Nonstationary covariance structure I: Deformations.

Slides:



Advertisements
Similar presentations
Spatial point patterns and Geostatistics an introduction
Advertisements

Bayesian Belief Propagation
CSCE643: Computer Vision Bayesian Tracking & Particle Filtering Jinxiang Chai Some slides from Stephen Roth.
Medical Image Registration Kumar Rajamani. Registration Spatial transform that maps points from one image to corresponding points in another image.
Bayesian inference “Very much lies in the posterior distribution” Bayesian definition of sufficiency: A statistic T (x 1, …, x n ) is sufficient for 
Model assessment and cross-validation - overview
Basic geostatistics Austin Troy.
Visual Recognition Tutorial
Forecasting JY Le Boudec 1. Contents 1.What is forecasting ? 2.Linear Regression 3.Avoiding Overfitting 4.Differencing 5.ARMA models 6.Sparse ARMA models.
Section 4.2 Fitting Curves and Surfaces by Least Squares.
WFM 6202: Remote Sensing and GIS in Water Management © Dr. Akm Saiful IslamDr. Akm Saiful Islam WFM 6202: Remote Sensing and GIS in Water Management Akm.
Meet the professor Friday, January 23 at SFU 4:30 Beer and snacks reception.
Some remarks about Lab 1. image(parana.krige,val=sqrt(parana.kri ge$krige.var)) contour(parana.krige,loc=loci,add=T)
Spatial Statistics IV Stat 518 Sp08. Recall Method of moments: square of all pairwise differences, smoothed over lag bins Problems: Not necessarily a.
The Fourier transform. Properties of Fourier transforms Convolution Scaling Translation.
Applied Geostatistics
Statistics, data, and deterministic models NRCSE.
Continuity and covariance Recall that for stationary processes so if C is continuous then Z is mean square continuous. To get results about sample paths.
Statistics, data, and deterministic models NRCSE.
Modelling non-stationarity in space and time for air quality data Peter Guttorp University of Washington NRCSE.
2-7 Feb 2003SAMSI Multiscale Workshop1 Nonstationary spatial covariance modeling via spatial deformation & extensions to covariates and models for dynamic.
Deterministic Solutions Geostatistical Solutions
Global processes Problems such as global warming require modeling of processes that take place on the globe (an oriented sphere). Optimal prediction of.
Bayesian kriging Instead of estimating the parameters, we put a prior distribution on them, and update the distribution using the data. Model: Prior: Posterior:
STAT 592A(UW) 526 (UBC-V) 890-4(SFU) Spatial Statistical Methods NRCSE.
Ordinary Kriging Process in ArcGIS
Space-time Modelling Using Differential Equations Alan E. Gelfand, ISDS, Duke University (with J. Duan and G. Puggioni)
Stat 592A Spatial Statistical Methods NRCSE.
Statistical Tools for Environmental Problems NRCSE.
Ensemble Learning (2), Tree and Forest
Model Inference and Averaging
Gridding Daily Climate Variables for use in ENSEMBLES Malcolm Haylock, Climatic Research Unit Nynke Hofstra, Mark New, Phil Jones.
Probabilistic Robotics Bayes Filter Implementations.
Regional climate prediction comparisons via statistical upscaling and downscaling Peter Guttorp University of Washington Norwegian Computing Center
Geographic Information Science
Dataset Development within the Surface Processes Group David I. Berry and Elizabeth C. Kent.
Spatial Statistics in Ecology: Continuous Data Lecture Three.
Combining CMORPH with Gauge Analysis over
Spatial Interpolation III
1 University of Texas at Austin Machine Learning Group 图像与视频处理 计算机学院 Motion Detection and Estimation.
Concepts and Applications of Kriging
1  The Problem: Consider a two class task with ω 1, ω 2   LINEAR CLASSIFIERS.
Esri UC 2014 | Technical Workshop | Concepts and Applications of Kriging Eric Krause Konstantin Krivoruchko.
Lecture 6: Point Interpolation
Esri UC2013. Technical Workshop. Technical Workshop 2013 Esri International User Conference July 8–12, 2013 | San Diego, California Concepts and Applications.
Case Selection and Resampling Lucila Ohno-Machado HST951.
Multidimensional Scaling By Marc Sobel. The Goal  We observe (possibly non-euclidean) proximity data. For each pair of objects number ‘i’ and ‘j’ we.
Of what use is a statistician in climate modeling? Peter Guttorp University of Washington Norwegian Computing Center
1 Chapter 8: Model Inference and Averaging Presented by Hui Fang.
Regularization of energy-based representations Minimize total energy E p (u) + (1- )E d (u,d) E p (u) : Stabilizing function - a smoothness constraint.
Environmental Modeling Spatial Interpolation. 1. Definition ► A procedure of estimating the values of properties at un-sampled sites ► The property must.
Space-time processes NRCSE. Separability Separable covariance structure: Cov(Z(x,t),Z(y,s))=C S (x,y)C T (s,t) Nonseparable alternatives Temporally varying.
Basis Expansions and Generalized Additive Models Basis expansion Piecewise polynomials Splines Generalized Additive Model MARS.
Tree and Forest Classification and Regression Tree Bagging of trees Boosting trees Random Forest.
Exposure Prediction and Measurement Error in Air Pollution and Health Studies Lianne Sheppard Adam A. Szpiro, Sun-Young Kim University of Washington CMAS.
CWR 6536 Stochastic Subsurface Hydrology Optimal Estimation of Hydrologic Parameters.
I. Statistical Methods for Genome-Enabled Prediction of Complex Traits OUTLINE THE CHALLENGES OF PREDICTING COMPLEX TRAITS ORDINARY LEAST SQUARES (OLS)
Biointelligence Laboratory, Seoul National University
Probability Theory and Parameter Estimation I
Model Inference and Averaging
NRCSE 2. Covariances.
CJT 765: Structural Equation Modeling
Latent Variables, Mixture Models and EM
REMOTE SENSING Multispectral Image Classification
Paul D. Sampson Peter Guttorp
Filtering and State Estimation: Basic Concepts
Concepts and Applications of Kriging
Image and Video Processing
Learning From Observed Data
Concepts and Applications of Kriging
Presentation transcript:

