2022-10-26 16:10
In the first installment of this three-part blog series, we summarize some of the latest research on automated building footprint extraction.
The post Automated Building Footprint Extraction… Read More
Blog Directory > Business Blogs > Companies Blogs > Azavea Atlas companies Blog >
Azavea Atlas Blog
azavea.com/blog
Tags:
introducing
encourage innovation internally
rights legislation
support
encourage innovation
census counts
machine learning workflow
responsive application
philadelphia
count
The Azavea Atlas blog is our take on how geography impacts our daily lives.
2022-10-11 14:34
A recap of Azavea's partnership with the Philadelphia Water Department to support Philadelphia's Green City, Clean Waters plan.
The post 14 Years of Helping to Manage Stormwater in Philadel… Read More
2022-10-03 21:32
We outline our 10% time program in detail, highlight some notable examples and themes, and describe the impact of the program.
The post Azavea’s 10% Time Program: How We Encourage Inno… Read More
2022-09-28 15:34
In this blog we demonstrate how an active learning approach can boost machine learning model performance with the human-in-the-loop workflow.
The post A Human-in-the-Loop Machine Learning Wo… Read More
2022-09-22 16:34
In order to benchmark efficiency, we take a deep dive into Zarr and Parquet data retrieval to compare performance on various time scales.
The post Benchmarking Zarr and Parquet Data Re… Read More
2022-09-08 17:48
A look at where restrictive voting rights legislation and gerrymandered redistricting plans are being passed.
The post A Look into the New Decade of Voting Rights Legislation and Redistricti… Read More
2022-08-24 20:33
Due to Next.js' ability to populate webpages in remote areas, we used it to build a decision-support tool that conveys landslide risk.
The post Building a fast-loading and responsive applica… Read More
2022-08-17 20:14
We donate a portion of our profits each year to support open source projects nominated by our team.
The post 1% For Open Source: Financial Support for Tools We Use appeared first on Azavea Read More
2022-08-03 19:57
What is the Climate Change Learning Group? At Azavea, we’ve woven climate initiatives into the identity of our business. As...
The post Introducing Azavea’s Climate Change Learni… Read More
2022-07-25 21:10
Population outside “housing units” The US Census counts most people in their residence (e.g. a house, apartment, or mobile home)...
The post How the Census counts people living i… Read More
2022-05-03 16:17
20 years on, Azavea has never taken on investor capital. Our CEO, Robert Cheetham, explains why this is the case.
The post Why We Haven’t Taken on Investment appeared first on Azavea Read More
2022-04-28 17:20
A recent project required us to implement an interactive map of the United States with a custom counties layer. This is what we learned.
The post How to code-split GeoJSON layers for your Ma… Read More
2022-04-18 13:12
This blog explores the direct classification approach to change detection using our open-source geospatial deep learning framework, Raster Vision, and the publicly available Onera Satellite… Read More
2022-04-08 16:54
NumFocus is a nonprofit that supports many open source tools used in Azavea's projects. Here, we highlight how they have supported our work.
The post Highlighting NumFocus Projects: How Open… Read More
2022-03-30 16:27
To address the disparity in access to funding resources, we partnered with Headwaters Economics to develop the Rural Capacity Index.
The post A Tool to Highlight Underfunded and Under-resour… Read More
2022-03-23 14:23
Netlify is a platform for web developers and designers that offers hosting and serverless backend services. Here, we provide Azavea's top three use cases for it and its benefits for our soft… Read More
2022-03-03 20:39
All of our developers are on Mac or Linux, but we can still do Windows work using .NET Core. Using this open-source technology we can develop applications for organizations that are restrict… Read More
2022-02-25 19:59
At Azavea we strive to create a diverse, equitable, and inclusive work environment. As we consider how to thoughtfully grow and strengthen our workplace, we reflect on what we have learned o… Read More
2022-02-04 21:05
As one of seven pilot programs to address environmental issues in Africa, Azavea trained student workers to label satellite imagery using GroundWork and created a machine learning model to i… Read More
2022-02-02 19:23
Azavea's CEO Robert Cheetham provides 6 trends he foresees in geospatial this year. These predictions are grounded in Robert's personal experience and perspective as Azavea CEO.
