id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_hkzle3wyofchtcheq2mcsv3yiu	Robert S. Walker	Machine learning with remote sensing data to locate uncontacted indigenous villages in Amazonia	2019	11	.pdf	application/pdf	4252	481	54	small-scale nature of the deforestation signature left by uncontacted populations clearing villages and gardens has similarities to those made by contacted indigenous villages. A random forest algorithm with an optimally-tuned detection cutoff has a leaveone-out cross-validated sensitivity and specificity of over 98%. Keywords Random forest, Satellite imagery, South America, Indigenous societies remnant indigenous societies generally referred to as uncontacted or isolated populations Machine learning with remote sensing data to locate uncontacted indigenous villages in Amazonia. project along with high-resolution imagery for uncontacted villages is available at Map of 500 contacted indigenous villages in Brazil and 25 uncontacted uncontacted villages have (1) smaller cleared areas, (2) longer distances from lights, (3) top four distinguishing features in terms of variable importance in the random forest model are uncontacted villages have (A) smaller cleared areas, (B) farther distances to satellite-detected lights at night, (C) Random forest classifier for remote sensing classification.	./cache/work_hkzle3wyofchtcheq2mcsv3yiu.pdf	./txt/work_hkzle3wyofchtcheq2mcsv3yiu.txt