Infrastructure Quality Assessment in Africa using Satellite Imagery and Deep Learning

Abstract

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.

Toward Model-Generated Household Listing in Low- and Middle-Income Countries Using Deep Learning

“…When aggregated, these counts were found to be highly predictive of neighborhood sociodemographic characteristics, such as household income, level of education, and race, as reported in the American Community Survey. Oshri et al 2018 [33] used CNNs on Landsat 8 and Sentinel 1 satellite imagery to predict coverage of important infrastructure, such as sewage systems, piped water, and electricity services, across 36 African countries.…”

Apache Spark Accelerated Deep Learning Inference for Large Scale Satellite Image Analytics

“…As such, remote sensing applications have leaped into a data and compute intensive era presenting challenges and opportunities for new advanced machine learning and computer vision workflows. Examples of such applications include providing possibilities to study sustainability outcomes at scale [5], and identifying urban environments over large contexts using abundant satellite imagery and breakthroughs in deep learning based image classification [6]. To achieve greater impact with machine learning on data and compute intense workloads, new advanced workflows are required for efficient utilization of high performance computing resources.…”

“…(4) We take advantage of Apache Spark to provide, for a single large image scene, a fast parallel inference functionality achieving tremendous speed-up with area pixel labeling rate of 5.245sq.km/sec, amounting to 453,168 sq.km/day -reducing a 28 day workload to 21 hours. (5) We present a containerized workflow for Apache Spark operations coordinated with GPUs for deep learning inference best practices, e.g. efficient GPU usage and ticketing across multiple workers, for large deep learning workloads deployed on GPU clusters.…”

Understanding Compressive Adversarial Privacy

“…Machine learning has progressed dramatically in many reallife tasks such as classifying image [1], processing natural language [2], predicting electricity consumption [3], and many more. These tasks rely on large datasets that are usually saturated with private information.…”

“…Difference between altered and original data when rank equals 4, 10, and GeneratingX (Neural Net attacker) Input: dataset D, parameter γ, iteration number T 2: Output: Optimal data publisher parameters θ g 3: Initialize θ t g and θ t h when t = 0 4: for t = 0, ..., T do5: take minibatch of n samples {x(1) , . .…”