NLDR methods for high dimensional NIRS dataset: application to vineyard soils characterization

In the context of vineyard soils characterizationn this paper explores and compare dierent recent Non Linear Dimensionality Reduction (NLDR) methods on a high-dimensional Near InfraRed Spectroscopy (NIRS) dataset. NLDR methods are based on k-neighborhood criterion and Euclidean and fractional distances metrics are tested. Results show that Multiscale Jensen-Shannon Embedding (Ms JSE) coupled with eu-clidean distance outperform all over methods. Application on data is made at global scale and at dierent scale of depth of soil.