E-Mail Alert

Add your e-mail address to receive forthcoming issues of this journal:

Journal Browser

Journal Browser

Special Issue "Remote Sensing and GIS for Habitat Quality Monitoring"

Quicklinks

A special issue of Remote Sensing (ISSN 2072-4292).

Deadline for manuscript submissions: closed (28 February 2015)

Special Issue Editors

Guest Editor
Prof. Dr. Norbert Pfeifer (Website)

Department of Geodesy and Geoinformation, Vienna University of Technology, Vienna, Austria
Chair EuroSDR Commission 2 “Image Analysis and Information Extraction”
Fax: +43 58801 122 99
Interests: Earth observation with photogrammetry and laser scanning; information extraction from images; topographic and environmental modelling
Guest Editor
Dr. András Zlinszky (Website)

Balaton Limnological Institute, Centre for Ecological Research, Hungarian Academy of Sciences, Klebelsberg Kuno út 3, 8237 Tihany, Hungary / Department of Geodesy and Geoinformation , Vienna University of Technology, E120, Gußhausstraße 27-29, 1040 Vienna, Austria
Fax: +43 58801 122 99
Interests: airborne laser scanning of vegetation for ecology and conservation; airborne imaging of wetland vegetation dynamics; processing of historic maps and aerial images for vegetation ecology and hydrology; neotectonics of the Lake Balaton region
Guest Editor
Prof. Dr. Hermann Heilmeier (Website)

Biology/Ecology Unit, Institute of Biosciences, TU Bergakademie Freiberg, Leipziger Str. 29, D-09599 Freiberg, Germany
Phone: +49 3731 39 32 08
Fax: +49 3731 39 30 12
Interests: conservation ecology, Remediation, Habitat modeling, Natura 2000 monitoring
Guest Editor
Prof. Dr. Heiko Balzter (Website)

Holder of the Royal Society Wolfson Research Merit Award, Centre for Landscape and Climate Research, Department of Geography, University of Leicester, Bennett Building, University Road, Leicester LE1 7RH, UK
Fax: +44 116 252 3854
Interests: land cover / land use change; spatial-temporal scaling; land/atmosphere interactions; data assimilation; synthetic aperture radar (SAR); SAR interferometry; SAR polarimetry; ground-based, airborne and spaceborne light detection and ranging (LIDAR); digital elevation models; carbon accounting; forest structure and biomass mapping; vegetation phenology; fire and burned area mapping
Guest Editor
Jun.-Prof. Dr. Bernhard Höfle (Website)

Chair of GIScience, Institute of Geography, Interdisciplinary Center for Scientific Computing, Heidelberg Center for the Environment, Heidelberg University, Berliner Straße 48, D-69120 Heidelberg, Germany
Fax: +49 6221 54 4529
Interests: geoprocessing algorithms for Geographic Information Systems (GIS); object-based image and 3D point cloud analysis; multi-source geoinformation fusion; 3D spatial data and analysis infrastructures; LiDAR applications in geosciences
Guest Editor
Dr. Bálint Czúcz (Website)

Institute of Ecology and Botany, Centre for Ecological Research, Hungarian Academy of Sciences, Alkotmány u. 2-4, 2163, Vácrátót, Hungary
Fax: +36 28 360 110
Interests: climate change, ecosystem services, predictive ecological modeling, ecological indicators, landscape ecology

Special Issue Information

Dear Colleagues,

This Special Issue, “Remote Sensing and GIS for Habitat Quality Monitoring”, aims to pave the way for operational habitat quality monitoring from earth observation data for more effective habitat conservation. The demand for protecting biodiversity has been underlined by a number of recent international agreements, while the increasing size of protected habitats calls for an urgent improvement in the efficiency of monitoring.

Meanwhile, GIS-based quantitative habitat quality mapping has arrived. Processes leading to this include the increase in coverage provided by high-resolution airborne and spaceborne data, the availability of high-level classification algorithms in commercial processing software, and an active dialogue between remote sensing and conservation ecology specialists. Nevertheless, several open questions remain. How can ecological principles best be represented in geoinformation algorithms? How can habitat quality or conservation status be quantified? Can we integrate or compare data from different sensors? Is conservation legislation and practice ready for the stream of newly available data? How can field reference data collection and sensor campaigns be optimized for efficiency?

