1. 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.

2. 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

3. Global temperature Global Historical Climatology Network 7280 stations with at least 10 years of data. Subset with 839 stations with data 1950-1991 selected.

4. Isotropic correlations

5. The Fourier transform

6. Properties of Fourier transforms Convolution Scaling Translation

7. Parceval’s theorem Relates space integration to frequency integration. Decomposes variability.

8. Aliasing Observe field at lattice of spacing . Since the frequencies  and  ’=  +2  m/  are aliases of each other, and indistinguishable. The highest distinguishable frequency is , the Nyquist frequency.

9. Illustration of aliasing Aliasing applet

10. Spectral representation Stationary processes Spectral process Y has stationary increments If F has a density f, it is called the spectral density.

11. Estimating the spectrum For process observed on nxn grid, estimate spectrum by periodogram Equivalent to DFT of sample covariance

12. Properties of the periodogram Periodogram values at Fourier frequencies (j,k)  are uncorrelated asymptotically unbiased not consistent To get a consistent estimate of the spectrum, smooth over nearby frequencies

13. Some common isotropic spectra Squared exponential Matérn

14. A simulated process

15. Thetford canopy heights 39-year thinned commercial plantation of Scots pine in Thetford Forest, UK Density 1000 trees/ha 36m x 120m area surveyed for crown height Focus on 32 x 32 subset

16. Spectrum of canopy heights

17. Whittle likelihood Approximation to Gaussian likelihood using periodogram: where the sum is over Fourier frequencies, avoiding 0, and f is the spectral density Takes O(N logN) operations to calculate instead of O(N 3 ).

18. Using non-gridded data Consider where Then Y is stationary with spectral density Viewing Y as a lattice process, it has spectral density

19. Estimation Let where J x is the grid square with center x and n x is the number of sites in the square. Define the tapered periodogram where. The Whittle likelihood is approximately

20. A simulated example

21. Estimated variogram

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

23. Another view of anisotropy

24. 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.

25. Lindgren & Rychlik transformation