iiinova — where your digital self keeps evolving

Aaron Zuspan @aazuspan.dev · 21/02/2025

I made a Github repository a few days ago to automatically track changes to the GNIS database of place names in the US. Apparently it works. #Denali

A git diff showing Denali renamed to Mt. Mckinley by executive order

110

Aaron Zuspan @aazuspan.dev · 10/12/2024

bsky.app/profile/did:... Nothing fancy at all. Turns out Earth's surface color is pretty predictable.

010

Aaron Zuspan @aazuspan.dev · 08/12/2024

The model is a stupidly simple pixel-based random forest trained with a grid of sampled points (below) using downscaled bioclimatic predictors derived from temp and precip (via WorldClim) and stretched MODIS RGB. I also tried predicting in HSV and LAB space, but RGB looked the best 🤷‍♂️

The globe from 3 different angles, showing a dense grid of colored points from dark purple to bright orange, representing annual temperature range.

060

Aaron Zuspan @aazuspan.dev · 08/12/2024

For comparison, here's the actual and predicted modern imagery from MODIS. A climate-only model definitely misses some topographic and soil detail, but seems to capture land cover surprisingly well.

Title: MODIS RGB - Annual Mosaic 2020. Earth from 3 different angles in natural color, using real satellite imagery. It's an annual mosaic, so there's snow and ice around the Arctic circle.

Title: MODIS RGB - Simulated with Modern Climate. Subtitle: Based on WorldClim 2.1 1970-2000 (Fick, S.E. and R.J Hijmans, 2017). Earth from 3 different angles in natural color. Some details are missing, but it looks very much like real satellite imagery of Earth.

230

Aaron Zuspan @aazuspan.dev · 08/12/2024

Am I too late for #30DayMapChallenge Day 14 - A World Map? I trained a model to predict MODIS RGB imagery from modern climate and applied it to modeled paleoclimate data to simulate a 22,000 year old satellite image of Earth

Title: MODIS RGB - Simulated at Last Glacial Maximum (~22k years ago). Subtitle: Basesd on WorldClim 1.4 downscaled CCSM (Hijmans et al, 2005). Earth from 3 different angles in natural color. It looks relatively similar to the modern world, but the northern hemisphere has much more ice and snow. Western Europe north of the Mediterranean, North America north of Kansas, and the Andes range in South America are white. Sea level was lower, so landforms are slightly larger than present day.

4426

Reposted by Aaron Zuspan

Eric Wastl @was.tl · 01/12/2024

This was my tenth(!) year building 25 days of puzzles for #AdventOfCode. You can solve them all for free! Most people write code to solve them, but you can solve them however you like. I hope they help people become better programmers. 🌟 The first puzzle comes out in two hours: adventofcode.com

adventofcode.com

Advent of Code 2024

601122205

Reposted by Aaron Zuspan

scikit-learn @scikit-learn.org · 22/11/2024

Please help us test the first release candidate for scikit-learn 1.6: pip install scikit-learn==1.6.0rc1 Changelog: scikit-learn.org/1.6/whats_ne... In particular, if you maintain a project with a dependency on scikit-learn, please let us know about any regression.

scikit-learn.org

Version 1.6

Legend for changelogs something big that you couldn’t do before., something that you couldn’t do before., an existing feature now may not require as much computation or memory., a miscellaneous min...

23918

Reposted by Aaron Zuspan

Mary Elkington 💙💛🇺🇦 @maryindevon.bsky.social · 13/11/2024

Many fail to understand how the location of receiving stations impacted early data collection of polar orbiting satellites in the early days. That's the circular pattern in the early data. In former life I re-processed 1978-1991 vis/ir data back when Dinosaurs Walked (data on tape reels)

021

Aaron Zuspan @aazuspan.dev · 13/11/2024

Great work! Having an app to explore the data is really useful.

010

Reposted by Aaron Zuspan

Katarzyna Ewa Lewińska @kelewinska.bsky.social · 22/10/2024

We all think we know how much #Landsat and #Sentinel-2 data is in the archives🛰️ 🌍 Global edition 🚨 See our new paper and dataset to check 1982-2023 data availability for your study site: tinyurl.com/yc82epfx #GEE data viewer: tinyurl.com/322e63p2

052

Aaron Zuspan @aazuspan.dev · 13/11/2024

#30DayMapChallenge, Day 12: Time and Space 51 years and 11 million #Landsat scenes, showing global cloud-free (<20%) coverage by path and row since Landsat 1 🛰️

2172

Reposted by Aaron Zuspan

Erwan Rivault @erwanrivault.com · 11/11/2024

#30DayMapChallenge Day 11: Arctic One year of MODIS daily mosaic images Did you know optical satellites like MODIS usually don't capture images over the poles in winter due to lack of sunlight? The "no data" hole grows as we near the winter solstice - and starts closing once daylight returns

23818

Aaron Zuspan @aazuspan.dev · 11/11/2024

Good point - much easier math at the equator! So in Swahili time, the clock is effectively counting how long the sun has been up/down? That's fascinating!

110

Aaron Zuspan @aazuspan.dev · 10/11/2024

Fun fact, I did zero input validation 👍

Text that says "Today at 90000.00° latitude you'll see 12.00 daylight hours. Tomorrow will be 0.0 minutes shorter. You would need to travel 1.9 kilometers to keep the same day length." Meanwhile the map shows you traveling from the north pole to the southern hemisphere.

010

Aaron Zuspan @aazuspan.dev · 10/11/2024

There's also an interactive version where you can calculate travel distance for any date/location www.aazuspan.dev/daylight-hou...

aazuspan.dev

Daylight Hours

Calculate the daylight hours at a given latitude and date, and see how far you need to travel to maintain today's day length.

100

Aaron Zuspan @aazuspan.dev · 10/11/2024

Visualizing how daylight hours change through the year depending on your latitude, for a blog post where I tried to figure out how far you'd need to travel to keep the same day length year-round (spoiler: not very far at first, then REALLY far at each equinox) www.aazuspan.dev/blog/chasing...

2114