Grassland habitat mapping by intra-annual time series analysis – Comparison of RapidEye and TerraSAR-X satellite data

Schuster, Christian; Schmidt, Tobias; Conrad, Christopher; Kleinschmit, Birgit; Förster, Michael

doi:10.1016/j.jag.2014.06.004

Cited by 129 publications

(135 citation statements)

References 79 publications

Supporting

Mentioning

124

Contrasting

Unclassified

Order By: Relevance

“…On hyperspectral images, up to three classes of grassland vegetation and other, non-grassland classes were differentiated [56]. Object-oriented image analysis of multispectral aerial or satellite images [57][58][59], and classification of high temporal resolution satellite images have also been used for similar purposes [60]. Heathlands were successfully analyzed for conservation-related mapping by hyperspectral and multispectral images, and these studies also included grassland vegetation classes [50,58,61,62].…”

Section: Remote Sensing Of Grassland Vegetationmentioning

confidence: 99%

“…Heathlands were successfully analyzed for conservation-related mapping by hyperspectral and multispectral images, and these studies also included grassland vegetation classes [50,58,61,62]. Using multi-temporal RapidEye and separately TerraSAR-X data, Schuster et al [60] and Neumann [49] mapped grassland, reaching very high accuracies (Kappa > 0.8), and Franke et al [40] successfully categorized grassland use intensity (four classes, overall accuracy > 80%). While these results are certainly ground breaking in their own field and cover a certain aspect of monitoring (detecting mowing regime for the radar-based studies, species composition principle components for the hyperspectral study), they are less compatible with the vegetation classification schemes normally used in conservation mapping, and their spatial resolution is also limited to several meters.…”

Section: Remote Sensing Of Grassland Vegetationmentioning

confidence: 99%

See 1 more Smart Citation

Categorizing Grassland Vegetation with Full-Waveform Airborne Laser Scanning: A Feasibility Study for Detecting Natura 2000 Habitat Types

Zlinszky

Schroiff²,

Kania³

et al. 2014

Remote Sensing

View full text Add to dashboard Cite

There is increasing demand for reliable, high-resolution vegetation maps covering large areas. Airborne laser scanning data is available for large areas with high resolution and supports automatic processing, therefore, it is well suited for habitat mapping. Lowland hay meadows are widespread habitat types in European grasslands, and also have one of the highest species richness. The objective of this study was to test the applicability of airborne laser scanning for vegetation mapping of different grasslands, including the Natura 2000 habitat type lowland hay meadows. Full waveform leaf-on and leaf-off point clouds were collected from a Natura 2000 site in Sopron, Hungary, covering OPEN ACCESS Remote Sens. 2014, 6 8057 several grasslands. The LIDAR data were processed to a set of rasters representing point attributes including reflectance, echo width, vegetation height, canopy openness, and surface roughness measures, and these were fused to a multi-band pseudo-image. Random forest machine learning was used for classifying this dataset. Habitat type, dominant plant species and other features of interest were noted in a set of 140 field plots. Two sets of categories were used: five classes focusing on meadow identification and the location of lowland hay meadows, and 10 classes, including eight different grassland vegetation categories. For five classes, an overall accuracy of 75% was reached, for 10 classes, this was 68%. The method delivers unprecedented fine resolution vegetation maps for management and ecological research. We conclude that high-resolution full-waveform LIDAR data can be used to detect grassland vegetation classes relevant for Natura 2000.

show abstract

Section: Remote Sensing Of Grassland Vegetationmentioning

confidence: 99%

Section: Remote Sensing Of Grassland Vegetationmentioning

confidence: 99%

Categorizing Grassland Vegetation with Full-Waveform Airborne Laser Scanning: A Feasibility Study for Detecting Natura 2000 Habitat Types

Zlinszky

Schroiff²,

Kania³

et al. 2014

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Some works report results with few images per year, such as Dusseux et al [51], but they worked on LAI. In their study for mapping grassland habitat using intra-annual RapidEye imagery, Schuster et al [52] concluded the more acquisition dates used, the better the mapping quality.…”

