A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery

10/16/2020
by   Esther Rolf, et al.
16

Combining satellite imagery with machine learning (SIML) has the potential to address global challenges by remotely estimating socioeconomic and environmental conditions in data-poor regions, yet the resource requirements of SIML limit its accessibility and use. We show that a single encoding of satellite imagery can generalize across diverse prediction tasks (e.g. forest cover, house price, road length). Our method achieves accuracy competitive with deep neural networks at orders of magnitude lower computational cost, scales globally, delivers label super-resolution predictions, and facilitates characterizations of uncertainty. Since image encodings are shared across tasks, they can be centrally computed and distributed to unlimited researchers, who need only fit a linear regression to their own ground truth data in order to achieve state-of-the-art SIML performance.

READ FULL TEXT

page 2

page 3

page 8

page 26

page 35

page 36

page 40

page 42

research
12/05/2020

Generating Synthetic Multispectral Satellite Imagery from Sentinel-2

Multi-spectral satellite imagery provides valuable data at global scale ...
research
02/26/2020

Super-Resolving Commercial Satellite Imagery Using Realistic Training Data

In machine learning based single image super-resolution, the degradation...
research
03/12/2018

Super-Resolution of Sentinel-2 Images: Learning a Globally Applicable Deep Neural Network

The Sentinel-2 satellite mission delivers multi-spectral imagery with 13...
research
05/13/2021

House Price Prediction using Satellite Imagery

In this paper we show how using satellite images can improve the accurac...
research
06/08/2018

Domain Adaptive Generation of Aircraft on Satellite Imagery via Simulated and Unsupervised Learning

Object detection and classification for aircraft are the most important ...
research
04/28/2021

DeepSatData: Building large scale datasets of satellite images for training machine learning models

This report presents design considerations for automatically generating ...
research
09/21/2022

Detecting Crop Burning in India using Satellite Data

Crop residue burning is a major source of air pollution in many parts of...

Please sign up or login with your details

Forgot password? Click here to reset