Nonstationary covariance structure I: Deformations

Evidence of anisotropy 15 o red 60 o green 105 o blue 150 o brown

Another view of anisotropy

General setup Z(x,t) =  (x,t) + (x) 1/2 E(x,t) +  (x,t) trend + smooth + error We shall assume that  is known or constant t = 1,...,T indexes temporal replications E is L 2 -continuous, mean 0, variance 1, independent of the error  C(x,y) = Cor(E(x,t),E(y,t)) D(x,y) = Var(E(x,t)-E(y,t)) (dispersion)

Geometric anisotropy Recall that if we have an isotropic covariance (circular isocorrelation curves). If for a linear transformation A, we have geometric anisotropy (elliptical isocorrelation curves). General nonstationary correlation structures are typically locally geometrically anisotropic.

The deformation idea In the geometric anisotropic case, write where f(x) = Ax. This suggests using a general nonlinear transformation. Usually d=2 or 3. G-plane D-space We do not want f to fold.

Implementation Consider observations at sites x 1,...,x n. Let be the empirical covariance between sites x i and x j. Minimize where J(f) is a penalty for non-smooth transformations, such as the bending energy

SARMAP An ozone monitoring exercise in California, summer of 1990, collected data on some 130 sites.

Transformation This is for hr. 16 in the afternoon

Identifiability Perrin and Meiring (1999): Let If (1) f and f -1 are differentiable in R n (2)  (u) is differentiable for u>0 then (f,  ) is unique up to a scaling for  and a homothetic transformation for f (scaling, rotation, reflection)

Richness Perrin & Senoussi (2000): Let f and f -1 be differentiable, and let r(x,y) be continuously differentiable. Then (stationarity) iff Let f(0)=0,c i i th column of. Then (isotropy) iff and

The Brownian sheet Let and Then So the Brownian sheet can be thought of as a stationary deformation. It is however not an istropic deformation.

Estimating variability Resample time slices with replacement from the original data (to maintain spatial structure). Re-estimate deformation based on each bootstrap sample. Kriging estimates can be made based on each of the bootstrap estimates, to get a better sense of the variability.

French rainfall data Altitude-adjusted 10-day aggregated rainfall data Nov-Dec for 39 sites from Languedoc-Rousillon region of France.

Estimated deformation

G-plane equicorrelation contours

D-plane Equicorrelation Contours

Uncertainty in deformation Model refitted using 24 of the 36 sites.

The smoothing parameter Cross-validation: Leave out sampling station i, estimate(θ,f) from remaining n-1 stations. Minimize the prediction error for site i, summed over i. Together with bootstrap estimate of variability, very computer intensive.

Thin-plate splines

A Bayesian implementation Likelihood: Prior: Linear part: fix two points in the G-D mapping put a (proper) prior on the remaining two parameters smoothing parameter

Computation Metropolis-Hastings algorithm for sampling from highly multidimensional posterior. Given estimates of D-plane locations, f(x i ), the transformation is extrapolated to the whole domain using thin plate splines. Predictive distributions for (a) temporal variance at unobserved sites, (b) the spatial covariance for pairs of observed and/or unobserved sites, (c) the observation process at unobserved sites.

California ozone

Posterior samples

Other applications Point process deformation (Jensen & Nielsen, Bernoulli, 2000) Deformation of brain images (Worseley et al., 1999)

Global processes Problems such as global warming require modeling of processes that take place on the globe (an oriented sphere). Optimal prediction of quantities such as global mean temperature need models for global covariances. Note: spherical covariances can take values in [-1,1]–not just imbedded in R 3. Also, stationarity and isotropy are identical concepts on the sphere.

Isotropic covariances on the sphere Isotropic covariances on a sphere are of the form where p and q are directions,  pq the angle between them, and P i the Legendre polynomials. Example: a i =(2i+1)  i

Global temperature Global Historical Climatology Network 7280 stations with at least 10 years of data. Subset with 839 stations with data selected.

Isotropic correlations

Spherical deformation Need isotropic covariance model on transformation of sphere/globe Covariance structure on convex manifolds Simple option: deform globe into another globe Alternative: MRF approach

A class of global transformations Iteration between simple parametric deformation of latitude (with parameters changing with longitude) and similar deformations of longitude (changing smoothly with latitude). (Das, 2000)

Three iterations

Resulting isocovariance curves

Comparison IsotropicAnisotropic

Assessing uncertainty

Another current climate problem General circulation models require accurate historical ocean surface temperature recordsocean surface temperature Data from buoys, ships, satellites