Previous reviews and special issues on ecological remote sensing typically focused on mapping either the extent of habitats or a single ecological variable. This Special Issue will present the next level of processing, where sensor and field data from several parameters, including the pattern and extent of habitats, structure, connectivity, species composition, and ecophysiological condition are processed and evaluated together, so as to deliver a quantitative representation of habitat quality.

Experimental reports, case studies, reviews, and future trend assessments are welcome (assuming they are relevant to habitat quality mapping and monitoring).

Selected topics of interest:

  • Operational examples of GIS and/or Remote Sensing-supported habitat quality monitoring
  • Case studies of GIS and RS in the monitoring of various habitat types
  • New sensors, algorithms, and applications in habitat quality mapping
  • GIS-and RS facilitated field ecological mapping
  • Data sources, data infrastructures for habitat quality monitoring (web maps, crowdsourcing, citizen science, sensor networks)
  • Requirements of practical conservation towards spatial data in habitat quality

Prof. Dr. Norbert Pfeifer
Dr. András Zlinszky
Prof. Dr. Hermann Heilmeier
Prof. Dr. Heiko Balzter
Jun.-Prof. Dr. Bernhard Höfle
Dr. Bálint Czúcz
Guest Editors

Submission

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. Papers will be published continuously (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are refereed through a peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed Open Access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs).

Keywords

  • habitat quality
  • natura 2000
  • species conservation
  • biodiversity
  • lidar
  • hyperspectral imaging
  • hypertemporal imaging
  • sensor fusion
  • conservation gis
  • aerial and satellite imaging

Published Papers (11 papers)

View options order results:
result details:
Displaying articles 1-11
Export citation of selected articles as:

Editorial

Jump to: Research

Open AccessEditorial Remote Sensing and GIS for Habitat Quality Monitoring: New Approaches and Future Research
Remote Sens. 2015, 7(6), 7987-7994; doi:10.3390/rs70607987
Received: 12 June 2015 / Accepted: 15 June 2015 / Published: 17 June 2015
Cited by 2 | PDF Full-text (649 KB) | HTML Full-text | XML Full-text
Abstract
Habitat quality is the ability of the environment to provide conditions appropriate for individual and species persistence. Measuring or monitoring habitat quality requires complex integration of many properties of the ecosystem, where traditional terrestrial data collection methods have proven extremely time-demanding. Remote [...] Read more.
Habitat quality is the ability of the environment to provide conditions appropriate for individual and species persistence. Measuring or monitoring habitat quality requires complex integration of many properties of the ecosystem, where traditional terrestrial data collection methods have proven extremely time-demanding. Remote sensing has known potential to map various ecosystem properties, also allowing rigorous checking of accuracy and supporting standardized processing. Our Special Issue presents examples where remote sensing has been successfully used for habitat mapping, quantification of habitat quality parameters, or multi-parameter modelling of habitat quality itself. New frontiers such as bathymetric scanning, grassland vegetation classification and operational use were explored, various new ecological verification methods were introduced and integration with ongoing habitat conservation schemes was demonstrated. These studies show that remote sensing and Geoinformation Science for habitat quality analysis have evolved from isolated experimental studies to an active field of research with a dedicated community. It is expected that these new methods will substantially contribute to biodiversity conservation worldwide. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)