Section: Introductionmentioning

confidence: 99%

“…Given the heterogeneity of grasslands in fragmented landscapes, their phenological cycle and the punctuality of the anthropogenic events (e.g., mowing), dense high spatial resolution intra-annual time series are necessary to identify the grassland management types [36,[52][53][54]. Moreover, to discriminate semi-natural grasslands from temporary grasslands, inter-annual time series are necessary.…”

Section: Introductionmentioning

confidence: 99%

“…Conversely, high spatial resolution missions did not provide dense time series and/or were costly (i.e., QuickBird, RapidEye). For these reasons and compared to crops, grasslands' differentiation through Earth observations is still considered as a challenge [52]. However, new missions like Sentinel-2 [55], with a very high revisit frequency (five days) and high spatial resolution (10 m in four spectral channels, 20 m in six channels), provide new opportunities for grasslands' monitoring over the years in fragmented landscapes [54] at no cost, thanks to the ESA free data access policy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2017

View full text Add to dashboard Cite

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 level 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 α-Gaussian mean kernel. It allows one to weight the influence of the covariance matrix when comparing two Gaussian distributions. This kernel is introduced in support vector machines for the supervised classification of grasslands from southwest France. A dense intra-annual multispectral time series of the 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 old and young grasslands' discrimination. Results are compared to other existing pixel-and object-based approaches in terms of classification accuracy and processing time. The proposed method is shown 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.

show abstract

Crop mapping and quantitative evaluation of cultivated land use intensity in Shandong Province, 2018–2022

Zhao,

Sun,

Wang

et al. 2024

Land Degrad Dev

View full text Add to dashboard Cite

Industrialization and urbanization have intensified land‐use pressures on agroecosystems. Monitoring cultivated land use intensity (CLUI) is crucial for implementing sustainable agriculture. However, current agroecosystem management in Shandong Province lacks high‐resolution CLUI information. To address this gap, this study measured and analyzed CLUI at a 1‐km scale in Shandong Province from 2018 to 2022, using self‐produced crop maps and the human appropriation of net primary production (HANPP) framework. The spatial autocorrelation model was used to analyze the spatiotemporal pattern and aggregation characteristics of cultivated land use intensity. The influencing factors of CLUI were analyzed using the propensity score matching method, which helps reduce the interference of confounding factors. The results are as follows: (1) The wheat‐maize planting pattern in Shandong Province has remained relatively stable, with a notable trend toward intensified cultivation in the western region. (2) CLUI exhibited notable spatial and temporal heterogeneity, with low and medium values predominantly located in the western region. CLUI increased from 1.13 to 1.24, exceeding the global average of 0.84. (3) CLUI showed significant spatial aggregation characteristics. In 2018, 2020, and 2022, the western region was mainly characterized by high‐high and high‐low types. In 2019 and 2021, it was mainly characterized by the low‐low type, with less prevalence of low‐high type. The center of gravity of high‐high and low‐high types shifted southwest, whereas that of high‐low and low‐low types shifted northeast. (4) Chemical fertilizers, pesticides, and plastic mulch exhibited significant positive correlations with CLUI, whereas temperature and precipitation showed significant negative correlations. Favorable natural conditions can mitigate human interference, leading to lower CLUI.

show abstract

Grassland habitat mapping by intra-annual time series analysis – Comparison of RapidEye and TerraSAR-X satellite data

Cited by 129 publications

References 79 publications

Categorizing Grassland Vegetation with Full-Waveform Airborne Laser Scanning: A Feasibility Study for Detecting Natura 2000 Habitat Types

Categorizing Grassland Vegetation with Full-Waveform Airborne Laser Scanning: A Feasibility Study for Detecting Natura 2000 Habitat Types

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

Crop mapping and quantitative evaluation of cultivated land use intensity in Shandong Province, 2018–2022

Contact Info

Product

Resources

About