An Algorithm to Detect Endangered Cultural Heritage by Agricultural Expansion in Drylands at a Global Scale

This article presents AgriExp, a remote-based workflow for the rapid mapping and monitoring of archaeological cultural heritage locations endangered by new agricultural expansion encroachment. Our approach is powered cloud-computing data cataloguing processing capabilities Google Earth Engine it uses all available scenes from Sentinel-2 image collection to map index-based multi-aggregate yearly vegetation changes. A user-defined index threshold maps first per-pixel occurrence an abrupt change returns updated classified multi-temporal aggregate in almost-real-time. The algorithm requires input vector table such as gazetteers or inventories, performs buffer zonal statistics each site return series spatial indicators potential disturbance. It also time charts evaluation validation local regional trends seasonal phenology. Additionally, we used MODIS, high-resolution Planet imagery further photo-interpretation critically sites. AgriExp was tested arid region Cholistan Desert eastern Pakistan. Here, hundreds mound surfaces are threatened accelerated transformation barren lands into irrigated lands. We have provided code with ensure that can be exported implemented little computational cost academics practitioners alike monitor landscapes elsewhere.