loading page

Feature Learning for Multispectral Satellite Imagery Classification using Neural Architecture Search
  • +1
  • Roberto Campbell,
  • Brian Coltin,
  • P. Michael Furlong,
  • Scott McMichael
Roberto Campbell
San Jose State University, San Jose State University

Corresponding Author:[email protected]

Author Profile
Brian Coltin
NASA Ames Research Center, NASA Ames Research Center
Author Profile
P. Michael Furlong
NASA Ames Research Center, NASA Ames Research Center
Author Profile
Scott McMichael
NASA Ames Research Center, NASA Ames Research Center
Author Profile

Abstract

Automated classification of remote sensing data is an integral tool for earth scientists, and deep learning has proven very successful at solving such problems. However, building deep learning models to process the data requires expert knowledge of machine learning. We introduce DELTA, a software toolkit to bridge this technical gap and make deep learning easily accessible to earth scientists. Visual feature engineering is a critical part of the machine learning lifecycle, and hence is a key area that will be automated by DELTA. Hand-engineered features can perform well, but require a cross functional team with expertise in both machine learning and the specific problem domain, which is costly in both researcher time and labor. The problem is more acute with multispectral satellite imagery, which requires considerable computational resources to process. In order to automate the feature learning process, a neural architecture search samples the space of asymmetric and symmetric autoencoders using evolutionary algorithms. Since denoising autoencoders have been shown to perform well for feature learning, the autoencoders are trained on various levels of noise and the features generated by the best performing autoencoders evaluated according to their performance on image classification tasks. The resulting features are demonstrated to be effective for Landsat-8 flood mapping, as well as benchmark datasets CIFAR10 and SVHN.