next up previous
Next: Conclusions Up: Reproducing the Grosswetterlagen Using Previous: 700hPa Geopotential Height

500hPa Geopotential Height

Figure 4 shows a graph of the proportion of correctly classified test patterns against values of k ranging from 1 to 100, for k-nearest neighbour classifiers used to reproduce the Grosswetterlagen catalogue on the basis of the first 18 principal components of the 500hPa geopotential height field. In each case a leave-one-out cross-validation strategy was employed to estimate the true generalisation error of the classifier. The optimal value for k was found to be 1, at which point 71.02% of the test patterns were classified correctly.


  
Figure 3: Graph of the proportion of correctly classified patterns against kfor k-nearest neighbour classifiers reproducing the Grosswetterlagen catalogue on the basis of the first 18 principal components of the 500hPa geopotential height field.
\begin{figure}
\begin{centering}
\includegraphics[scale=0.6]{results/partc/knn.eps}
\end{centering}\end{figure}

Table 3 shows a confusion matrix for the optimal 1-nearest neighbour classifier, again using a leave-one-out cross validation approach to estimate the true generalisation performance.


 
Table 3: Confusion matrix for a 1-nearest neighbour classifier reproducing the Grosswetterlagen catalogue on the basis of the first 18 principal components of the 500hPa geopotential height field.
  Model Classification
 
\begin{sideways}Wa \end{sideways}

\begin{sideways}Wz \end{sideways}

\begin{sideways}Ws \end{sideways}

\begin{sideways}Ww \end{sideways}

\begin{sideways}SWa \end{sideways}

\begin{sideways}SWz \end{sideways}

\begin{sideways}NWa \end{sideways}

\begin{sideways}NWz \end{sideways}

\begin{sideways}HM \end{sideways}

\begin{sideways}BM \end{sideways}

\begin{sideways}TM \end{sideways}

\begin{sideways}Na \end{sideways}

\begin{sideways}Nz \end{sideways}

\begin{sideways}HNa \end{sideways}

\begin{sideways}HNz \end{sideways}

\begin{sideways}HB \end{sideways}

\begin{sideways}TrM \end{sideways}

\begin{sideways}NEa \end{sideways}

\begin{sideways}NEz \end{sideways}

\begin{sideways}HFa \end{sideways}

\begin{sideways}HFz \end{sideways}

\begin{sideways}HNFa\end{sideways}

\begin{sideways}HNFz\end{sideways}

\begin{sideways}SEa \end{sideways}

\begin{sideways}SEz \end{sideways}

\begin{sideways}Sa \end{sideways}

\begin{sideways}Sz \end{sideways}

\begin{sideways}TB \end{sideways}

\begin{sideways}TrW \end{sideways}

\begin{sideways}U \end{sideways}
  Wa 422 56 1 4 9 5 7 10 20 31 0 0 5 1 3 2 4 2 4 1 0 1 1 1 0 3 0 2 4 7
  Wz 70 1168 14 12 14 21 14 30 18 49 2 1 14 2 2 4 30 1 2 3 4 0 1 3 0 1 2 9 20 13
  Ws 0 17 213 3 1 4 2 2 0 3 2 0 2 2 1 1 1 0 1 0 0 1 2 2 1 0 1 0 5 3
  Ww 3 8 7 135 3 3 0 2 6 9 1 1 1 0 0 1 2 0 0 6 3 1 1 3 3 1 0 2 4 2
  SWa 9 11 2 2 201 7 3 2 11 12 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 6 1 2 4 4
  SWz 7 20 7 5 7 237 1 4 4 5 1 1 0 0 1 1 1 0 1 2 1 1 1 2 2 4 0 3 4 5
  NWa 8 9 0 0 2 0 167 2 6 11 1 0 2 1 1 5 1 0 1 0 0 0 0 0 0 0 0 0 4 3
  NWz 11 26 2 3 2 2 3 291 9 15 2 3 8 1 2 4 12 1 2 0 0 0 0 0 0 0 0 0 4 9
  HM 24 8 0 3 10 5 5 3 370 32 0 4 3 1 2 17 2 2 1 8 0 2 1 5 1 2 2 1 4 5
  BM 24 45 3 8 11 7 14 15 33 727 8 0 6 3 2 14 13 7 3 8 6 7 5 9 2 8 0 0 14 13
  TM 0 5 3 1 0 0 0 3 1 8 168 1 1 0 4 2 9 2 0 1 3 0 2 3 4 1 0 2 7 6
  Na 0 0 0 1 0 0 0 2 0 5 0 47 1 0 0 1 0 4 0 0 1 0 0 0 1 0 1 0 0 1
  Nz 2 18 1 0 1 0 2 6 2 6 2 1 189 2 1 3 7 1 2 1 1 0 1 1 0 0 0 1 4 3
  HNa 1 2 1 0 0 0 2 0 2 5 0 0 4 130 2 2 1 1 1 3 1 0 1 0 0 0 0 1 0 2

