Then PCA is performed on the input dataset of eight climate and land use parameters using SPSS. As shown in Table 9, the PCA findings reveal that the three of the eight input parameters have eigenvalues greater than 1.0. The scree plot of eigenvalues is shown in Figure 8.
Table 9
Total variance explained using SPSS
| Component | Initial eigenvalues | Extraction sums of squared loadings | Rotation sums of squared loadings | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Total | % of Variance | Cumulative % | Total | % of Variance | Cumulative % | Total | % of Variance | Cumulative % | |
| 1 (P) | 3.42 | 42.73 | 42.73 | 3.42 | 42.73 | 42.73 | 3.40 | 42.56 | 42.56 |
| 2 (Tmax) | 1.61 | 20.13 | 62.86 | 1.61 | 20.13 | 62.86 | 1.62 | 20.25 | 62.81 |
| 3 (Tmin) | 1.28 | 15.93 | 78.79 | 1.28 | 15.93 | 78.79 | 1.28 | 15.99 | 78.79 |
| 4 (AL) | 0.93 | 11.67 | 90.46 | – | – | – | – | – | – |
| 5 (FL) | 0.61 | 7.67 | 98.13 | – | – | – | – | – | – |
| 6 (GL) | 0.12 | 1.44 | 99.58 | – | – | – | – | – | – |
| 7 (SL) | 0.03 | 0.42 | 99.99 | – | – | – | – | – | – |
| 8 (UL) | 0.00 | 0.01 | 100.0 | – | – | – | – | – | – |
| Component | Initial eigenvalues | Extraction sums of squared loadings | Rotation sums of squared loadings | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Total | % of Variance | Cumulative % | Total | % of Variance | Cumulative % | Total | % of Variance | Cumulative % | |
| 1 (P) | 3.42 | 42.73 | 42.73 | 3.42 | 42.73 | 42.73 | 3.40 | 42.56 | 42.56 |
| 2 (Tmax) | 1.61 | 20.13 | 62.86 | 1.61 | 20.13 | 62.86 | 1.62 | 20.25 | 62.81 |
| 3 (Tmin) | 1.28 | 15.93 | 78.79 | 1.28 | 15.93 | 78.79 | 1.28 | 15.99 | 78.79 |
| 4 (AL) | 0.93 | 11.67 | 90.46 | – | – | – | – | – | – |
| 5 (FL) | 0.61 | 7.67 | 98.13 | – | – | – | – | – | – |
| 6 (GL) | 0.12 | 1.44 | 99.58 | – | – | – | – | – | – |
| 7 (SL) | 0.03 | 0.42 | 99.99 | – | – | – | – | – | – |
| 8 (UL) | 0.00 | 0.01 | 100.0 | – | – | – | – | – | – |
Extraction Method: PCA.
Figure 8
The eigenvalues of the input dataset of eight parameters.