We apply deep learning to daytime satellite imagery to predict changes in income and population at high spatial resolution in US data. For grid cells with lateral dimensions of 1.2 km and 2.4 km (where the average US county has dimension of 51.9 km), our model predictions achieve R2 values of 0.85 to 0.91 in levels, […]

The post Using Neural Networks to Predict Microspatial Economic Growth appeared first on Marginal REVOLUTION.

   Comments* In reply to rayward. his history is one with few if any ... *by So Much For Subtlety*

• BC, such as the academy, the tower that fell, it is greed; and ... by Equestrian
• I asked ChatGPT to write a Christmas carol about their ... by dan1111
• In reply to Pedant. The deer are invisible now. I am ... by Equestrian
• In reply to rayward. Access to capital formulation befuddles ... by Equestrian
• Plus 7 more... Related Stories* Productivity in the two Irelands (extrapolate this)
• AFA mask meeting update
• Hail to Our New Leader!