John Collins

Earlier posts talked about geometric encoding for geospatial Machine Learning (ML) and Artificial Intelligence (AI) applicaitons, with a focus on Multi-Point Proximity (MPP) encoding. MPP yields conformable encodings (i.e. having consitent size and shape) for any geometric object in a bounded domain. In other words, you could have a

Think about what it takes to solve this problem: Fill in the blank: I took my ___ for a walk because he was barking so much. Most people would guess that the missing word is "dog", but how does one infer that? For starters, you need to understand the

A few months ago I was working in my home office when the house started to shake. At first I thought maybe a big tree fell somewhere nearby – it happens sometimes in the forested area where I live. But the rumbling went on for about 10 seconds, too long to

"A point is that which has no part." So begins Euclid's Elements, a systematic exposition of the principles of geometry, starting from the most basic definitons, proceeding by logical inference to virtually all that was known about the discipline at the time. It would be hard

My previous post talked about Multi-Point Proximity (MPP) encoding: the idea that any Point, LineString, or Polygon can be approximately encoded based on its distance to a set of reference points. The post demonstrated that the method captures some key properties of the encoded shapes, and allows them them to

When I was an undergraduate Geography major in the 1980s, Geographic Information Systems (GIS) was a fairly new discipline. One of my courses actually used what people called "the world's first GIS textbook". People would still debate the relative merits of making maps with computers versus