In this study, we present a convolutional neural network (CNN) architecture, GeoConv, designed to improve the accuracy and adaptability of deep learning models using satellite imagery. Traditional CNNs, such as ResNet18, employ fixed-weight convolutional layers - i.e., layers that leverage the same set of weights for each input observation. However, these models can struggle to capture context-specific features inherent in satellite images, which may vary significantly across different geographic regions. To address this challenge, the GeoConv model utilizes dynamic weights that adapt based on the input image coordinates, allowing the model to tailor its feature extraction process to the unique characteristics of different geographic regions. Through experiments, we illustrate the utility of this approach in a case study which leverages satellite imagery to estimate household wealth across 11 countries, with GeoConv explaining an additional 10.12% of the variance in the data compared to a ResNet18 model. These results underscore the importance of incorporating spatially adaptive mechanisms in handling the variability present in satellite imagery. Code is available at: https://github.com/heatherbaier/geoconv.

Convolutional Neural Networks (CNNs) are leveraged for a wide range of satellite imagery information extraction tasks. However, for tasks which seek to estimate aggregated information across highly variable geographic extents, existing techniques are subject to critical limitations. We engage with a specific case study exploring this challenge: estimating census variables across 2358 Mexican municipalities, which range in scope from 2.21 km2 (˜74,000 30 m pixels) to 72,417.9 km2 (millions of pixels). Building on recent literature which has illustrated the capability of deep learning to extract socioeconomic information from satellite imagery, we specifically seek to establish baseline metrics of error that might be expected when estimating a range of census variables based on coarse-resolution (Landsat) satellite imagery alone. For each of 52 variables, we implement a multi-glimpse recurrent attention model, in which we parametrically determine subsets of each municipality to sample across iterative steps. Results of a five-fold validation indicate that nearly half of the tested variables (22) can be estimated with r2 values greater than 0.75. Results suggest considerable promise for the use of satellite imagery to estimate socioeconomic factors in both historic time periods for which surveys were not conducted, as well as contemporary inaccessible regions.

This article introduces the Flow matrix, which expresses the sizes of transitions among categories between two time points. We use the Flow matrix to create a metric R that measures the instability of annual change among time intervals that partition the time extent. Specifically, R is the proportion of change that would need to be reallocated to different time interval(s) to achieve uniform change during the time extent. This article computes R for 10 Long Term Ecological Research (LTER) sites and for seven case studies from published land change data. Of the 10 LTER sites analyzed, the Andrews site in Oregon had the highest R value (37.1% of change), while the Luquillo site in Puerto Rico had the lowest (1.7% of change). We analyze the mathematical behavior of R, especially with respect to how the partitioning of the time extent into intervals can influence R.