SLIDE 1
A wavelet based approach to climate biome clustering Introduction
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
A wavelet based approach to climate biome clustering Derek Desantis - - PowerPoint PPT Presentation
A wavelet based approach to climate biome clustering Derek Desantis - - PowerPoint PPT Presentation
A wavelet based approach to climate biome clustering Introduction A wavelet based approach to climate biome clustering Derek Desantis University of Nebraska - Lincoln August 7, 2018 A wavelet based approach to climate biome clustering
SLIDE 2
SLIDE 3
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
SLIDE 4
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
Problem
SLIDE 5
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
Problem Only applies to land data
SLIDE 6
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
Problem Only applies to land data Only uses precipitation and temperature data
SLIDE 7
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
Problem Only applies to land data Only uses precipitation and temperature data As the climate changes, so must the biomes
SLIDE 8
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
Problem Only applies to land data Only uses precipitation and temperature data As the climate changes, so must the biomes K¨
- ppen-Gieger is just a heuristic
SLIDE 9
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
Problem Only applies to land data Only uses precipitation and temperature data As the climate changes, so must the biomes K¨
- ppen-Gieger is just a heuristic
Goal Cluster on any chosen variables
SLIDE 10
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
Problem Only applies to land data Only uses precipitation and temperature data As the climate changes, so must the biomes K¨
- ppen-Gieger is just a heuristic
Goal Cluster on any chosen variables Detect where biomes are shifting
SLIDE 11
A wavelet based approach to climate biome clustering Learning Climate Biomes K¨
- ppen-Gieger Model
Problem Only applies to land data Only uses precipitation and temperature data As the climate changes, so must the biomes K¨
- ppen-Gieger is just a heuristic
Goal Cluster on any chosen variables Detect where biomes are shifting Want a data driven model
SLIDE 12
A wavelet based approach to climate biome clustering Coarse Overview of ML Supervised vs Unsupervised
Supervised Learning: Discover salient features of data to separate into predetermined classes - Data comes with labels.
SLIDE 13
A wavelet based approach to climate biome clustering Coarse Overview of ML Supervised vs Unsupervised
Supervised Learning: Discover salient features of data to separate into predetermined classes - Data comes with labels. Example Given an image of a leaf, determine which tree (from a predetermined list) it came from.
SLIDE 14
A wavelet based approach to climate biome clustering Coarse Overview of ML Supervised vs Unsupervised
Supervised Learning: Discover salient features of data to separate into predetermined classes - Data comes with labels. Example Given an image of a leaf, determine which tree (from a predetermined list) it came from. Unsupervised Learning: Discover classes hidden in the data
- Data does not come with labels.
SLIDE 15
A wavelet based approach to climate biome clustering Coarse Overview of ML Supervised vs Unsupervised
Supervised Learning: Discover salient features of data to separate into predetermined classes - Data comes with labels. Example Given an image of a leaf, determine which tree (from a predetermined list) it came from. Unsupervised Learning: Discover classes hidden in the data
- Data does not come with labels.
Example Given images of leaves, automatically sort images into bins based of features (not set or necessarily known).
SLIDE 16
A wavelet based approach to climate biome clustering Coarse Overview of ML Difficulty in ML
Remark Determining biomes directly from data is unsupervised
SLIDE 17
A wavelet based approach to climate biome clustering Coarse Overview of ML Difficulty in ML
Remark Determining biomes directly from data is unsupervised Generically speaking, supervised is “easier” than unsupervised
SLIDE 18
A wavelet based approach to climate biome clustering Coarse Overview of ML Difficulty in ML
Remark Determining biomes directly from data is unsupervised Generically speaking, supervised is “easier” than unsupervised Large scale unsupervised learning is notoriously difficult (AKA prohibitively expensive): K-means ∼ O(K ∗ number data ∗ dim)
SLIDE 19
A wavelet based approach to climate biome clustering Wavelets Brief Overview
Example Let f = [1, 1, 2, 2, .5, 0, 0, 0, 3, 1].
