Putting farmers on the map: land cover classification of Galapagos agroecosystems

Authors: Francisco Laso*, University of North Carolina - Chapel Hill, Fátima Lorena Benítez, Universidad San Francisco de Quito, Gonzalo Rivas-Torres, Universidad San Francisco de Quito, Carolina Sampedro, Universidad San Francisco de Quito, Javier Arce-Nazario, University of North Carolina - Chapel Hill
Topics: Coupled Human and Natural Systems, Land Use and Land Cover Change, Environment
Keywords: Galapagos, Agriculture, Conservation, Remote Sensing, PlanetScope, Sentinel-2, UAV, Drones, Mapping, Land Use, Land Cover
Session Type: Virtual Paper
Day: 4/10/2021
Start / End Time: 3:05 PM / 4:20 PM
Room: Virtual 17
Presentation File: No File Uploaded

The humid highlands of the Galapagos are the islands’ most biologically productive regions and a key habitat for endemic animal and plant species. These areas are crucial for the region’s food security and the control of invasive plants, but little is known about its land cover's spatial distribution. We generated a baseline high-resolution land cover map of the agricultural zones and their surrounding protected areas. We combined the high spatial resolution of PlanetScope images with the high spectral resolution of Sentinel-2 images in an object-based classification using a RandomForest algorithm. We used images collected with an unoccupied aerial vehicle (UAV) to verify and validate our classified map. Despite the astounding diversity and heterogeneity of the highland landscape, our classification yielded useful results (overall Kappa: 0.7, R2: 0.69) and revealed that across all four inhabited islands, invasive plants cover the largest fraction (28.5%) of the agricultural area, followed by pastures (22.3%), native vegetation (18.6%), food crops (18.3%), and mixed forest and pioneer plants (11.6%). Our results are consistent with the historical trajectories of colonization and abandonment of the highlands. The produced dataset is designed to suit the needs of practitioners of both conservation and agriculture. We are distributing this dataset under a creative commons license to foster collaboration between agriculture and conservation.

Abstract Information

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

To access contact information login