Technologies: Python, Ruby, C, C++, C#, JavaScript, TypeScript, PowerShell, Flask, SQL, PostGIS, Shapely, Unity, Unreal Engine, multiple assembly/machine languages, Windows user code and kernel drivers, Google Maps and other map APIs, geographic and airspace data
Hi, I'm Michael Geary. I've programmed in many languages and environments over the years. Some of my current interests are:
• Developer experience. I love helping my fellow developers solve problems, and building tools to make their jobs easier and more enjoyable.
• Aviation and geographic data. For example, airspace and obstacle data importers for Wing; election results and voter information maps for Google; many interactive maps for other companies.
• Hardware interfacing. In a way, I am a "full stack" developer, but my stack may involve a front end to a piece of hardware rather than the cloud. I first got into programming via ham radio, so RF hardware remains an interest.
• Designing and building APIs. Too often an API is designed by exposing the internals of whatever system provides the API. My philosophy is the opposite: start with the apps. I like to build a series of sample apps before starting on the API. This way I can imagine what API will make those apps and others like them easy to build.
• Talk with users! I don't like to sit in a back room cranking out code. I want to make sure it's the right code for what my users need, and that it's easy to maintain and improve as we learn more about what they want.
Which would violate FAA regulations if it was powered on (as it obviously was):
"When portable electronic devices powered by lithium batteries are in checked baggage, they must be completely powered off and protected to prevent unintentional activation or damage."
How exactly do we know it was in checked luggage vs carry on luggage compartment.
Without tools, its not exactly easy to point-point a Bluetooth signal. Nor are passengers meant to be roaming around the aircraft whilst in flight (i.e to access carry on luggage compartment and turn it off).
Of course there were smoking and non-smoking sections on airplanes. The same air recirculated through the entire airplane, and the non-smoking section began the very next row after the smoking section.
One task where GeoJSON falls down is simplification of a group of polygons with common boundaries, e.g. the 48 conterminous US states. If you start with a highly detailed set of polygons, you need to simplify them for practical display in an online map.
GeoJSON doesn't encode the fact that the boundary points are common between adjacent polygons. When you simplify those polygons, each one is handled separately, and you end up with "slivers" where the boundaries are misaligned:
TopoJSON solves this by encoding each such boundary only once. So when you simplify the polygons, they are all done together, and the same simplification applies to adjacent polygons. No more slivers!
GeoJSON is not TopoJSON. Saying that is "falling down" is like criticizing a zebra for not being a giraffe. GeoJSON is a mapping of the (non-topological) "simple features" model into JSON, full stop. It does that fine.
Yes, the same "slivers" problem occurs when you try to simplify features in any format that uses individual polygons, such as shapefiles or whatnot. That's the only case I was referring to.
I don't think I would trust a zebra or a giraffe for this task either.
Is this actually GeoJSON falling down, or decades of convention extended to JSON? Topology is great, but it is sidestepped by Shapefile/WKT/WKB/etc, in favor of independent primitives like POINT, LINE, POLYGON. If GeoJSON did not exist as a new JSON GIS data format encoding these primitives, TopoJSON would not have "replaced" it, due to the added mis-match with other non-topological formats.
From what I can tell, the top criticism of GeoJSON is the under-enforced winding order specification, and crossing the antemeridian.
Similarly, typical map APIs like the Google Maps API accept GeoJSON and not TopoJSON. I was not suggesting TopoJSON as a replacement for GeoJSON, but as a complement to it. With the tools on the TopoJSON GitHub, you can have GeoJSON input and output, but convert to TopoJSON for the simplification step to avoid the "slivers" problem.
The problem is simplification. Suppose two regions share a border with some nonlinear points a, b, c, d. Simplifying the polygon for the first region might yield a, b, d while the second yield a, c, d. This creates gaps or overlaps between the two regions.
But what is the border? Set the border to what it actually is, not a simplification of it. The state of Colorado is formally a 697 sided polygon, don't simplify it to a rectangle.
This is not what OP is describing. It is very common to simplify objects for decreasing boundary objects by orders of magnitude. GeoJSON is missing correlation when you do that. Simplifying country objects from a GeoJSON source could lead to a gap between the country borders. So you either have poor representation or a longer pipeline to convert objects to an amenable object set. It also breaks idempotency in some regards.
To do the simplification, you detect shared borders, simplify and generate polygons again.
That doesn’t make topojson inherently superior. You can convert back and forth and for many applications geojson is easier to process.
Yes, you could write code to do that. Or use the utilities provided in the TopoJSON GitHub and let them do it for you: convert to TopoJSON, simplify, convert back to GeoJSON. They have already written all the code for you.
