Hat Tip to arstechnica for this article

This is a classic example of why we need to question where our data comes from. Once you stop to think about it, there are a number of possible explanations as to how this island came to be on charts and maps when it most likely never was. Effective spatial data analysis needs people’s brains to actually check out any anomalies thrown up when combining datasets. Algorithms can alert us to there being something that ‘needs a closer look’ but the actual looking is probably best done by someone who understands geographic information.

Similarly, any response to a spatial data anomaly must be informed by a number of factors, including things such as:

• where the data was sourced from
• who collected it and why
• what we are using it to do

In some instances a conservative response is the best way to go, in others, we may get away with ignoring the fact that an anomaly was even found. What we shouldn’t do is assume that there is a “correct response” that will then apply for all possible instances – real life just doesn’t work that way.

Unless you happened to be, or know, an oceanic vulcanologist, ‘floating pumice islands‘ are probably not the explanation that comes to mind!