Predicting Food Security Outcomes Using Convolutional Neural Networks (CNNs) for Satellite Tasking
arXiv:1902.05433
Abstract
Obtaining reliable data describing local Food Security Metrics (FSM) at a granularity that is informative to policy-makers requires expensive and logistically difficult surveys, particularly in the developing world. We train a CNN on publicly available satellite data describing land cover classification and use both transfer learning and direct training to build a model for FSM prediction purely from satellite imagery data. We then propose efficient tasking algorithms for high resolution satellite assets via transfer learning, Markovian search algorithms, and Bayesian networks.
Research performed as part of the Sustainability and Artificial Intelligence Laboratory (SAIL) at Stanford University. Second revised version corrects typographical errors and adds a few references
References in corpus (4)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- GeoGAN: A Conditional GAN with Reconstruction and Style Loss to Generate Standard Layer of Maps from Satellite Images
- Semi-Supervised Multitask Learning on Multispectral Satellite Images Using Wasserstein Generative Adversarial Networks (GANs) for Predicting Poverty
- Predicting US State-Level Agricultural Sentiment as a Measure of Food Security with Tweets from Farming Communities
Cited by in corpus (3)
- GeoGAN: A Conditional GAN with Reconstruction and Style Loss to Generate Standard Layer of Maps from Satellite Images
- Semi-Supervised Multitask Learning on Multispectral Satellite Images Using Wasserstein Generative Adversarial Networks (GANs) for Predicting Poverty
- Predicting US State-Level Agricultural Sentiment as a Measure of Food Security with Tweets from Farming Communities