Contribution of SPOT-7 multi-temporal imagery for mapping wetland vegetation

Hubert‐Moy, Laurence; Fabre, Elodie; Rapinel, Sébastien

doi:10.1080/22797254.2020.1795727

Cited by 7 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The table includes only the results of studies using hyperspectral data (Hyper) or multispectral data (Multi) and the sources of accuracies for classes of Natura 2000 habitats. Code Natura 2000 RS data F1 score from this study F1 score from literature Source Meadows (1340) Hyper 0.61 No data No data Multi 0.42 No data No data Meadows (6410) Hyper 0.69; 0.79 0.73 44 Multi 0.58; 0.59 0.85 45 0.74–0.85 46 0.74 47 Meadows (6440) Hyper 0.87; 0.90 0.83 20 Multi 0.82; 0.83 No data No data Meadows (6510) Hyper 0.71 0.72 48 0.85 18 Multi 0.39 0.89 49 0.77–0.90 46 Grassland (6230) Hyper ...…”

Section: Discussionmentioning

confidence: 99%

The utility of airborne hyperspectral and satellite multispectral images in identifying Natura 2000 non-forest habitats for conservation purposes

Jarocińska

Kopeć

Niedzielko

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Aerial hyperspectral and multispectral satellite data are the two most commonly used datasets to identify natural and semi-natural vegetation. However, there is no documented analysis based on data from several areas concerning the difference in the classification accuracy of non-forest Natura 2000 habitat with the use of aerial hyperspectral and satellite multispectral data. Also, there is no recommendation, on which habitat can be classified with sufficient accuracy using free multispectral images. This study aimed to analyse the difference in classification accuracy of Natura 2000 habitats representing: meadows, grasslands, heaths and mires between data with different spectral resolutions and the results utility for nature conservation compared to conventional maps. The analysis was conducted in five study areas in Poland. The classification was performed on multispectral Sentinel-2 (S2) and hyperspectral HySpex (HS) images using the Random Forest algorithm. Based on the results, it can be stated that the use of HS data resulted in higher classification accuracy, on average 0.14, than using S2 images, regardless of the area of the habitat. However, the difference in accuracy was not constant, varying by area and habitat characterisation. Greater differences in accuracy were observed for areas where habitats were characterised by high α-diversity or β-diversity. The HS and S2 data make it possible to create maps that provide a great deal of new knowledge about the distribution of Natura 2000 habitats, which is necessary for the management of protected areas. The obtained results indicate that by using S2 images it is possible to identify, at a satisfactory level, alluvial meadows and grassland. For heaths and mires, using HS data improved the results, but it is also possible to acquire general distribution of these classes, whereas HS images are obligatory for mapping salt, Molinia and lowland hay meadows.

show abstract

Section: Discussionmentioning

confidence: 99%

The utility of airborne hyperspectral and satellite multispectral images in identifying Natura 2000 non-forest habitats for conservation purposes

Jarocińska

Kopeć

Niedzielko

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Applying RF (or other machine learning methods) directly to raw satellite multitemporal imagery data from discrete time series is a common method for vegetation and habitat mapping. These time series, typically based on a limited number of cloud-free scenes (e.g., <15%) selected within one year, can be constructed using individual spectral bands or predefined vegetation indices chosen by the authors [6,14,15,17,18,[70][71][72]. In our study we used Sentinel-2 spectral bands discrete time series as input data for RF, avoiding an uncritical pre-selection among various available vegetation indices.…”

Section: Pure Machine Learning Approachmentioning

confidence: 99%

“…This lower performance was expected for several reasons. Model B typically employs input data based on time series of images selected for their cloud-free and low-cloud-cover conditions in a single reference year, reducing the data processing complexity, e.g., [14]. However, this approach often results in a limited number of images being available, with missing data for specific months.…”

Section: Models Comparison 421 Pure Machine Learning Approach: B Modelsmentioning

confidence: 99%

“…These kinds of data are essential for an accurate supervised classification and mapping of plant communities and habitats [5][6][7][8][9][10][11][12][13]. Many studies have demonstrated the potential of direct machine learning applications for raw satellite multitemporal data [14][15][16][17][18]. These models, which we can define as 'Pure Machine Learning' according to Durell et al [19], usually use time series of individual spectral bands or classic vegetation indices, such as the popular NDVI [20], consisting of a limited number of scenes within a single year.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation and Selection of Multi-Spectral Indices to Classify Vegetation Using Multivariate Functional Principal Component Analysis

