Azavea Blog - Geospatial and Software Development Topics

Using the Dedupe Machine Learning Library for Cleaning and Matching Data

By Justin Walgran on August 30th, 2019

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 commonalities in jumbled text, and confidently compare large lists without the need to compare each individual entry.

United States outline around an image of farmland.

Company

Temperate Takes a Rural Approach

By Jessica Cahail on August 27th, 2019

Temperate will soon incorporate rural areas into its climate planning capabilities.

OAR map overlaid on top of hands sewing a garment.

Software Engineering

Connecting Data and People with the Open Apparel Registry

By Deb Boyer on August 7th, 2019

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 from the OAR contributed to decision making by brands and facilities.

Ground truth imperfectly overlaying machine learning predictions.

Software Engineering

Using Noisy Labels to Train Deep Learning Models on Satellite Imagery

By Lewis Fishgold on August 5th, 2019

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.

Picture of dice overlaid with charts from Anscombe's Quartet.

Software Engineering

Lies, Damned Lies, and Accuracy Metrics

By Joe Morrison on July 31st, 2019

How accurate of a machine learning model can you make? It depends on how we decide to define "accurate".

Picture of countryside road side-by-side a torn aerial cityview.

Spatial Analysis

Exploring the Urban-Rural Divide through Politicians’ Social Media

By Luke McKinstry on July 23rd, 2019

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.

Featured Posts

Using the Dedupe Machine Learning Library for Cleaning and Matching Data

Is This a Crosswalk?: 5 Takeaways from Training a Data Labeling Team

Using the Dedupe Machine Learning Library for Cleaning and Matching Data

Temperate Takes a Rural Approach

Connecting Data and People with the Open Apparel Registry

Using Noisy Labels to Train Deep Learning Models on Satellite Imagery

Lies, Damned Lies, and Accuracy Metrics

Exploring the Urban-Rural Divide through Politicians’ Social Media