Open AccessWater Depth Inversion based on Landsat-8 Date and Random Forest Algorithm
Author(s) -
Jin Zhang,
Shujun Li,
Wang Mo
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1437/1/012073
Subject(s) - inversion (geology) , random forest , remote sensing , algorithm , geology , computer science , artificial intelligence , geomorphology , structural basin
In view of the fact that the traditional water depth inversion model is susceptible to water quality and environmental factors, the water depth inversion model is constructed using the random forest algorithm using the high resolution remote sensing image of the Huangyan Island area and the corresponding measured water depth data. The influence of the number of training sets on the inversion of remote sensing water depth is explored. The results show that the inversion accuracy of random forest is higher, and for this method, the more features in the training set, the better the effect of remote sensing inversion.