Pesaresi,

Mancini,

Quattrini

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

The identification, classification and mapping of different plant communities and habitats is of fundamental importance for defining biodiversity monitoring and conservation strategies. Today, the availability of high temporal, spatial and spectral data from remote sensing platforms provides dense time series over different spectral bands. In the case of supervised mapping, time series based on classical vegetation indices (e.g., NDVI, GNDVI, …) are usually input characteristics, but the selection of the best index or set of indices (which guarantees the best performance) is still based on human experience and is also influenced by the study area. In this work, several different time series, based on Sentinel-2 images, were created exploring new combinations of bands that extend the classic basic formulas as the normalized difference index. Multivariate Functional Principal Component Analysis (MFPCA) was used to contemporarily decompose the multiple time series. The principal multivariate seasonal spectral variations identified (MFPCA scores) were classified by using a Random Forest (RF) model. The MFPCA and RF classifications were nested into a forward selection strategy to identify the proper and minimum set of indices’ (dense) time series that produced the most accurate supervised classification of plant communities and habitat. The results we obtained can be summarized as follows: (i) the selection of the best set of time series is specific to the study area and the habitats involved; (ii) well-known and widely used indices such as the NDVI are not selected as the indices with the best performance; instead, time series based on original indices (in terms of formula or combination of bands) or underused indices (such as those derivable with the visible bands) are selected; (iii) MFPCA efficiently reduces the dimensionality of the data (multiple dense time series) providing ecologically interpretable results representing an important tool for habitat modelling outperforming conventional approaches that consider only discrete time series.

show abstract

“…Therefore, satellite data are more effectively used in vegetation monitoring, providing large-area coverage and constant revisit time ensuring capture of ongoing changes. For high-resolution data, Hubert-Moy et al [10] applied SPOT-7 data to mapping marsh communities, achieving F1-scores of 0.77-0.99, followed by WorldView-2, while Greaves et al [11] based on airborne lidar, 20 cm RGBN imagery and Random Forest achieved 86% overall accuracy for tundra vegetation, and Meng et al [12], using Gaofen-1 satellite for alpine grassland communities, obtained producer accuracy between 67 and 96%. However, with the reduced number of spectral bands of high-resolution satellites, it is limited to identify plant communities with unique spectral characteristics [13].…”

Section: Introductionmentioning

confidence: 99%

Combining Multitemporal Optical and Radar Satellite Data for Mapping the Tatra Mountains Non-Forest Plant Communities

Kluczek,

Zagajewski,

Kycko

2024

Remote Sensing

View full text Add to dashboard Cite

Climate change is significantly affecting mountain plant communities, causing dynamic alterations in species composition as well as spatial distribution. This raises the need for constant monitoring. The Tatra Mountains are the highest range of the Carpathians which are considered biodiversity hotspots in Central Europe. For this purpose, microwave Sentinel-1 and optical multi-temporal Sentinel-2 data, topographic derivatives, and iterative machine learning methods incorporating classifiers random forest (RF), support vector machines (SVMs), and XGBoost (XGB) were used for the identification of thirteen non-forest plant communities (various types of alpine grasslands, shrublands, herbaceous heaths, mountain hay meadows, rocks, and scree communities). Different scenarios were tested to identify the most important variables, retrieval periods, and spectral bands. The overall accuracy results for the individual algorithms reached RF (0.83–0.96), SVM (0.87–0.93), and lower results for XGBoost (0.69–0.82). The best combination, which included a fusion of Sentinel-1, Sentinel-2, and topographic data, achieved F1-scores for classes in the range of 0.73–0.97 (RF) and 0.66–0.95 (SVM). The inclusion of topographic variables resulted in an improvement in F1-scores for Sentinel-2 data by one–four percent points and Sentinel-1 data by 1%–9%. For spectral bands, the Sentinel-2 10 m resolution bands B4, B3, and B2 showed the highest mean decrease accuracy. The final result is the first comprehensive map of non-forest vegetation for the Tatra Mountains area.

show abstract

Contribution of SPOT-7 multi-temporal imagery for mapping wetland vegetation

Cited by 7 publications

References 48 publications

The utility of airborne hyperspectral and satellite multispectral images in identifying Natura 2000 non-forest habitats for conservation purposes

The utility of airborne hyperspectral and satellite multispectral images in identifying Natura 2000 non-forest habitats for conservation purposes

Evaluation and Selection of Multi-Spectral Indices to Classify Vegetation Using Multivariate Functional Principal Component Analysis

Combining Multitemporal Optical and Radar Satellite Data for Mapping the Tatra Mountains Non-Forest Plant Communities

Contact Info

Product

Resources

About