Who can use this feature
Owners
and Editors
of projects within Pro
and Pro +
workspaces
Selection requirements for tool to work
At least two point layers (minimum two features in each) AND
A dataset
The Classify dataset
tool in GeoNadir allows you to quickly perform Random Forest classification using training points you define. This enables you to categorise land cover, vegetation types, or other features in your dataset with high accuracy—turning raw data into actionable insights in just a few clicks.
Step by step
To build your classification, follow these steps:
Create point layers as training sites of your features of interest.
You need to have at least two layers, and each layer must have at least two features in it.
The points need to overlap with the dataset you are going to classify.
We recommend a minimum of 30 points per feature / class of interest. 70% of these points will be selected at random to train your classification, and the remaining 30% will be used to validate it.
Try to capture the natural variability of your feature when you select these points (e.g. if you are interested in a certain tree species, don't just use a single tree for all of your points).
For best results, use the colour styling for your points that you would like to see on your final classification.
In the table of contents, select your point layers AND the dataset you are going to classify (hold ctrl or cmd as you click to multiselect).
From the top menu bar, click the '
classify dataset
' button.Select a layer for the algorithm to include in the classification.
Click run
You will be able to see your classification in the table of contents of your project, attributed with 'Processing' as below.
Depending on the size of your dataset, the classification process can take some time, so please be patient. But don't worry, you can continue to work on your project in GeoNadir while it's processing. Or you can even close the project, browser, and your computer and it won't disrupt the processing! It's all done in the cloud, so as soon as you've set it to run, you can relax and we'll take care of it for you.
When the classification is complete, it will automatically appear on your map, and you will see the updated status in your table of contents - see below for an example.
+++THE FOLLOWING FEATURES ARE COMING SOON+++
Calculating classification statistics
Curious to delve into the statistics of your newly created classification? Follow these steps:
Select your classification in the table of contents
From the top menu bar, click on the
Calculate statistics
button
A pop up will appear with a range of statistics for you to view and interact with.
Understanding the data
Click on any graph to expand it - this will make it easier to see and interact with.
You can show or hide the results for each class on the graphs by clicking its name in the legend.
Total area
The Donut Chart visually compares the area coverage of each category in the classification. The total area of all classes is displayed in the center. Hovering over a segment of the graph reveals the class name and its area. This helps you quickly understand how different classes contribute to the overall area distribution.
Overall accuracy
Overall accuracy is a measure of how well your classification performed, shown as a percentage. It’s calculated by comparing all your sample points—both training and validation—to the results of the classification. We check how many points were correctly classified and divide that by the total number of points.
For example, if you created 100 sample points and 87 of them were correctly matched to the right class in the final classification, your overall accuracy would be 87%.
In GeoNadir, we automatically split your input sample points: 70% are used to train the model, and 30% are used to test it—but the final accuracy is based on all 100% of your points to give you a clear picture of how well the model performed overall.
Sankey chart
The Sankey chart helps you see how well each class in your dataset was classified.
Each colored bar on the left shows the true class of your sample points, while the bars on the right show how those points were predicted by the classification model. The lines (or “flows”) between them show where the points went—correct matches flow straight across, and misclassifications flow into the wrong class.
The thicker the line, the more points it represents. You can hover over each bar or line to see the class name and number of points.
This is a great way to spot which classes were most accurate and where confusion occurred between similar-looking areas.
Compare
The Lollipop chart gives you a quick visual comparison of classification results per class. You can switch between different metrics to explore how well each class performed:
Class accuracy – the percentage of points in each class that were correctly classified
False positives – points incorrectly predicted as this class
False negatives – points that belong to this class but were misclassified as something else
Total area – the total area that the model assigned to this class. The statistics unit for the area measurements (e.g. m2, ft2) will be the same as your project units. If you would like to change your measurement units, follow these instructions.
This makes it easy to spot which classes performed well and where the model may have over- or under-predicted.
Below the chart, you'll find a summary table showing the same statistics in detail, so you can dig deeper into the numbers if needed.