Machine Learning Archives

A Human-in-the-Loop Machine Learning Workflow for Geospatial Data

By Adeel Hassan on September 28th, 2022

In this blog we demonstrate how an active learning approach can boost machine learning model performance with the human-in-the-loop workflow.

Software Engineering

Benchmarking Zarr and Parquet Data Retrieval using the National Water Model (NWM) in a Cloud-native environment

By Vijay Lulla, Lewis Fishgold and Terence Tuhinanshu on September 22nd, 2022

In order to benchmark efficiency, we take a deep dive into Zarr and Parquet data retrieval to compare performance on various time scales.

Software Engineering

Change detection with Raster Vision

By Adeel Hassan on April 18th, 2022

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 Change Detection (OSCD) dataset.

Spatial Analysis

Machine Learning to Drive Urban Resilience: Mapping Tree Canopy with the World Bank

By Niki LaGrone on February 4th, 2022

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 identify tree canopy.

Software Engineering

The Azavea Cloud Dataset

By James McClain on August 2nd, 2021

Azavea is releasing a dataset consisting of 32 unique Sentinel-2 tiles with cloud labels produced by humans.

1976 Synthetic Aperture Radar image of Willow Run Airport and vicinity, representing 15-foot (5 meter) resolution.

Company

Labeling SAR Imagery for Machine Learning: A Beginners Guide

By Niki LaGrone on April 27th, 2021

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.