Geographical representation of signatures as percentages in an electorate.

An exploded 3D pie chart where one of the slices has been exploded(separately represented to bring attention)
Source

2

Visualizing large concentrations

Hexbin maps are ideal for showing clusters and dense data points within spatial datasets, providing clarity when scatterplots become overwhelmed with overlapping points.

Doughnut Chart: Central Hole Represents Key Data Information.
Information on the data represented as a hole in the center of a doughnut chart

Source

3

Analyzing spatial patterns

When exploring spatial distributions and detecting hotspots or trends, hexbins offer clear segmentation with colours representing data intensity, making them effective for geospatial density visualization.

1855 Army Volume: Pie chart illustration depicting Eastern army distribution.

Polar chart by Florence Nightingale, 1858, If the death count in each month is subdivided by cause of death, it is possible to make multiple comparisons on one diagram

Source

4

Comparing multiple data layers

Hexbin maps can be layered with other visual elements or time-based data to show changes or comparisons across consistent spatial units.

Types of Hexbin Visualizations

1. Standard Hexbin Density Plot

This is the most common type, where the data space is divided into regular hexagonal bins. Each hexagon’s colour or size represents the count of data points within it. This plot is highly effective for visualizing distributions and clusters in large datasets.

2. Hexbin Heatmap

A variation of the standard hexbin plot, this uses a colour gradient (heatmap) to show density intensity visually. Darker or warmer colours indicate areas with higher data concentrations, helping quickly identify hotspots and patterns.

3. Hexbin Choropleth Map

In this type, hexagons replace irregular geographic regions (like states or districts), providing uniform shapes that help reduce bias from varying area sizes. The color of each hexagon encodes a numeric variable, enabling fairer spatial density visualization.

4. 3D Hexbin Visualization

This advanced variant uses hexagons with height or extrusion to represent quantity, adding a third dimension to the density plot. It enhances perception of magnitude differences across hexagonal bins, commonly used in geospatial and statistical analysis.

5. Interactive Hexbin Maps

These allow zooming and filtering of hexbin data layers, often implemented in web visualizations. They combine hexbin density representation with user interactivity for detailed exploration of spatial data.

When Not to Use Hexbins?

1

When preserving individual data points is essential

Hexbin visualization aggregates points into hexagonal bins, so precise location or value of individual data points is lost. For small datasets or when each data point matters, scatterplots or raw data views are better.

2

For audiences unfamiliar with the concept

Hexbin maps can be complex and less intuitive than simple heatmaps or bar charts, requiring explanation for non-technical viewers.

3

When data is sparse or evenly distributed

If data points are few or uniformly spread, hexbin visualizations offer little added insight and may appear uniformly colored, obscuring patterns.

4

When precise spatial boundaries matter

Hexbin maps divide space into uniform hexagons, which can mask fine geographic boundaries important in detailed spatial analysis.

5

When display space is limited

Hexagons may leave unused gaps in rectangular display areas, limiting efficient space use compared to rectangular binning or other chart types.

Share on

Was this Page helpful?

Get in Touch

Partner with us to bring your ideas to life.

Thank you for your feedback.