Predicting Food Security Outcomes Using Convolutional Neural Networks (CNNs) for Satellite Tasking

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 (5)

• Food safety risk prediction with Deep Learning models using categorical embeddings on European Union data
• 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
• Linear Stability Analysis of a Normal Shock Train in a Constant Area Isolator of a Hypersonic ScramJet