data maps climate cities @WorldResources, likes dogs, all views my own

Joined December 2011
The state of play, a week into Elon's assault on USAID. USAID is in a state of suspended animation - it has been powered down, but it's not *quite* to the point where it can't be powered back on. What happens next comes down to the courts & Congress. 🧵
26
527
69
1,610
250,508
🚀 We are thrilled to announce the release of the Icechunk storage engine, a new open-source library and specification for the storage of multidimensional array (a.k.a. tensor) data in cloud object storage. Read our blog post about Icechunk here: earthmover.io/blog/icechunk
2
27
12
82
29,384
I'm so excited to finally introduce Fields of The World (FTW!) - the largest & most diverse ML dataset for field instance segmentation in satellite images. FTW has >70k samples from 24 countries (4 continents), with semantic & instance labels + Sentinel-2 RGB-NIR from 2 dates. 🧵
8
71
7
301
27,691
Alex Kovac retweeted
if your company asks privately about why a "critical" feature is missing in an open source project, and isn't willing to pay to have it implemented, it is not, in fact, "critical"
1
8
34
2,606
GDAL 3.9 was released today with a bunch of updates for @GeoParquet, including support for spatial filtering in the upcoming GeoParquet 1.1 version! Credit to @EvenRouault and other GDAL contributors 🙇‍♂️! github.com/OSGeo/gdal/blob/v…
1
27
1
109
7,742
Alex Kovac retweeted
I appreciate the nod to "File over app" from @mbostock and the @observablehq team in the latest announcement. It's so cool that a Markdown file with code blocks can be the source for complex data visualizations and dashboards. This means the files are interoperable with @obsdmd. Here I am running an Observable site from Obsidian
9
29
3
473
70,925
We need #machinelearning for satellite data ("SatML") to address planetary-scale challenges 🌍 but mainstream ML is ill-suited to SatML data & contexts. It's time we recognize satellite data as a distinct modality for ML research to unlock its potential 🦾arxiv.org/abs/2402.01444
3
73
3
304
26,724
someone should create a collection of implementation examples and success stories for companies who have migrated off paid service APIs to open-source, self-hosted solutions (or open-source solutions on a cloud-hosted platform) everyone is learning the same patterns in silos – at Palo Alto, CA
4
5
26
7,799
open sourced a small cost calculator: estimate the monthly bill of running @protomaps on AWS or Cloudflare based on usage, compared to Google Maps and hosted base map APIs. Now part of the Documentation site! docs.protomaps.com/deploy/co…
2
10
3
74
7,540
Alex Kovac retweeted
A comprehensive list of 9,043 #NASA Earth science data products available in TSV and JSON formats. Integration into #leafmap for interactive search and visualization is coming soon 🗺️🌎 ➡️ github.com/opengeos/NASA-Ear… @NASAEarthData #opendata #geospatial #earthobservation
12
49
1
234
17,414
Alex Kovac retweeted
We’re excited to publish our data on @source_coop, a utility dedicated to making it easier to share and access data using open standards. Thanks to @OurRadiantEarth for this 🙏 🌐 Use to measure land, carbon, and biodiversity impacts from agriculture: beta.source.coop/repositorie…
1
11
1
54
5,744
Taking a quick look at GLanCE land cover training data with lonboard for the #30DayMapChallenge github.com/kovaca/maps/blob/…
A year of vehicle collisions in NYC, with radius determined by number of pedestrians and cyclists injured, and colored by time of day. Made in Python with #lonboard. #30daymapchallenge Reproduce it with this notebook: github.com/developmentseed/l…
1
4
1
13
2,450
"I’m so excited about this: we now have the ability to entirely self-host vector maps of any location in the world, using openly licensed data, without depending on anything other than our own static file hosting web server. " - @simonw perfect use case for extract+basemaps!
5
37
3,397
1
3
243
1
68
Alex Kovac retweeted
To help you navigate the expanding universe of cloud-native geospatial technologies, we’re excited to introduce the Cloud-Optimized Geospatial Formats Guide. Visit the guide to get started guide.cloudnativegeo.org
3
31
95
8,129
Alex Kovac retweeted
Using GDAL for data visualization. Wherein I try to explain the difference between "imagery" and "data", with the help of two radically different pictures of the same place with the *exact* same instrument: medium.com/@robsimmon/a-gent…
3
27
1
166
19,557