Tree Species Classification in Temperate Forests Using Formosat-2 Satellite Image Time Series

Abstract

Abstract:Mapping forest composition is a major concern for forest management, biodiversity assessment and for understanding the potential impacts of climate change on tree species distribution. In this study, the suitability of a dense high spatial resolution multispectral Formosat-2 satellite image time-series (SITS) to discriminate tree species in temperate forests is investigated. Based on a 17-date SITS acquired across one year, thirteen major tree species (8 broadleaves and 5 conifers) are classified in a study area of southwest France. The performance of parametric (GMM) and nonparametric (k-NN, RF, SVM) methods are compared at three class hierarchy levels for different versions of the SITS: (i) a smoothed noise-free version based on the Whittaker smoother; (ii) a non-smoothed cloudy version including all the dates; (iii) a non-smoothed noise-free version including only 14 dates. Noise refers to pixels contaminated by clouds and cloud shadows. The results of the 108 distinct classifications show a very high suitability of the SITS to identify the forest tree species based on phenological differences (average κ = 0.93 estimated by cross-validation based on 1235 field-collected plots). SVM is found to be the best classifier with very close results from the other classifiers. No clear benefit of removing noise by smoothing can be observed. Classification accuracy is even improved using the non-smoothed cloudy version of the SITS compared to the 14 cloud-free image time series. However conclusions of the results need to be considered with caution because of possible overfitting. Disagreements also appear between the maps produced by the classifiers for complex mixed forests, suggesting a higher classification uncertainty in these contexts. Our findings suggest that time-series data can be a good alternative to hyperspectral data for mapping forest types. It also demonstrates the potential contribution of the recently launched Sentinel-2 satellite for studying forest ecosystems.

Exploring Multispectral ALS Data for Tree Species Classification

“…Photogrammetric point clouds produced from images collected with unmanned aerial vehicles (UAVs) [25] and even space-borne very high resolution stereo-imagery (VHRSI) [26] have also been used for this purpose. To make use of the differences in phenology between different tree species, time series of satellite images are being studied [27].…”

Object-Based Classification of Grasslands from High Resolution Satellite Image Time Series Using Gaussian Mean Map Kernels

“…It has been successfully applied to smooth NDVI time series in the literature [72][73][74][75]. The smoother was adapted for unequally-spaced intervals and accounted for missing data (see [62] for a detailed description of the method). The smoothing parameter was the same for all of the pixels.…”

“…Notice that the smoothing is done at the cost of under-estimating the local maxima of the temporal profile. and accounted for missing data (see [62] for a detailed description of the method). The smoothing For the intra-annual time series, we used all of the spectral information.…”

“…To our knowledge, these methods do not use the high spatial and the high temporal resolutions jointly. Moreover, all of these studies used vegetation indices as a variable, although it has been shown that classification results are better when using more spectral information [35,62].…”

Analysis of Vegetation Change and Mapping Tree Species in Mountainous Area Using Multi-Source Satellite Data: A Case Study of Djebel El Ouahch, Algeria

“…Unfortunately, obtaining an accurate tree species classification from high floristic diversity, using Multispectral Landsat images, is still a challenging task, many factors influences the spectral response of tree species such as: leaf biochemical and physiological properties, canopy structure, density, age, and environmental conditions [12]. In that respect, Google Earth imagery, as a free and open source data, with spatial resolution less than 0.5m, have provided great supports for mapping the spatial distribution of tree species using the visual characteristics such as shape, texture, colour, size, pattern, site….…”