Deep reinforcement learning could support tighter human-machine collaboration

For nearly two years, we’ve been researching a new approach to map roads in satellite imagery using machine learning (ML). Deep reinforcement learning (RL) is a relatively new subfield of ML that we’re applying for autonomous road mapping. Rather than the current approach of classifying individual road pixels and extracting road vectors from the result, RL models can take a satellite image as input and then manipulate a cursor to “trace out” a road network. This mimics how humans map, and therefore has potential to better integrate with and massively accelerate human mapping efforts.

Satellite image and road network from the SpaceNet dataset.

Introduction

Road maps are vital for everyday…


Today is World Refugee Day, so we want to highlight some early work on finding people who have been forced from their homes. This is part of a larger effort with the Conflict Ecology research lab at Oregon State University and Humanitarian OpenStreetMap Team.

A person is forcibly displaced from their home almost every two seconds. Driven by conflict and disaster, the population of displaced people worldwide grew to 70 million people at the end of 2018. This represents a new global record, slightly larger than the population of France. Whether they are refugees seeking assistance in another country or…


This is an ongoing project to support the World Bank’s Global Program on Resilient Housing.

Hard to find, easy to fix

People living in neighborhoods with poor building standards are more likely to be killed by a disaster. Their homes, too often built in a cheap or makeshift manner, are susceptible to dangerous events like earthquakes, hurricanes, and landslides. These (typically poor) inhabitants make up a disproportionate number of the 1,300,000 lives taken by disasters in the last 25 years. Families move into poor urban communities seeking better jobs and opportunities but don’t possess the money or technical knowledge to access safe, resilient housing. Governments and…


This guide is for machine learning practitioners looking to apply Keras models at scale. I’ll cover a concrete problem we faced and then provide a code walkthrough of our solution.

Finding electricity infrastructure at scale

Access to electricity is a major issue in parts of the developing world. So much so that the United Nations specifically allotted one of its 15 Sustainable Development Goals (specifically, #7) to “ensuring access to affordable, reliable, and modern energy for all.” Many organizations are working hard to improve energy access around the world, but it’s often difficult to find maps of the existing electric grid. Without infrastructure maps, these…


A pipeline to fully map the Red Planet

This blog post coincides with research that we’re presenting at the American Geophysical Union Conference on Dec 13th, 2018.

The exploration of Mars will require precise maps. Current feature maps for Mars are created by hand and therefore only include large features. Collaborating with researchers at Arizona State University, we used the YOLO deep learning architecture to autonomously detect surface features (here, craters) faster and at much finer scales. With assistance from Artificial Intelligence (AI), we can bring down the planet-wide mapping process from years to weeks.

Motivation

For much of history, explorers left home not knowing what they would encounter…


Creating maps from satellite imagery is a tedious task. Objects we often care about mapping (e.g., buildings and roads) lie in a complex visual soup of trees, shadows, and clouds and can vary in their appearance across the world. We rely on human mappers because attempts to fully automate this process with machine learning (ML) have proven difficult — even with modern deep learning methods. While ML algorithms scale much better than human effort, they are relatively rigid and haven’t been able to capture the flexibility and contextual awareness that comes naturally to humans. At Development Seed, we’re betting that…


Over half the world’s population lives in urban areas, many in unplanned urban sprawl. The high rate of urbanization is a major challenge for keeping cities safe, resilient, and sustainable — the aim of the UN’s Sustainable Development Goal #11. One component of achieving this goal is tied to accurate maps of buildings. With complete maps, urban planners can more effectively improve infrastructure including public transit, roads, and waste management. Toward this goal, we’re working on machine learning (ML) tools to recognize buildings and speed up the urban mapping process.

Autonomously mapping buildings remains an area of active research as…


Artificial intelligence is not magic. It may be portrayed like magic — we see big advancements like autonomous cars, superhuman Atari game play, AlphaGo, and ubiquitous home assistants. Like magic, AI can also defy understanding. The broad concepts of machine learning (ML) — the applied arm of AI — can be challenging to explain to anyone who hasn’t spent time developing their own models. Deep learning models, which sit at the cutting edge of ML, are nearly impossible to dissect and understand for AI experts and novices alike.

However, regarding AI as magic is a liability — especially in the…

Mark Wronkiewicz

Using AI to deliver insight from satellite images

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store