Fred Hohman
/ CSE Ph.D. Student at GT

A Deep Learning Approach for Population Estimation from Satellite Imagery

Caleb Robinson, Fred Hohman, Bistra Dilkina

The top 8 most confident prediction images from the test set for each class (e.g. 99% prediction for a given class), all of which are correctly classified. Notice the types of images that appear from top (highways, few people) to bottom (buildings, many people) further indicated that our deep learning model is learning semantically-relevant features from satellite imagery.


Knowing where people live is a fundamental component of many decision making processes such as urban development, infectious disease containment, evacuation planning, risk management, conservation planning, and more. While bottom-up, survey driven censuses can provide a comprehensive view into the population landscape of a country, they are expensive to realize, are infrequently performed, and only provide population counts over broad areas. Population disaggregation techniques and population projection methods individually address these shortcomings, but also have shortcomings of their own. To jointly answer the questions of “where do people live” and “how many people live there,” we propose a deep learning model for creating high-resolution population estimations from satellite imagery. Specifically, we train convolutional neural networks to predict population in the USA at a 0.01 degree x 0.01 degree resolution grid from 1-year composite Landsat imagery. We validate these models in two ways: quantitatively, by comparing our model’s grid cell estimates aggregated at a county-level to several US Census county-level population projections, and qualitatively, by directly interpreting the model’s predictions in terms of the satellite image inputs. We find that aggregating our model’s estimates gives comparable results to the Census county-level population projections and that the predictions made by our model can be directly interpreted, which give it advantages over traditional population disaggregation methods. In general, our model is an example of how machine learning techniques can be an effective tool for extracting information from inherently unstructured, remotely sensed data to provide effective solutions to social problems.


PDF | Github (coming soon!) | BibTeX


A Deep Learning Approach for Population Estimation from Satellite Imagery
Caleb Robinson, Fred Hohman, Bistra Dilkina
arXiv:1708.09086. August 30, 2017.
PDF | Github (coming soon!) | BibTeX


  title={A Deep Learning Approach for Population Estimation from Satellite Imagery},
  author={Robinson, Caleb and Hohman, Fred and Dilkina, Bistra},
  journal={arXiv preprint arXiv:1708.09086},