Abstract: Using active learning to quantify how training data errors impact classification accuracy over smallholder-dominated agricultural systems (AGU Fall Meeting 2018)

Using active learning to quantify how training data errors impact classification accuracy over smallholder-dominated agricultural systems

Lyndon D Estes¹, Stephanie R Debats², Dennis McRitchie³, Ronald Eastman⁴, Lei Song¹, Tammy Woodard⁵, Sitian Xiong⁶, Su Ye¹, Kaixi Zhang⁵, Ryan Barry Avery⁷ and Kelly K Caylor⁸, (1)Clark University, Graduate School of Geography, Worcester, MA, United States, (2)Uber ATG, San Francisco, CA, United States, (3)Self Employed, Tucson, AZ, United States, (4)Clark Labs, Worcester, MA, United States, (5)Clark University, Clark Labs, Worcester, MA, United States, (6)Clark University, Graduate School of Geography, Worcester, United States, (7)University of California Santa Barbara, Santa Barbara, CA, United States, (8)University of California Santa Barbara, Department of Geography, Santa Barbara, CA, United States

Back to: Advancements in Global Land Cover and Land Use Monitoring I