The post 2… Read More
2022-01-10 21:21
2021 brought a lot of challenges to tech companies and many have concerns leading into 2022. Considering how much we learned from 2021, as the year came to a close we gathered learnings from… Read More
2021-12-20 22:14
We’ve seen a trend in requests from potential clients. Organizations are bringing us complex, built-in-house Excel spreadsheets and asking us to convert them into web-based decision-su… Read More
2021-12-07 17:57
DistrictBuilder, Azavea’s free redistricting tool, recently held a competition in partnership with the Public Mapping Project to encourage more participation in the redistricting proce… Read More
2021-11-29 18:40
The Case for User Experience Design and Visualizing Climate Data The world is getting hotter, faster. The ten warmest years...
The post Partnering with Probable Futures to Visualize Climate… Read More
2021-08-02 17:22
Azavea is releasing a dataset consisting of 32 unique Sentinel-2 tiles with cloud labels produced by humans.
The post The Azavea Cloud Dataset appeared first on Azavea Read More
2021-07-21 10:47
Using open source data and easily customizable software, Azavea worked with PeopleForBikes to improve city transit networks.
The post Improving City Transit Networks through Data and Public… Read More
2021-05-04 01:28
We're launching a library called Loam. Loam allows GDAL to be used in client-side code in a web application. Loam wraps a version of GDAL compiled to WebAssembly and makes the GDAL API and u… Read More
2021-04-27 16:09
SAR imagery is having a moment. In this blog we explore what exactly it is, why it is so special, and tips for labeling it.
The post Labeling SAR Imagery for Machine Learning: A Beginners Gu… Read More
2021-04-26 13:19
This release presents a major jump in Raster Vision's power and flexibility. The newly added features allow for finer control of the model training as well as greater flexibility in ingestin… Read More
2021-04-05 19:12
STAC is a specification for enabling online search and discovery of geospatial assets. This post walks through getting started with a number of STAC APIs.
The post Getting Started with STAC… Read More
2021-03-31 12:47
Need to create a training dataset that contains multiple images? GroundWork launches "Campaigns" to help you handle large datasets for machine learning.
The post GroundWork Launches Campaign… Read More
2021-03-25 15:59
In February, we learned more about PostgreSQL indexing. Casey Cesari learned about speeding up fuzzy match searches with tri-gram indexes, and James Santucci learned how much he didn't know… Read More
2021-03-08 15:01
Azavea partnered with Facebook and Ladysmith to make an engaging platform that makes data from a massive gender survey actionable.
The post Making Gender Data Actionable appeared first on Az… Read More
2021-03-02 19:52
Azavea joins the Stripe Climate effort and will contribute 2% to carbon removal technologies as a part of our commitment to the environment.
The post Azavea Joins the Stripe Climate Effort f… Read More
2021-02-08 19:30
We compare the results of two machine learning models that detect clouds in Sentinel-2 satellite imagery and share pointers about models you can try for yourself.
The post Cloud Detection in… Read More
2021-02-01 16:38
In December, we learned about planning five years of a project all at once, superpowered performance debugging with tracing, and tracking down the one bad part of gigantic single line JSON d… Read More
2021-01-25 18:13
k6.io provides a flexible base for load testing with a convenient scripting language, and the quickstart docs will get you pretty far, but testing with a session of TMS requests had some uni… Read More
2021-01-18 15:55
Hear from labeling competition participants on why this diverse group of people came together, from across the world, to collaborate on a hallmark training dataset compliant with the STAC st… Read More
2021-01-06 14:50
2020 was awful. Who was accessible changed radically. We, and the people around us, by necessity took on different roles. Including at work.
The post A Day in the Work-Life in 2020 appeared… Read More
2020-12-21 20:42
This Month We Learned about people-first hiring and onboarding and using nix-shell for consistent development environments.
