Translator Disclaimer
12 December 2019 Long-term forest mapping from classification of MODIS time series: best practices
Author Affiliations +
Abstract

Coarse spatial resolution (CSR) time series have been successfully used at regional scale to produce homogeneous and up-to-date forest cover maps. This study aims to classify CSR time series using a nomenclature as detailed as national forest inventories nomenclatures. To identify best practices for classifying time series, three algorithms are compared: maximum likelihood, support vector machine, and random forest. For each algorithm, training, temporal compositing, and selection of input features have been optimized. Results establish a clear improvement in classification accuracy when red, near-infrared, and short-wave infrared spectral bands are used instead of vegetation indices. Temporal compositing has a major impact when the whole phenological cycle is used for 3 consecutive years. Random forest produces the best classification, support vector machine appears to be sensitive to overtraining, and maximum likelihood is unable to deal with the complex characteristics of forest and natural vegetation classes.

© 2019 Society of Photo-Optical Instrumentation Engineers (SPIE) 1931-3195/2019/$28.00 © 2019 SPIE
Jean-Philippe Denux, Emmanuelle Cano, Laurence Hubert-Moy, Marie Parrens, and Véronique Chéret "Long-term forest mapping from classification of MODIS time series: best practices," Journal of Applied Remote Sensing 14(2), 022208 (12 December 2019). https://doi.org/10.1117/1.JRS.14.022208
Received: 5 June 2019; Accepted: 20 November 2019; Published: 12 December 2019
JOURNAL ARTICLE
18 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Vegetation MTF in-flight measurement using HRVIR
Proceedings of SPIE (November 15 2000)
Advanced band sharpening study
Proceedings of SPIE (August 04 1997)

Back to Top