Infrastructure Quality Assessment in Africa using Satellite Imagery and Deep Learning

The UN Sustainable Development Goals allude to the importance of infrastructure quality in three of its seventeen goals. However, monitoring infrastructure quality in developing regions remains prohibitively expensive and impedes efforts to measure progress toward these goals. To this end, we investigate the use of widely available remote sensing data for the prediction of infrastructure quality in Africa. We train a convolutional neural network to predict ground truth labels from the Afrobarometer Round 6 survey using Landsat 8 and Sentinel 1 satellite imagery. Our best models predict infrastructure quality with AUROC scores of 0.881 on Electricity, 0.862 on Sewerage, 0.739 on Piped Water, and 0.786 on Roads using Landsat 8. These performances are significantly better than models that leverage OpenStreetMap or nighttime light intensity on the same tasks. We also demonstrate that our trained model can accurately make predictions in an unseen country after fine-tuning on a small sample of images. Furthermore, the model can be deployed in regions with limited samples to predict infrastructure outcomes with higher performance than nearest neighbor spatial interpolation.

[1]  Stefano Ermon,et al.  Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping , 2015, AAAI.

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Stefano Ermon,et al.  Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data , 2017, AAAI.

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Thomas Bentley,et al.  Inadequate Access, Poor Government Performance make Water a Top Priority in Africa , 2015 .

[7]  Luisa Verdoliva,et al.  Land Use Classification in Remote Sensing Images by Convolutional Neural Networks , 2015, ArXiv.

[8]  Bertrand Le Saux,et al.  Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks , 2017, ISPRS Journal of Photogrammetry and Remote Sensing.

[9]  Shawn D. Newsam,et al.  Bag-of-visual-words and spatial extensions for land-use classification , 2010, GIS '10.

[10]  Jefersson Alex dos Santos,et al.  Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[11]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Carlo Gatta,et al.  Unsupervised Deep Feature Extraction for Remote Sensing Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  Christopher D. Brown,et al.  Receiver operating characteristics curves and related decision measures: A tutorial , 2006 .

[15]  Stefano Ermon,et al.  Monitoring Ethiopian Wheat Fungus with Satellite Imagery and Deep Feature Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[16]  Marta C. González,et al.  Using Convolutional Networks and Satellite Imagery to Identify Patterns in Urban Environments at a Large Scale , 2017, KDD.

[17]  Konstantinos Karantzalos,et al.  BENCHMARKING DEEP LEARNING FRAMEWORKS FOR THE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE MULTISPECTRAL DATA , 2016 .

[18]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[19]  A. Glassman,et al.  The Political Economy of Bad Data: Evidence from African Survey and Administrative Statistics , 2015 .

[20]  Lior Bragilevsky,et al.  Deep learning for Amazon satellite image analysis , 2017, 2017 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM).

[21]  S. M. García,et al.  2014: , 2020, A Party for Lazarus.

[22]  Patrick Weber,et al.  OpenStreetMap: User-Generated Street Maps , 2008, IEEE Pervasive Computing.

[23]  Geoffrey E. Hinton,et al.  Learning to Detect Roads in High-Resolution Aerial Images , 2010, ECCV.

[24]  Richard R. Irish,et al.  Landsat 7 automatic cloud cover assessment , 2000, SPIE Defense + Commercial Sensing.

[25]  A. Zipf,et al.  Comparative Spatial Analysis of Positional Accuracy of OpenStreetMap and Proprietary Geodata , 2012 .

[26]  Michael Reibel,et al.  Geographic Information Systems and Spatial Data Processing in Demography: a Review , 2007 .

[27]  Jiangye Yuan,et al.  Automatic Building Extraction in Aerial Scenes Using Convolutional Networks , 2016, ArXiv.

[28]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[29]  Florence March,et al.  2016 , 2016, Affair of the Heart.

[30]  Brian L. Spatocco,et al.  Targeting Villages for Rural Development Using Satellite Image Analysis , 2015, Big Data.

[31]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[32]  Geoffrey E. Hinton,et al.  Learning to Label Aerial Images from Noisy Data , 2012, ICML.

[33]  Qingshan Liu,et al.  Learning Multiscale Deep Features for High-Resolution Satellite Image Scene Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Sang Michael Xie,et al.  Combining satellite imagery and machine learning to predict poverty , 2016, Science.

[35]  Adyasha Maharana,et al.  Using Deep Learning and Satellite Imagery to Quantify the Impact of the Built Environment on Neighborhood Crime Rates , 2017, ArXiv.

[36]  Johannes Hoogeveen,et al.  Mobile Phone Panel Surveys in Developing Countries: A Practical Guide for Microdata Collection , 2016 .