Fig 1.
Topography and geographical location of Taiwan.
The topography was derived from the ASTER GDEM 2 digital elevation model (cf. Sect. Digital elevation model and related inputs). The depicted vegetation plots are described in Sect. Training data for the MCF conditions map. Country borders were taken from OpenStreetMap [27].
Fig 2.
Altitudinal occurrence of MCF and non-MCF vegetation plots.
The depicted vegetation plots are described in Sect. Training data for the MCF conditions map.
Fig 3.
Ground fog frequency map calculated from MODIS data captured between 1 January 2003 and 31 December 2014.
Fig 4.
Maps of MCF conditions with (A) and without (B) the ground fog frequency being included.
Table 1.
Validation results for MCF conditions maps A and B.
The best value of each statistical parameter is written in bold type. TP = true positives; TN = true negatives; FP = false positives; FN = false negatives; MCC = Matthews correlation coefficient; PC = Proportion correct (PC); POD = Probability of detection; POFD = Probability of false detection; FAR = False alarm rate (FAR).
Table 2.
Validation results for Random Forest models trained with different raster input sets.
The best value of each statistical parameter is written in bold type. TP = true positives; TN = true negatives; FP = false positives; FN = false negatives; MCC = Matthews correlation coefficient; PC = Proportion correct (PC); POD = Probability of detection; POFD = Probability of false detection; FAR = False alarm rate (FAR).
Fig 5.
Final MCF map (green area), created from the combination of the MCF conditions map B (green and orange area) and the forest map (white and green area).