The U.S. Census Bureau this year launched an experimental method of using satellite images to count new housing construction, The Center Square reports. “For select areas of interest, Survey of Construction data collected by field representatives have been replaced with estimates obtained from satellite imagery to demonstrate the efficacy of this data collection method,” the bureau writes in a mid-December release. The satellite images are run through “convolutional neural networks,” or CNNs, to identify construction. The programs will be able to differentiate excavation, foundation, framing, unfinished roof, and finished roofs. The program can also distinguish between single-family detached, single-family attached, multifamily, and nonresidential structures. The bureau is only using the experimental method in District 7, which includes Texas, Oklahoma, Arkansas and Louisiana. Read the full story.