Uncertainty quantification for probabilistic machine learning in earth observation using conformal prediction

Autor: Singh, Geethen, Moncrieff, Glenn, Venter, Zander, Cawse-Nicholson, Kerry, Slingsby, Jasper, Robinson, Tamara B

Unreliable predictions can occur when using artificial intelligence (AI) systems with negative consequences for downstream applications, particularly when employed for decision-making. Conformal prediction provides a model-agnostic framework for unce

Externí odkaz: http://arxiv.org/abs/2401.06421

Global 10 m Land Use Land Cover Datasets: A Comparison of Dynamic World, World Cover and Esri Land Cover

Autor: Venter, Zander, Barton, David Nicholas, Chakraborty, Tirthankar, Simensen, Trond, Singh, Geethen

Externí odkaz: https://hdl.handle.net/11250/3054469

Uncertainty quantification for probabilistic machine learning in earth observation using conformal prediction.

Autor: Singh G; Department of Botany and Zoology, Centre for Invasion Biology, Stellenbosch University, Stellenbosch, South Africa. Geethen.singh@gmail.com., Moncrieff G; Global Science, The Nature Conservancy, Cape Town, 7945, South Africa.; Department of Statistical Sciences, Centre for Statistics in Ecology, Environment and Conservation, University of Cape Town, Private Bag X3, Rondebosch, Cape Town, 7701, South Africa., Venter Z; Norwegian Institute for Nature Research-NINA, Sognsveien 68, 0855, Oslo, Norway., Cawse-Nicholson K; Carbon Cycles and Ecosystems, Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USA., Slingsby J; Department of Biological Sciences and Centre for Statistics in Ecology, Environment and Conservation, University of Cape Town, Private Bag X3, Rondebosch, Cape Town, 7701, South Africa.; Fynbos Node, South African Environmental Observation Network, Centre for Biodiversity Conservation, Cape Town, South Africa., Robinson TB; Department of Botany and Zoology, Centre for Invasion Biology, Stellenbosch University, Stellenbosch, South Africa.

Publikováno v: Scientific reports [Sci Rep] 2024 Jul 13; Vol. 14 (1), pp. 16166. Date of Electronic Publication: 2024 Jul 13.