Optical time series for the separation of land cover types with similar spectral signatures: cocoa agroforest and forest

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{Batista:2022:IJRS,

• author = "Joao E. Batista and Nuno M. Rodrigues and Ana I. R. Cabral and Maria J. P. Vasconcelos and Adriano Venturieri and Luiz G. T. Silva and Sara Silva",
• title = "Optical time series for the separation of land cover types with similar spectral signatures: cocoa agroforest and forest",
• journal = "International Journal of Remote Sensing",
• year = "2022",
• volume = "43",
• number = "9",
• pages = "3298--3319",
• keywords = "genetic algorithms, genetic programming, Cocoa agroforest classification, land cover mapping, machine learning, time series, tropical areas",
• publisher = "Taylor \& Francis",
• DOI = "doi:10.1080/01431161.2022.2089540",
• data_url = "https://github.com/jespb/Cocoa_PublicDS",
• size = "22 pages",
• abstract = "One of the main applications of machine learning (ML) in remote sensing (RS) is the pixel-level classification of satellite images into land cover types. Although classes with different spectral signatures can be easily separated, e.g. aquatic and terrestrial land cover types, others have similar spectral signatures and are hard to separate using only the information within a single pixel. This work focused on the separation of two cover types with similar spectral signatures, cocoa agroforest and forest, over an area in Para, Brazil. For this, we study the training and application of several ML algorithms on datasets obtained from a single composite image, a time-series (TS) composite obtained from the same location and by preprocessing the TS composite using simple TS preprocessing techniques. As expected, when ML algorithms are applied to a dataset obtained from a composite image, the median producer accuracy (PA) and user accuracy (UA) in those two classes are significantly lower than the median overall accuracy (OA) for all classes. The second dataset allows the ML models to learn the evolution of the spectral signatures over 5 months. Compared to the first dataset, the results indicate that ML models generalise better using TS data, even if the series are short and without any preprocessing. This generalization is further improved in the last dataset. The ML models are subsequently applied to an area with different geographical bounds. These last results indicate that, out of seven classifiers, the popular random forest (RF) algorithm ranked fourth, while XGBoost (xGB) obtained the best results. The best OA, as well as the best PA/UA balance, were obtained by performing feature construction using the M3GP algorithm and then applying XGB to the new extended dataset.",
• notes = "a LASIGE, Faculty of Sciences, University of Lisbon, Portugal",

}

Genetic Programming entries for Joao E Batista Nuno Miguel Rodrigues Domingos Ana Isabel Rosa Cabral Maria Jose Vasconcelos Adriano Venturieri Luiz Guilherme Teixeira Silva Sara Silva

Citations