SLIDE 20
A wavelet based approach to climate biome clustering Wavelets Brief Overview
Example Let f = [1, 1, 2, 2, .5, 0, 0, 0, 3, 1]. Taking the wavelet transform yields two new signals:
1 Approximation Information - Averages of pairs of points 2 Detail Information - Differences from averages
SLIDE 21
A wavelet based approach to climate biome clustering Wavelets Brief Overview
Example Let f = [1, 1, 2, 2, .5, 0, 0, 0, 3, 1]. Taking the wavelet transform yields two new signals:
1 Approximation Information - Averages of pairs of points 2 Detail Information - Differences from averages
Taking DWT: g1 = [1, 2, 0.25, 0, 2] h1 = [0, 0, 0.25, 0, 1]
SLIDE 22
A wavelet based approach to climate biome clustering Wavelets Brief Overview
Example Let f = [1, 1, 2, 2, .5, 0, 0, 0, 3, 1]. Taking the wavelet transform yields two new signals:
1 Approximation Information - Averages of pairs of points 2 Detail Information - Differences from averages
Taking DWT: g1 = [1, 2, 0.25, 0, 2] h1 = [0, 0, 0.25, 0, 1]
SLIDE 23
A wavelet based approach to climate biome clustering Clustering Biomes Select Variables
LOCA Data: 1950-1970
SLIDE 24
A wavelet based approach to climate biome clustering Clustering Biomes Select Variables
LOCA Data: 1950-1970 Choose wavelets: Space: Haar Time: db2
SLIDE 25
A wavelet based approach to climate biome clustering Clustering Biomes Prepare Data
Prec Data: t=0
SLIDE 26
A wavelet based approach to climate biome clustering Clustering Biomes Prepare Data
Prec Data: t=0 Interpolate Nan:
SLIDE 27
A wavelet based approach to climate biome clustering Clustering Biomes Take DWT of Data
Interpolate Nan:
SLIDE 28
A wavelet based approach to climate biome clustering Clustering Biomes Take DWT of Data
DWT: 2 space, 0 time
SLIDE 29
A wavelet based approach to climate biome clustering Clustering Biomes Clustering
Locate data values corresponding to non-NAN values (with ǫ boundary)
SLIDE 30
A wavelet based approach to climate biome clustering Clustering Biomes Clustering
Locate data values corresponding to non-NAN values (with ǫ boundary) Cluster the approximation coefficients for each variable
SLIDE 31
A wavelet based approach to climate biome clustering Clustering Biomes Clustering
Locate data values corresponding to non-NAN values (with ǫ boundary) Cluster the approximation coefficients for each variable
Settled on K-means Determined number of clusters using silhouette and Calinski Harabaz scores Used 3 clusters for Prec, 4 clusters for Tmin and Tmax
SLIDE 32
A wavelet based approach to climate biome clustering Clustering Biomes Map Clusters Back To Data
Data Clusters (1,0): 1950-1970
SLIDE 33
A wavelet based approach to climate biome clustering Clustering Biomes Map Clusters Back To Data
Data Clusters (1,0): 1950-1970
SLIDE 34
A wavelet based approach to climate biome clustering Clustering Biomes Map Clusters Back To Data
Data Clusters (1,0): 1950-1970
SLIDE 35
A wavelet based approach to climate biome clustering Clustering Biomes Map Clusters Back To Data
Data Clusters (1,0): 1950-1970
SLIDE 36
A wavelet based approach to climate biome clustering Clustering Biomes Final Clusters
Combined Data Clusters (1,0): 1950-1970
SLIDE 37
A wavelet based approach to climate biome clustering Clustering Biomes Final Clusters
North America K¨
- ppen-Gieger Model
SLIDE 38
A wavelet based approach to climate biome clustering Biome Shift Clusters Change
Combined Data Clusters (1,0): 1950-1970
SLIDE 39
A wavelet based approach to climate biome clustering Biome Shift Clusters Change
Combined Data Clusters (1,0): 1993-2013
SLIDE 40
A wavelet based approach to climate biome clustering Biome Shift Find Correlation Between Clusters
Correlation Between 1950-1970 Clusters and 1993-2013 Clusters
SLIDE 41
A wavelet based approach to climate biome clustering Biome Shift Find Correlation Between Clusters
Sorted Correlation Between 1950-1970 Clusters and 1993-2013 Clusters
SLIDE 42
A wavelet based approach to climate biome clustering Biome Shift Find Correlation Between Clusters
Reindex Combined Data Clusters (1,0): 1950-1970
SLIDE 43
A wavelet based approach to climate biome clustering Biome Shift Find Correlation Between Clusters
Combined Data Clusters (1,0): 1993-2013
SLIDE 44
A wavelet based approach to climate biome clustering Biome Shift Find Correlation Between Clusters
Difference Between 1950-1970 Clusters and 1993-2013 Clusters
SLIDE 45
A wavelet based approach to climate biome clustering Future Work
1 Add other variables (e.g. wind)
SLIDE 46
A wavelet based approach to climate biome clustering Future Work
1 Add other variables (e.g. wind) 2 Parallelism and optimization
SLIDE 47
A wavelet based approach to climate biome clustering Future Work
1 Add other variables (e.g. wind) 2 Parallelism and optimization 3 Perform an analytical comparison to the K¨
- ppen-Gieger
Model
SLIDE 48
A wavelet based approach to climate biome clustering Future Work
1 Add other variables (e.g. wind) 2 Parallelism and optimization 3 Perform an analytical comparison to the K¨
- ppen-Gieger