A Machine Learning and Cross-Validation Approach for the Discrimination of Vegetation Physiognomic Types Using Satellite Based Multispectral and Multitemporal Data

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left" rowspan="2">Features</td><td class="align_center" colspan="2"> Temporal composites</td><td class="align_center" rowspan="2">Subtotal features</td></tr><tr class="thead"><td class="align_center">Monthly</td><td class="align_center">Percentiles</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">Spectral: Red, Near Infrared, Blue, Green, Mid Infrared, Shortwave Infrared 1, and Shortwave Infrared 2</td><td class="align_center">12 × 7</td><td class="align_center">11 × 7</td><td class="align_center">161</td></tr><tr><td class="align_left">Spectral indices: NDVI, EVI, and LSWI</td><td class="align_center">12 × 3</td><td class="align_center">11 × 3</td><td class="align_center">69</td></tr><tr><td class="align_left" colspan="4"><hr/></td></tr><tr><td class="align_left">Total features</td><td class="align_left" colspan="2"> </td><td class="align_center">230</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Description of the input features used in the research.

Scientifica

tab2

Table 2

Table 2: A Machine Learning and Cross-Validation Approach for the Discrimination of Vegetation Physiognomic Types Using Satellite Based Multispectral and Multitemporal Data 

Table 2 | A Machine Learning and Cross-Validation Approach for the Discrimination of Vegetation Physiognomic Types Using Satellite Based Multispectral and Multitemporal Data 