Site Selection - Geospatial Analtycs

In this straightforward example, we perform a typical geospatial analysis: Site Selection.
We want to open a new Italian restaurant in one of the most competitive markets, New York.
Five commercial spaces available have passed a first human screening, considering the budget and the position(Manhattan).
But now we need some geospatial data to make a solid decision on where to open our Restaurant.
To do this, we use the new KNIME extension Geospatial Analytics, with a bunch of nodes that allow us to retrieve spatial statistics. Specifically, we want to know the following:

How many Italian restaurants are already near each commercial space available (within a 300m Area)?
To answer this question, we use the Open Street Map Point of Interests node (OSM POIs) and the Buffer node to define the radius area.

What are the principal inhabitants features of each Area? What is the socio-economic level, etc.? Are there students?
To fetch this data, the Open Datasets nodes US2020 Census Data and US2020 TIGER Map came to help us.

Then we put it together, generating five potential areas with associated geospatial data. We use this data to calculate a dynamic weighted Score to help us to make the correct decision.

Finally, using the Geospatial View node, we can visualize the five areas with all the metrics and the other Italian restaurants, assigning a colour based on the previously calculated weighted Score. The green the better is our Area to open our new Italian Restaurant.

Geospatial Analytics is fully developed in Python, e.g. the Geopandas library, which was heavily used to write the nodes. All the nodes provided with the extension are the perfect toolkit to apply geospatial technologies in a no-code/low-code way, so also beginners can benefit from this kind of analysis.

External resources

• Center for Geographic Analysis
• Geopandas Documentation
• Request US Census API key (for free)