The wide availability of multispectral satellite imagery through projects such as Landsat and Sentinel, combined with the introduction of deep learning in general and Convolutional Neural Networks (CNNs) in particular, has allowed for the rapid and effective analysis of multiple classes of problems pertaining to land coverage. Taking advantage of the two phenomena, we propose a machine learning model for the classification of land abandonment.

Groundwater resources became a recognized enabler of important rural and socio-economic development in Mediterranean countries. However, the development of this groundwater economy is currently associated with an increased pressure on the available resource and negative implications on the socio-ecological system. Managing complex socio-ecological systems, such as those that occur in water resource management, is a multi-actor, multi-scale and dynamic decision-making process.

The contemporary American rural landscape reflects a mix of ongoing economic changes in agricultural land use, population change, and built environments. The mix depends on past and recent change which represent landscapes of memory and silence to those experiencing economic and demographic renaissance. We develop a typology of five stages that reflect the contemporary rural scene and conduct field transects in Northwest Iowa and Central Maine. Features of the dynamics in rural America are evident in photographs of residences, land use changes, and commercial structure.