\begin{sideways}\makebox[0pt]{True Classification}
\end{sideways}
HNz 1 3 1 0 0 0 1 1 3 2 1 0 2 2 134 2 2 1 1 0 2 4 2 0 1 1 0 1 3 5
  HB 4 2 0 0 0 1 6 6 10 13 3 0 3 6 2 245 4 1 5 6 1 3 0 2 0 0 1 0 2 1
  TrM 7 25 4 3 0 0 0 13 4 12 7 0 5 0 2 6 263 1 5 2 3 0 0 2 0 0 0 9 14 7
  NEa 1 1 0 1 1 0 2 2 0 5 1 3 2 2 0 6 1 90 6 4 2 1 0 0 0 0 0 0 0 2
  NEz 1 1 1 0 0 1 2 3 4 6 0 0 3 2 0 7 3 6 101 3 1 0 1 2 2 0 0 0 1 3
  HFa 0 4 1 3 0 1 0 2 3 16 1 0 2 3 0 9 3 6 2 216 6 6 6 4 6 2 0 3 0 4
  HFz 0 2 1 3 0 2 0 0 2 4 7 1 1 1 0 3 2 0 1 5 133 1 1 5 4 1 0 4 3 1
  HNFa 0 0 0 0 0 1 0 0 4 5 2 0 0 1 3 4 0 2 1 3 1 91 3 2 2 0 0 0 5 0
  HNFz 1 0 2 1 0 3 0 0 1 5 5 2 3 1 1 2 0 0 2 3 1 2 107 2 3 1 0 1 3 0
  SEa 1 2 0 6 0 2 1 1 6 8 0 0 1 3 2 0 1 0 2 5 2 1 2 127 2 4 1 3 4 3
  SEz 1 1 2 4 1 2 0 0 1 4 7 0 0 0 0 0 0 0 1 4 5 2 0 3 84 1 2 2 2 0
  Sa 5 1 0 0 5 2 0 0 7 11 0 0 0 0 1 0 0 0 1 1 2 1 0 7 4 113 0 1 2 0
  Sz 1 0 1 0 3 0 0 0 3 3 0 1 0 1 0 1 1 0 0 2 0 1 0 1 0 2 51 0 1 0
  TB 2 10 1 1 1 5 0 0 2 2 2 0 2 1 1 0 3 1 2 2 5 0 2 4 0 0 0 165 7 6
  TrW 6 21 9 4 3 4 5 6 4 14 8 0 3 1 2 2 12 3 2 3 2 3 3 3 1 3 0 8 347 5
  U 9 12 4 2 6 5 2 10 12 18 3 1 4 4 3 5 11 1 1 1 2 0 1 4 1 5 0 2 13 13
 


next up previous
Next: Conclusions Up: Reproducing the Grosswetterlagen Using Previous: 700hPa Geopotential Height
Gavin Cawley ESE Faculty
1999-08-11