Professor Danielle Wood and collaborators at the National Polytechnic Institute in Mexico published a paper called "Assessing Human Settlement Sprawl in Mexico via Remote Sensing and Deep Learning."  The work contributes to the overall series of projects pursued by Prof. Wood, team Space Enabled, and collaborators around the world to improve the utility of satellite-based earth observation data to support policy and Sustainable Development. Lead Author Antonio Briseno Montes served as a visiting student at Space Enabled during January 2024. Co-author Prof Joaquin Salas is speaking in the EVDT Community Meeting virtual webinar on April 10, 2024: https://www.media.mit.edu/events/evdt-community-meeting-april-2024/.

The abstract reads:

"Understanding human settlements' geographic location and extent can support decision-making in resource distribution, urban growth policies, and natural resource protection. This research presents an approach to assess human settlement sprawl using labeled multispectral satellite image patches and Convolutional Neural Networks (CNN). By training deep learning classifiers with a dataset of 5,359,442 records consisting of satellite images and census data from 2010, we evaluate sprawl for settlements across the country. The study focuses on major cities in Mexico, comparing ground truth results for 2015 and 2020. EfficientNet-B7 achieved the best performance with a ROC AUC of 0.970 and a PR AUC of 0.972 among various CNN architectures evaluated. To evaluate human settlement sprawl, we introduce an information-based metric that offers advantages over entropy-based alternatives."