The post This Month We Learned — November 2020 appeared firs… Read More
2019-12-16 16:50
What are our committees and what do they do? Hear from Robert and Azaveans what each of our committees are and why they matter.
The post Committees at Azavea appeared first on Azavea Read More
2019-12-14 02:25
How accurate are our supervised machine learning models and what are they really doing? We offer 3 tips to help you better understand these models.
The post Three Ways to Get Into the &ldquo&hell…Read More
2019-12-12 18:42
Working with frontend state can be challenging. With TypeScript, thoughtfully constructed types can help prevent bugs by making bad states unrepresentable. Let's explore a common use case an… Read More
2019-12-10 06:57
ML's predictive powers are driving a rage for deep learning in the crisis management and disaster relief industries. How can these powers be harnessed for ethical machine learning?
The post… Read More
2019-12-09 13:39
Leadership is an activity, not a position. We developed a committee system in 2016 to provide leadership opportunities for all of our colleagues and to enhance our work space.
The post Expan… Read More
2019-12-05 16:55
The Cicero Team often relies on local news websites to keep our elected official data up to date. However, local news is on the decline and websites are harder to navigate. This post discuss… Read More
2019-12-03 13:40
Ten years ago we started a charitable contributions program. We developed a program that would increase our impact and expand employee ownership.
The post 10 Years into Azavea’s Charit… Read More
2019-11-25 18:01
Machine learning on satellite imagery is revolutionizing disaster relief. What does ethical machine learning mean in this field?
The post Ethical Machine Learning for Disaster Relief: Avoidi… Read More
2019-11-22 16:39
We're investing heavily in the STAC specification - including building a STAC-compatible Python library and server as well contributing to the Label Extension. We're hoping this work will he… Read More
2019-11-05 16:30
Today, the availability of satellite imagery still far outpaces our capacity to analyze it, but machine learning and tools like Raster Vision are helping.
The post An Introduction to Satelli… Read More
2019-11-04 19:36
PySTAC is a Python library for reading, writing, and manipulating SpatioTemporal Asset Catalogs. PySTAC 0.3 is now released and ready to use!
The post Introducing PySTAC: A Core Library for… Read More
2019-10-29 20:09
GeoTrellis 3.0 includes feature additions and improvements that make it easier to read raster data from a variety of formats and sources, and support COG's.
The post GeoTrellis 3.0 Release a… Read More
2019-10-08 16:20
Read about our journey to hiring an outsourced data labeling firm and how we've found a partner in Cloud Factory.
The post Azavea and CloudFactory: Partners on Quality Training Data and Soci… Read More
2019-10-01 15:16
STAC is creating an ecosystem of interoperable spatiotemporal assets. Learn how Azavea has contibuted and about future steps for the specification.
The post STAC: Creating an Ecosystem of Sp… Read More
2019-09-26 18:50
Using R and QGIS to analyze substandard housing in Philadelphia with open data. We used open data to identify violations, evictions, and illegal rentals.
The post Housing & Landlords: Us… Read More
2019-09-13 17:24
We trained remote computer vision workers to provide data labeling for machine learning projects. Here's what we learned.
The post Is This a Crosswalk?: 5 Takeaways from Training a Data Lab… Read More
Putting Native American Voters On The Map: Using Cadastral Data To Geocode Non-Traditional Addresses
2019-09-12 13:43
We used cadastral land survey data to geocode previously unmappable Native American voters in Montana.
The post Putting Native American Voters on the Map: Using Cadastral Data to Geocode No… Read More
2019-08-30 17:09
We used transfer learning to teach a model to take advantage of multi-band imagery without discarding the original RGB pre-training. This resulted in significant performance improvement.
The… Read More
2019-08-30 13:37
To deal with issues of apparel facility list data quality and scale quickly and efficiently we need a machine learning tool that can capture the knowledge of domain experts, find commonaliti… Read More
2019-08-27 14:20
Temperate will soon incorporate rural areas into its climate planning capabilities.