Research

Jump to: Editorial

Open AccessArticle Topo-Bathymetric LiDAR for Monitoring River Morphodynamics and Instream Habitats—A Case Study at the Pielach River
Remote Sens. 2015, 7(5), 6160-6195; doi:10.3390/rs70506160
Received: 15 January 2015 / Accepted: 5 May 2015 / Published: 19 May 2015
Cited by 3 | PDF Full-text (36137 KB) | HTML Full-text | XML Full-text
Abstract
Airborne LiDAR Bathymetry (ALB) has been rapidly evolving in recent years and now allows fluvial topography to be mapped in high resolution (>20 points/m2) and height accuracy (<10 cm) for both the aquatic and the riparian area. This article presents [...] Read more.
Airborne LiDAR Bathymetry (ALB) has been rapidly evolving in recent years and now allows fluvial topography to be mapped in high resolution (>20 points/m2) and height accuracy (<10 cm) for both the aquatic and the riparian area. This article presents methods for enhanced modeling and monitoring of instream meso- and microhabitats based on multitemporal data acquisition. This is demonstrated for a near natural reach of the Pielach River, with data acquired from April 2013 to October 2014, covering two flood events. In comparison with topographic laser scanning, ALB requires a number of specific processing steps. We present, firstly, a novel approach for modeling the water surface in the case of sparse water surface echoes and, secondly, a strategy for improved filtering and modeling of the Digital Terrain Model of the Watercourse (DTM-W). Based on the multitemporal DTM-W we discuss the massive changes of the fluvial topography exhibiting deposition/erosion of 103 m3 caused by the 30-years flood event in May 2014. Furthermore, for the first time, such a high-resolution data source is used for monitoring of hydro-morphological units (mesohabitat scale) including the consequences for the target fish species nase (Chondrostoma nasus, microhabitat scale). The flood events caused a spatial displacement of the hydro-morphological units but did not effect their overall frequency distribution, which is considered an important habitat feature as it documents resilience against disturbances. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Open AccessArticle Towards Detection of Cutting in Hay Meadows by Using of NDVI and EVI Time Series
Remote Sens. 2015, 7(5), 6107-6132; doi:10.3390/rs70506107
Received: 26 February 2015 / Revised: 28 April 2015 / Accepted: 7 May 2015 / Published: 15 May 2015
Cited by 1 | PDF Full-text (7983 KB) | HTML Full-text | XML Full-text
Abstract
The main requirement for preserving European hay meadows in good condition is through prerequisite cut management. However, monitoring these practices on a larger scale is very difficult. Our study analyses the use of MODIS vegetation indices products, namely EVI and NDVI, to [...] Read more.
The main requirement for preserving European hay meadows in good condition is through prerequisite cut management. However, monitoring these practices on a larger scale is very difficult. Our study analyses the use of MODIS vegetation indices products, namely EVI and NDVI, to discriminate cut and uncut meadows in Slovakia. We tested the added value of simple transformations of raw data series (seasonal statistics, first difference series), compared EVI and NDVI, and analyzed optimal periods, the number of scenes and the effect of smoothing on classification performance. The first difference series transformation saw substantial improvement in classification results. The best case NDVI series classification yielded overall accuracy of 85% with balanced rates of producer’s and user’s accuracies for both classes. EVI yielded slightly lower values, though not significantly different, although user accuracy of cut meadows achieved only 67%. Optimal periods for discriminating cut and uncut meadows lay between 16 May and 4 August, meaning only seven consecutive images are enough to accurately detect cutting in hay meadows. More importantly, the 16-day compositing period seemed to be enough for detection of cutting, which would be the time span that might be hopefully achieved by upcoming on-board HR sensors (e.g., Sentinel-2). Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Open AccessArticle Monitoring the Distribution and Dynamics of an Invasive Grass in Tropical Savanna Using Airborne LiDAR
Remote Sens. 2015, 7(5), 5117-5132; doi:10.3390/rs70505117
Received: 5 February 2015 / Revised: 10 April 2015 / Accepted: 20 April 2015 / Published: 24 April 2015
Cited by 2 | PDF Full-text (4575 KB) | HTML Full-text | XML Full-text
Abstract
The spread of an alien invasive grass (gamba grass—Andropogon gayanus) in the tropical savannas of Northern Australia is a major threat to habitat quality and biodiversity in the region, primarily through its influence on fire intensity. Effective control and eradication [...] Read more.