It depends on what purpose you are using the polygons. In an online map you need to simplify way down. Consider these Colorado maps at two different zoom levels:
Even the one zoomed in on the state appears to use maybe 15-20 vertices max.
In the second one, if I squint real hard I can just barely make out one slight dogleg on the western border and one on the south. And that is partly because I knew to look for them in the zoomed-in map.
If we use, say, the Census TIGER/Line boundary definitions for the states, we are probably talking about hundreds of thousands of vertices, perhaps millions. You won't be using those in an online map without simplifying.
The Texas border with Mexico is formally down the centerline of the Rio Grande, even as the river moves (ignoring fiddly complications). Even if you could somehow take a perfect snapshot of it at a given time, you'd run into the coastline paradox when sampling it.
So don’t simplify the shapes on their own. Geojson is a storage and exchange format, you can still convert it to other formats if you want to modify it.
I think what the original comment is pointing out is that GeoJSON lacks a concept of a shared boundary. Shared boundaries expressed in GeoJSON get around that by duplicating data. Whenever data is duplicated, there's a risk that the copies will not be exactly the same. That makes the task of modification more challenging given that the real world is full of messy data, like duplicates not matching.
20-25 years ago I worked a lot with map data from otherwise high quality, and sometimes authoritative, sources like the USGS and NOAA that had this non-identical shared boundaries problem (in formats other than GeoJSON). If the format doesn't allow such mistakes to be expressed, then they have to fix their data to publish it in said format.
Sure, but not every format is useful for everything. Geojson is great if you want a simple way to express a shape to show on a map. It’s like criticizing CSV because people put strings in choice value fields instead of doing a foreign key to another table. That’s just not what the format is used for.
I'd take your point further... No format is useful for everything. But we have to be aware of the trade-offs of each format (or language or tool or ...) in order to make the right choice of what to use for a given use case. We do that by sharing knowledge of where a given tool succeeds and where it falls down. Pointing out something a format doesn't handle well is not condemning that format for all use cases (I happily choose GeoJSON over other formats for many things).
Partly true, but don't blame GeoJSON. Blame the data model.
GeoJSON is firmly rooted in the "simple features" model of spatial data. Sometimes called the "vector data model", this is ubiquitous in GIS. Each geographic entity (aka "Feature") has a single geometry and many non-geometry attributes. Each feature is independent.
The vector data model (for better or worse) is the basis of many systems because it fits the tabular/relational style so closely. What is a feature but a row in a table plus a special column describing its geometry? Topological relationships are ignored by design.
TopoJSON, ESRI coverages, the internal OpenStreetMap data model, and a few others are notable exceptions. They explicitly handle spatial relationships, at the cost of making the model unintelligible to row-based processing.
I like TopoJSON and have used it in projects. But it's weird to set it up as opposition to GeoJSON. It's a complement. GeoJSON is a general data format meant to replace uses of ESRI Shapefiles and other complex formats. TopoJSON is more of a solution for a particular application need.
Is there much work developing or using TopoJSON these days? I haven't seen much about it in a few years.
To be clear, I'm not suggesting TopoJSON as an alternative to GeoJSON. I like GeoJSON and was loosely involved with the working group that created and updated its spec.
I'm just saying that for the specific task I mentioned GeoJSON or any format such as shapefiles that store polygons individually naturally leads to the "sliver" problem.
A nice processing pipeline is:
1. Convert GeoJSON to TopoJSON.
2. Run the simplification on the TopoJSON.
3. Convert the resulting TopoJSON back to GeoJSON.
The TopoJSON GitHub has tools for each of these steps.
When I was a very young kid in Eugene, Oregon, we always kept a supply of Chet's Tamales in the freezer. They always had one black olive hidden somewhere in the middle. It wasn't just a tamale, it was a treasure hunt!
In first grade, we took a field trip to Chet's factory. It was so interesting to see how they made tamales in quantity–and they sent us each home with a free tamale.
Another Oregon treat is Tillamook cheese. My family went on one of their tours. They still offer tours today, but you are in a glassed-in area on the second floor overlooking the line. Back then, we got to walk right up to the vats of cheese curd. They trusted us (and instructed us!) to not poke our fingers in.
Much more recently, a friend who works at La Terra Fina in Union City, California took me on a private tour of their manufacturing plant. You may have seen LTF's quiches and dips at stores like Safeway and Costco, and private label versions at other stores.
