NEXUS Institute: capturing 40+ years of agricultural development across Arequipa, Peru using random forest land cover classification and Landsat 1, 2, 3, 5, and 7 imagery

Authors: Timothy Filley, Purdue University, Zachary Brecheisen*, Purdue University, Darrell Schulze, Purdue University
Topics: Agricultural Geography, Land Use and Land Cover Change, Remote Sensing
Keywords: NEXUS, Peru, Landsat, land cover change, agriculture, random forest, R, Earth Explorer
Session Type: Paper
Day: 4/6/2019
Start / End Time: 3:05 PM / 4:45 PM
Room: Balcony B, Marriott, Mezzanine Level
Presentation File: No File Uploaded


The Arequipa Nexus Institute for Food, Energy and the Environment (Nexus Institute) is located in Southwestern Peru, generally bounded by the city of Arequipa to the east, the Majes River to the west, the Pacific Ocean to the south, and the Andes mountains to the north. Though agriculture has been practiced in parts of this cool desert region (MAT~15°C, MAP <10cm) for centuries, there has been an explosion of agricultural development in the last 30 years. This research is focused on the spatial quantification of this agricultural expansion across a ~25,000km2 landscape over the last 40+ years using Landsat 1, 2, 3, 5, and 7 data accessed via USGS’ Earth Explorer and Google Earth Engine Explorer. I am further investigating and contrasting several physiographic categories of agriculture currently defined as: alluvial floodplain agriculture, headwater montane agriculture, and upland non-montane agriculture. Upland non-montane agriculture in particular has expanded tremendously over the last 30 years driven by export markets, but the magnitude of this expansion relative to other physiographic modes of agriculture is unknown.These efforts are underway using Landsat data in conjunction with SRTM-derived (Shuttle Radar Topography Mission) topographic data to categorize land cover using “random forest” supervised classification algorithms in the R statistical program. Future goals are to quantify urban agricultural change around the city of Arequipa and also to study high elevation (>3500m) glacial melt marshes which are used for pasturing llamas and vicuñas which may be impacted by climate change.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login