The post Temperate Takes a Rural Approach appeared first on Azavea - Beyond Dots on a Map Read More
2019-08-07 12:13
Since its launch on March 28, the Open Apparel Registry (OAR) has grown to include over 18,300 facilities in 92 countries. We’ve already heard of a few fascinating use cases where data… Read More
2019-08-05 20:25
How do noisy labels affect the accuracy of a deep learning model? We added different amounts of noise to the SpaceNet Vegas buildings dataset and trained some models to find out.
The post Us… Read More
2019-07-31 12:26
How accurate of a machine learning model can you make? It depends on how we decide to define "accurate".
The post Lies, Damned Lies, and Accuracy Metrics appeared first on Azavea - Beyond Do… Read More
2019-07-23 12:35
In this blog we look at how urban-rural differences play out in the way elected officials adopt social media and hope to shed light on this supposed wedge in a divided country.
The post Expl… Read More
2019-07-10 12:19
Open data and open standards can play a central role in providing safe, equitable, and efficient transportation for everyone. The scooters are coming. We should demand data this time.
The po… Read More
2019-07-03 19:55
Raster Foundry and GeoTrellis now support WMS and WCS standards, enabling streamlined workflows that utilize multiple data sources.
The post Introducing WMS and WCS Support for GeoTrellis an… Read More
2019-07-01 13:45
Many U.S. cities opt for spring elections. We tracked almost 60 local elections happening throughout the U.S. since March. We discuss partisan trends and elected official turnover rates.
The… Read More
2019-06-04 14:10
Employee feedback makes our office space and practices better. We implemented Start-Stop-Continue in 2011 to solicit robust and anonymous employee feedback, and have made significant changes… Read More
2019-06-04 00:13
In partnership with Downstream Strategies, we created MUB Monitor - a comprehensive GIS-based tool that helps water professionals track spills, assess watershed threats, and make informed de… Read More
2019-05-31 12:54
Here are 5 ways companies can make the transition back to work smoother for working parents.
The post 5 Ways Company Leaders can Support New Parents in the Workforce appeared first on Azavea… Read More
2019-05-30 17:47
Utilizing earth imagery to achieve all 17 UN SDGs by 2030 will take considerate effort. In order to do this effectively, we must include training and capacity building in our solutions.
The… Read More
2019-05-20 20:07
As a 10% time project, we replicated a small piece of the Raster Foundry backend code in Haskell, using servant for the REST interface and postgresql-simple for database interaction.
The pos… Read More
2019-05-14 19:12
We made a quick election calendar using the Cicero database and Observable Notebooks. This tutorial shows how you can replicate using D3.js.
The post Make an Election Calendar with D3.js app… Read More
2019-05-02 15:01
All around the country boundaries separate neighborhoods with high and low life expectancy. We used python to find the most extreme examples.
The post Analyzing Spatial Patterns in Life Expe… Read More
2019-04-25 13:56
The Cicero database is expanding to cover elected officials and electoral districts in 50 new Canadian cities.
The post Access Local Elected Official Data for Canadian Cities appeared first… Read More
2019-04-23 14:23
Cloud-Optimized GeoTIFFs (COGs) are geoTIFFs hosted on a cloud or file server, and are optimized for remote reads. They proved useful in a recent project.
The post Using Cloud-Optimized GeoT… Read More
2019-04-17 13:57
This case study showcases how Temperate is uniquely poised to walk cities through the confusing process of conducting a climate vulnerability assessment.
The post Blacksburg, VA Finds Their… Read More
2019-04-16 13:49
Scoring Philadelphia City Council districts on assets and risks using a weighted spatial analysis model in R and Python.
The post Scoring Philadelphia’s City Council Districts for Chil… Read More
2019-04-15 18:01
This release of Raster Vision includes bug fixes, an easier setup, improved performance, and the ability to train models off of labels in OSM.
The post Raster Vision 0.9 Release Candidate ap… Read More
2019-04-01 13:05
Aster Vision is an open source machine learning library for analyzing huge troves of astrospatial data and finding habitable planets around nearby stars.
