Maïlys Lopes

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

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.

Object-based classification of grasslands from high resolution satellite image time series using Gaussian mean map kernels

This paper deals with the classification of grasslands using high resolution satellite image time series. Grasslands considered in this work are semi-natural elements in fragmented landscapes, i.e., they are heterogeneous and small elements. The first contribution of this study is to account for grassland heterogeneity while working at the object scale by modeling its pixels distributions by a Gaussian distribution. To measure the similarity between two grasslands, a new kernel is proposed as a second contribution: the a-Gaussian mean kernel. It allows to weight the influence of the covariance matrix when comparing two Gaussian distributions. This kernel is introduced in Support Vector Machine for the supervised classification of grasslands from south-west France. A dense intra-annual multispectral time series of Formosat-2 satellite is used for the classification of grasslands management practices, while an inter-annual NDVI time series of Formosat-2 is used for permanent and temporary grasslands discrimination. Results are compared to other existing pixel- and object-based approaches in terms of classification accuracy and processing time. The proposed method shows to be a good compromise between processing speed and classification accuracy. It can adapt to the classification constraints and it encompasses several similarity measures known in the literature. It is appropriate for the classification of small and heterogeneous objects such as grasslands.

Spectro-Temporal Heterogeneity Measures from Dense High Spatial Resolution Satellite Image Time Series: Application to Grassland Species Diversity Estimation

Grasslands represent a significant source of biodiversity that is important to monitor over large extents. The Spectral Variation Hypothesis (SVH) assumes that the Spectral Heterogeneity (SH) measured from remote sensing data can be used as a proxy for species diversity. Here, we argue the hypothesis that the grassland’s species differ in their phenology and, hence, that the temporal variations can be used in addition to the spectral variations. The purpose of this study is to attempt verifying the SVH in grasslands using the temporal information provided by dense Satellite Image Time Series (SITS) with a high spatial resolution. Our method to assess the spectro-temporal heterogeneity is based on a clustering of grasslands using a robust technique for high dimensional data. We propose new SH measures derived from this clustering and computed at the grassland level. We compare them to the Mean Distance to Centroid (MDC). The method is experimented on 192 grasslands from southwest France using an intra-annual multispectral SPOT5 SITS comprising 18 images and using single images from this SITS. The combination of two of the proposed SH measures—the within-class variability and the entropy—in a multivariate linear model explained the variance of the grasslands’ Shannon index more than the MDC. However, there were no significant differences between the predicted values issued from the best models using multitemporal and monotemporal imagery. We conclude that multitemporal data at a spatial resolution of 10 m do not contribute to estimating the species diversity. The temporal variations may be more related to the effect of management practices.

Potential of Sentinel-2 and SPOT5 (Take5) time series for the estimation of grasslands biodiversity indices

The aim of this study is to assess the potential of satellite image time series with high spatial and high temporal resolutions for the prediction of grasslands plant biodiversity. The grasslands are modeled at the object scale to be consistent with ecological measurements (one biodiversity index per grassland). A kernel regression is used to predict the biodiversity index of a grassland from its spectro-temporal reflectance. The method is applied using two intra-annual multispectral or NDVI time series of SPOT5 Take5 (18 dates) and Sentinel-2 (7 dates) to predict the Shannon and the Simpson indices of about 200 grasslands in south-west France. The best coefficient of determination for the prediction of the Shannon index is 0.13 and it is 0.17 for the Simpson index prediction. The unsatisfactory results suggest that a high temporal resolution combined with a high spatial resolution and multispectral bands are not sufficient to estimate grassland biodiversity at the grassland scale.

High dimensional Kullback-Leibler divergence for grassland management practices classification from high resolution satellite image time series

The aim of this study is to build a model suitable to classify grassland management practices using satellite image time series with high spatial resolution. The study site is located in southern France where 52 parcels with three management types were selected. The NDVI computed from a Formosat-2 intra-annual time series of 17 images was used. To work at the parcel scale while accounting for the spectral variability inside the grasslands, the pixels signal distribution is modeled by a Gaussian distribution. To deal with the small ground sample size compared to the large number of variables, a parsimonious Gaussian model is used. A high dimensional symmetrized Kullback-Leibler divergence (KLD) is introduced to compute the similarity between each pair of grasslands. Our proposed model provides better results than the conventional KLD in terms of classification accuracy using SVM.