Spline interpolation is a widely used class of methods for solving interpolation problems by constructing smooth interpolants that minimize a regularized energy functional involving the Laplacian operator. While many existing approaches focus on Euclidean domains or the sphere, relying on the spectral properties of the Laplacian, this work introduces a method for spline interpolation on general manifolds by exploiting its equivalence with kriging.
Geostatistics, extreme events and Deep Learning for the climate transition
A project at heart of two transitions
A digital transition
Massive and heterogeneous environmental data necessitates new geostatistical and generative AI methods.
A climate transition
In response to changes affecting air, water, soil and biodiversity, unprecedented in their amplitude, speed and simultaneous nature.
The objectives of the chair in three lines of research
Developing effective methods and tools, combining geostatistics, extreme value theory and generative AI, to process spatial and temporal data in order to assess impacts and quantify risks associated with ongoing climate change.
Predictive methods
Develop predictive methods for spatial and spatio-temporal phenomena, capable of processing large datasets.
A toolbox
Develop innovative simulation methods for extreme events and risk assessment and distribute them freely.
Hybrid approaches
Hybridizing statistical approaches with generative AI and physical knowledge to combine flexibility, rigor and knowledge.
Publications
This work examines to what extends bias correction methods improve the statistical characterization of extreme compound events.
Events
57th Statistics Days
The Geolearning chair was strongly represented at the 57th Statistics Days, held in Clermont-Ferrand.
Four presentations from the Geolearning chair at METMA XII
Lucia Clarotto, Alexandre Loret, Mike Pereira and Thomas Romary presented their work at the 12th international workshop on spatio-temporal modeling.