The post Aster Vision – A New… Read More
2019-03-28 14:38
We are excited to announce the launch of the Open Apparel Registry, an open source global map of garment producing facilities.
The post Introducing the Open Apparel Registry appeared first o… Read More
2019-03-11 21:00
Idris is a pure, statically-typed functional language with a powerful type system. Let's explore writing code in Idris using type-driven development and interactive editing.
The post The Pow… Read More
2019-03-07 13:00
Tree-shaking lodash can reduce the size of your JavaScript bundle, but it requires that a few conditions are met along the way to implementing it.
The post Lessons on tree-shaking Lodash wit… Read More
2019-03-06 18:59
Last month we attended an activitst conference and learned a few things that we thought might be helpful to others in the political advocacy space.
The post 5 Tips to Making The Most of It… Read More
2019-03-04 16:52
TileJSON.io is an open source project by Azavea. It is an easy way to view and share raster tile sets using slippy map endpoints.
The post Introducing TileJSON.io, A Fast and Easy Way to Vie… Read More
2019-02-28 03:15
We're working with the Inter-American Development Bank to improve the GIS capacity of Guyana with tools built to extract OpenStreetMap data.
The post Enhancing GIS Capacity with OpenStreetMa… Read More
2019-02-25 19:32
We gathered elected official data from all across the country after the 2018 U.S. midterm election. We show shifting party structure and contact methods.
The post New Elected Officials, Visu… Read More
2019-02-21 15:36
We leveraged our ability to process raster imagery, our open sources libraries, and our knack for machine learning to map agricultural fields in Africa.
The post Mapping Africa: Crowdsourced… Read More
2019-02-13 14:17
Accuracy in deep learning models is not as cut and dry as many present it to be. We examine several examples where accuracy is more of a judgment call.
The post Accuracy is in the Eye of the… Read More
2019-02-12 17:23
Here’s a map of every state legislator in the U.S. as of February 2019, with districts and elected official data from the Cicero database.
The post Here’s a Map of Every State Le… Read More
2019-01-23 14:54
We sold HunchLab, our web-based predictive policing and patrol management system, in the fall of 2018. Our CEO outlines why.
The post Why We Sold HunchLab appeared first on Azavea - Beyond D… Read More
2019-01-15 21:10
Over 1.3 million people are killed on the world’s roads every year. More than 30 million suffer life-changing injuries. Based...
The post Reducing Road Crashes with DRIVER appeared fir… Read More
2019-01-09 17:00
As a mission-based organization, how we select the projects we pursue is an ongoing conversation at Azavea. We share our thought process here.
The post How Azavea Selects Projects appeared f… Read More
2018-12-18 16:45
Part two of our design process series details how we established Temperate's brand in a saturated industry, with the product's goal driving decision making.
The post Giving Form to Temperate… Read More
2018-12-07 20:52
The first in a two-part series, this blog post details how we solved a design problem by asking questions in building our climate adaptation planning app.
The post Problem-solving by asking… Read More
2018-12-05 17:49
We recently released Temperate: A new climate adaptation planning companion for cities. This blog explores how AWS, and the data they host, fueled this app.
The post AWS Enables Temperate ap… Read More
2018-12-03 21:22
Without outside funding and given our commitment to openly sharing our knowledge, people often ask: How do you fund your innovation? We outline 6 main ways.
The post Six Ways Azavea Funds In… Read More
2018-11-29 17:05
More companies are taking their impact on the world into consideration and consumers are paying attention. Can being political be profitable?
The post Why You Shouldn’t Keep Politics o… Read More
2018-11-14 17:38
Azavea rolled out Temperate, a climate adaptation planning app, in 2018. Get the details here.
The post Temperate: Your Climate Adaptation Planning Companion appeared first on Azavea - Beyon… Read More
2018-11-09 14:02
Azavea attended the UN World Data Forum in Dubai last week and learned how Earth Imagery can be applied to Sustainable Development Goals (SDGs).
The post Reflections from the UN World Data F… Read More
Subscribe to Azavea Atlas
Get updates delivered right to your inbox!