I think they were making the Artichoke-Jalapeño dip that day. What struck me was the contrast between the first part of the production line and the rest. They start with huge blocks of cream cheese, industrial size cans of artichokes and jalapeños, and dump them into a giant mixer by hand.
Once a batch is mixed and gets a taste test, the rest of the line is high speed and highly automated. Plastic tubs come through and get the dip squirted into them, the plastic seal and top goes on, and then a labeling machine attaches each label.
Pro tip: If you like their dips, try them warm. My friend had not actually done this, so I asked Claude for a recipe:
---
One time a friend served some La Terra Fina dip warm at a party. I'd only had it cold before, and it was a revelation. I forgot to ask for his recipe, but I believe he warmed it in the oven for a while and then under the broiler for a bit to lightly brown the top. What would be a good temperature and time for the first step, assuming a typical shallow casserole pan?
---
La Terra Fina dips warm up beautifully — the cream cheese base gets silky and the flavors meld in a way cold just can't match.
For a shallow casserole dish, I'd suggest:
Oven step: 325°F for about 20–25 minutes. Low and slow is the move here — you want it heated through without the dairy breaking or getting grainy. A shallow dish speeds things up compared to a deep one, so check at 20 minutes. You're looking for it to be bubbling gently around the edges.
Broiler step: 2–4 minutes on high, watching closely. The top should get lightly golden with a few darker spots — that slight caramelization on the cheese and any onion bits is where the magic happens. Don't walk away during this part.
A few notes:
• Pull it from the fridge 15–20 minutes before baking if you can, so it's not stone cold going in
• The spinach artichoke and artichoke jalapeño varieties both do particularly well warm
• Serving with something sturdy (crostini, pita chips, thick tortilla chips) beats thin crackers when it's hot and scoopable
The broiler browning is really what elevates it — that textural contrast between the creamy interior and the slightly crispy top is what probably made it feel like a revelation.
Technologies: Python, Ruby, C, C++, C#, JavaScript, TypeScript, PowerShell, Flask, SQL, PostGIS, Shapely, Unity, Unreal Engine, multiple assembly/machine languages, Windows user code and kernel drivers, Google Maps and other map APIs, geographic and airspace data
Hi, I'm Michael Geary. I've programmed in many languages and environments over the years. Some of my current interests are:
• Developer experience. I love helping my fellow developers solve problems, and building tools to make their jobs easier and more enjoyable.
• Aviation and geographic data. For example, airspace and obstacle data importers for Wing; election results and voter information maps for Google; many interactive maps for other companies.
• Hardware interfacing. In a way, I am a "full stack" developer, but my stack may involve a front end to a piece of hardware rather than the cloud. I first got into programming via ham radio, so RF hardware remains an interest.
• Designing and building APIs. Too often an API is designed by exposing the internals of whatever system provides the API. My philosophy is the opposite: start with the apps. I like to build a series of sample apps before starting on the API. This way I can imagine what API will make those apps and others like them easy to build.
• Talk with users! I don't like to sit in a back room cranking out code. I want to make sure it's the right code for what my users need, and that it's easy to maintain and improve as we learn more about what they want.
Remote: Yes, or hybrid if nearby
Willing to relocate: Possibly
Technologies: Python, Ruby, C, C++, C#, JavaScript, TypeScript, PowerShell, Flask, SQL, PostGIS, Shapely, Unity, Unreal Engine, multiple assembly/machine languages, Windows user code and kernel drivers, Google Maps and other map APIs, geographic and airspace data
Résumé/CV: https://www.geary.com/resume.html or https://www.geary.com/resume.pdf and https://www.linkedin.com/in/michaelgeary/
Email: mike@geary.com
Hi, I'm Michael Geary. I've programmed in many languages and environments over the years. Some of my current interests are:
• Developer experience. I love helping my fellow developers solve problems, and building tools to make their jobs easier and more enjoyable.
• Aviation and geographic data. For example, airspace and obstacle data importers for Wing; election results and voter information maps for Google; many interactive maps for other companies.
• Hardware interfacing. In a way, I am a "full stack" developer, but my stack may involve a front end to a piece of hardware rather than the cloud. I first got into programming via ham radio, so RF hardware remains an interest.
• Designing and building APIs. Too often an API is designed by exposing the internals of whatever system provides the API. My philosophy is the opposite: start with the apps. I like to build a series of sample apps before starting on the API. This way I can imagine what API will make those apps and others like them easy to build.
• Talk with users! I don't like to sit in a back room cranking out code. I want to make sure it's the right code for what my users need, and that it's easy to maintain and improve as we learn more about what they want.
Open to full time or contract.
I look forward to talking with you!