An algorithm that combines Big Earth Data and geospatial analysis in Google Earth Engine for the automated detection of archaeological mounds and Cultural Heritage sites that are potentially endangered by new agricultural developments.

The dataset contains supplementary materials to accompany the paper “Conesa, F. C., Orengo, H. A., Lobo, A., & Petrie, C. A. (2022). An Algorithm to Detect Endangered Cultural Heritage by Agricultural Expansion in Drylands at a Global Scale. Remote Sensing, 15(1), 53. MDPI AG. http://doi.org/10.3390/rs15010053".

It includes the JavaScript code to be implemented in Google Earth Engine(c) and the R script for vector output visualisation.

The algorithm is powered by the cloud-computing data cataloguing and processing capabilities of Google Earth Engine and it uses all the available scenes from the Sentinel-2 image collection to map index-based multi-aggregate yearly vegetation changes.

The algorithm requires an input vector table such as data gazetteers or heritage inventories, and it performs buffer zonal statistics for each site to return a series of spatial indicators of potential site disturbance. It also returns time series charts for the evaluation and validation of the local to regional vegetation trends and phenological circles.

Additionally, it employs multi-temporal MODIS, Sentinel-2 and high-resolution Planet imagery for further photo-interpretation of critically endangered sites.

AgriExp was first tested in the arid region of the Cholistan Desert in eastern Pakistan, home of hundreds of archaeological mounds dating back to the Indus Civilisation (ca. 3500 -1900 aC).