The spread of an alien invasive grass (gamba grass—Andropogon gayanus) in the tropical savannas of Northern Australia is a major threat to habitat quality and biodiversity in the region, primarily through its influence on fire intensity. Effective control and eradication of this invader requires better insight into its spatial distribution and rate of spread to inform management actions. We used full-waveform airborne LiDAR to map areas of known A. gayanus invasion in the Batchelor region of the Northern Territory, Australia. Our stratified sampling campaign included wooded savanna areas with differing degrees of A. gayanus invasion and adjacent areas of native grass and woody tree mixtures. We used height and spatial contiguity based metrics to classify returns from A. gayanus and developed spatial representations of A. gayanus occurrence (1 m resolution) and canopy cover (10 m resolution). The cover classification proved robust against two independent field-based investigations at 500 m2 (R2 = 0.87, RMSE = 12.53) and 100 m2 (R2 = 0.79, RMSE = 14.13) scale. Our mapping results provide a solid benchmark for evaluating the rate and pattern of A. gayanus spread from future LiDAR campaigns. In addition, this high-resolution mapping can be used to inform satellite image analysis for the evaluation of A. gayanus invasion over broader regional scales. Our research highlights the huge potential that airborne LiDAR holds for facilitating the monitoring and management of savanna habitat condition. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Open AccessArticle Can Airborne Laser Scanning (ALS) and Forest Estimates Derived from Satellite Images Be Used to Predict Abundance and Species Richness of Birds and Beetles in Boreal Forest?
Remote Sens. 2015, 7(4), 4233-4252; doi:10.3390/rs70404233
Received: 10 December 2014 / Revised: 22 March 2015 / Accepted: 1 April 2015 / Published: 9 April 2015
Cited by 4 | PDF Full-text (999 KB) | HTML Full-text | XML Full-text | Supplementary Files
Abstract
In managed landscapes, conservation planning requires effective methods to identify high-biodiversity areas. The objective of this study was to evaluate the potential of airborne laser scanning (ALS) and forest estimates derived from satellite images extracted at two spatial scales for predicting the [...] Read more.
In managed landscapes, conservation planning requires effective methods to identify high-biodiversity areas. The objective of this study was to evaluate the potential of airborne laser scanning (ALS) and forest estimates derived from satellite images extracted at two spatial scales for predicting the stand-scale abundance and species richness of birds and beetles in a managed boreal forest landscape. Multiple regression models based on forest data from a 50-m radius (i.e., corresponding to a homogenous forest stand) had better explanatory power than those based on a 200-m radius (i.e., including also parts of adjacent stands). Bird abundance and species richness were best explained by the ALS variables “maximum vegetation height” and “vegetation cover between 0.5 and 3 m” (both positive). Flying beetle abundance and species richness, as well as epigaeic (i.e., ground-living) beetle richness were best explained by a model including the ALS variable “maximum vegetation height” (positive) and the satellite-derived variable “proportion of pine” (negative). Epigaeic beetle abundance was best explained by “maximum vegetation height” at 50 m (positive) and “stem volume” at 200 m (positive). Our results show that forest estimates derived from satellite images and ALS data provide complementary information for explaining forest biodiversity patterns. We conclude that these types of remote sensing data may provide an efficient tool for conservation planning in managed boreal landscapes. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Open AccessArticle Using Optical Satellite Data and Airborne Lidar Data for a Nationwide Sampling Survey
Remote Sens. 2015, 7(4), 4253-4267; doi:10.3390/rs70404253
Received: 1 January 2015 / Revised: 22 March 2015 / Accepted: 1 April 2015 / Published: 9 April 2015
Cited by 2 | PDF Full-text (26900 KB) | HTML Full-text | XML Full-text
Abstract
A workflow for combining airborne lidar, optical satellite data and National Forest Inventory (NFI) plots for cost efficient operational mapping of a nationwide sample of 5 × 5 km squares in the National Inventory of Landscapes in Sweden (NILS) landscape inventory in Sweden [...] Read more.
A workflow for combining airborne lidar, optical satellite data and National Forest Inventory (NFI) plots for cost efficient operational mapping of a nationwide sample of 5 × 5 km squares in the National Inventory of Landscapes in Sweden (NILS) landscape inventory in Sweden is presented. Since the areas where both satellite data and lidar data have a common data quality are limited, and impose a constraint on the number of available NFI plots, it is not feasible to perform classifications in a single step. Instead a stratified approach where canopy cover and canopy height are first predicted from lidar data trained with NFI plots is proposed. From the lidar predictions a forest stratum is defined as grid cells with more than 3 m mean tree height and more than 10% vertical canopy cover, the remaining grid cells are defined as open land. Both forest and open land are then classified into broad vegetation classes using optical satellite data. The classification of open land is trained with aerial photo interpretation and the classification of the forest stratum is trained with a new set of NFI plots. The result is a rational procedure for nationwide sample based vegetation characterization. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Open AccessArticle Airborne Lidar for Woodland Habitat Quality Monitoring: Exploring the Significance of Lidar Data Characteristics when Modelling Organism-Habitat Relationships
Remote Sens. 2015, 7(4), 3446-3466; doi:10.3390/rs70403446
Received: 19 November 2014 / Accepted: 18 March 2015 / Published: 24 March 2015
Cited by 4 | PDF Full-text (3719 KB) | HTML Full-text | XML Full-text | Supplementary Files
Abstract
Structure is a fundamental physical element of habitat, particularly in woodlands, and hence there has been considerable recent uptake of airborne lidar data in forest ecology studies. This paper investigates the significance of lidar data characteristics when modelling organism-habitat relationships, taking a [...] Read more.
Structure is a fundamental physical element of habitat, particularly in woodlands, and hence there has been considerable recent uptake of airborne lidar data in forest ecology studies. This paper investigates the significance of lidar data characteristics when modelling organism-habitat relationships, taking a single species case study in a mature woodland ecosystem. We re-investigate work on great tit (Parus major) habitat, focussing on bird breeding data from 1997 and 2001 (years with contrasting weather conditions and a demonstrated relationship between breeding success and forest structure). We use a time series of three lidar data acquisitions across a 12-year period (2000–2012). The lidar data characteristics assessed include time-lag with field data (up to 15 years), spatial sampling density (average post spacing in the range of 1 pulse per 0.14 m2–17.77 m2), approach to processing (raster or point cloud), and the complexity of derived structure metrics (with a total of 33 metrics assessed, each generated separately using all returns and only first returns). Ordinary least squares regression analysis was employed to investigate relationships between great tit mean nestling body mass, calculated per brood, and the various canopy structure measures from all lidar datasets. For the 2001 bird breeding data, the relationship between mean nestling body mass and mean canopy height for a sample area around each nest was robust to the extent that it could be detected strongly and with a high level of statistical significance, with relatively little impact of lidar data characteristics. In 1997, all relationships between lidar structure metrics and mean nestling body mass were weaker than in 2001 and more sensitive to lidar data characteristics, and in almost all cases they were opposite in trend. However, whilst the optimum habitat structure differed between the two study years, the lidar-derived metrics that best characterised this structure were consistent: canopy height percentiles and mean overstorey canopy height (calculated using all returns or only first returns) and the standard deviation of canopy height (calculated using all returns). Overall, our results suggest that for relatively stable woodland habitats, ecologists should not feel prohibited in using lidar data to explore or monitor organism–habitat relationships because of perceived data quality issues, as long as the questions investigated, the scale of analysis, and the interpretation of findings are appropriate for the data available. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Open AccessArticle Mapping Natura 2000 Habitat Conservation Status in a Pannonic Salt Steppe with Airborne Laser Scanning
Remote Sens. 2015, 7(3), 2991-3019; doi:10.3390/rs70302991
Received: 5 December 2014 / Revised: 4 March 2015 / Accepted: 9 March 2015 / Published: 13 March 2015
Cited by 4 | PDF Full-text (5293 KB) | HTML Full-text | XML Full-text | Supplementary Files
Abstract
Natura 2000 Habitat Conservation Status is currently evaluated based on fieldwork. However, this is proving to be unfeasible over large areas. The use of remote sensing is increasingly encouraged but covering the full range of ecological variables by such datasets and ensuring [...] Read more.
Natura 2000 Habitat Conservation Status is currently evaluated based on fieldwork. However, this is proving to be unfeasible over large areas. The use of remote sensing is increasingly encouraged but covering the full range of ecological variables by such datasets and ensuring compatibility with the traditional assessment methodology has not been achieved yet. We aimed to test Airborne Laser Scanning (ALS) as a source for mapping all variables required by the local official conservation status assessment scheme and to develop an automated method that calculates Natura 2000 conservation status at 0.5 m raster resolution for 24 km2 of Pannonic Salt Steppe habitat (code 1530). We used multi-temporal (summer and winter) ALS point clouds with full-waveform recording and a density of 10 pt/m2. Some required variables were derived from ALS product rasters; others involved vegetation classification layers calculated by machine learning and fuzzy categorization. Thresholds separating favorable and unfavorable values of each variable required by the national assessment scheme were manually calibrated from 10 plots where field-based assessment was carried out. Rasters representing positive and negative scores for each input variable were integrated in a ruleset that exactly follows the Hungarian Natura 2000 assessment scheme for grasslands. Accuracy of each parameter and the final conservation status score and category was evaluated by 10 independent assessment plots. We conclude that ALS is a suitable data source for Natura 2000 assessments in grasslands, and that the national grassland assessment scheme can successfully be used as a GIS processing model for conservation status, ensuring that the output is directly comparable with traditional field based assessments. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Open AccessArticle Gradient-Based Assessment of Habitat Quality for Spectral Ecosystem Monitoring
Remote Sens. 2015, 7(3), 2871-2898; doi:10.3390/rs70302871
Received: 30 November 2014 / Revised: 2 March 2015 / Accepted: 4 March 2015 / Published: 10 March 2015
Cited by 4 | PDF Full-text (11842 KB) | HTML Full-text | XML Full-text | Supplementary Files
Abstract
The monitoring of ecosystems alterations has become a crucial task in order to develop valuable habitats for rare and threatened species. The information extracted from hyperspectral remote sensing data enables the generation of highly spatially resolved analyses of such species’ habitats. In [...] Read more.
The monitoring of ecosystems alterations has become a crucial task in order to develop valuable habitats for rare and threatened species. The information extracted from hyperspectral remote sensing data enables the generation of highly spatially resolved analyses of such species’ habitats. In our study we combine information from a species ordination with hyperspectral reflectance signatures to predict occurrence probabilities for Natura 2000 habitat types and their conservation status. We examine how accurate habitat types and habitat threat, expressed by pressure indicators, can be described in an ordination space using spatial correlation functions from the geostatistic approach. We modeled habitat quality assessment parameters using floristic gradients derived by non-metric multidimensional scaling on the basis of 58 field plots. In the resulting ordination space, the variance structure of habitat types and pressure indicators could be explained by 69% up to 95% with fitted variogram models with a correlation to terrestrial mapping of >0.8. Models could be used to predict habitat type probability, habitat transition, and pressure indicators continuously over the whole ordination space. Finally, partial least squares regression (PLSR) was used to relate spectral information from AISA DUAL imagery to floristic pattern and related habitat quality. In general, spectral transferability is supported by strong correlation to ordination axes scores (R2 = 0.79–0.85), whereas second axis of dry heaths (R2 = 0.13) and first axis for pioneer grasslands (R2 = 0.49) are more difficult to describe. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Open AccessArticle Classification of Herbaceous Vegetation Using Airborne Hyperspectral Imagery
Remote Sens. 2015, 7(2), 2046-2066; doi:10.3390/rs70202046
Received: 13 October 2014 / Revised: 9 January 2015 / Accepted: 21 January 2015 / Published: 12 February 2015
Cited by 5 | PDF Full-text (3180 KB) | HTML Full-text | XML Full-text
Abstract
Alkali landscapes hold an extremely fine-scale mosaic of several vegetation types, thus it seems challenging to separate these classes by remote sensing. Our aim was to test the applicability of different image classification methods of hyperspectral data in this complex situation. To [...] Read more.
Alkali landscapes hold an extremely fine-scale mosaic of several vegetation types, thus it seems challenging to separate these classes by remote sensing. Our aim was to test the applicability of different image classification methods of hyperspectral data in this complex situation. To reach the highest classification accuracy, we tested traditional image classifiers (maximum likelihood classifier—MLC), machine learning algorithms (support vector machine—SVM, random forest—RF) and feature extraction (minimum noise fraction (MNF)-transformation) on training datasets of different sizes. Digital images were acquired from an AISA EAGLE II hyperspectral sensor of 128 contiguous bands (400–1000 nm), a spectral sampling of 5 nm bandwidth and a ground pixel size of 1 m. For the classification, we established twenty vegetation classes based on the dominant species, canopy height, and total vegetation cover. Image classification was applied to the original and MNF (minimum noise fraction) transformed dataset with various training sample sizes between 10 and 30 pixels. In order to select the optimal number of the transformed features, we applied SVM, RF and MLC classification to 2–15 MNF transformed bands. In the case of the original bands, SVM and RF classifiers provided high accuracy irrespective of the number of the training pixels. We found that SVM and RF produced the best accuracy when using the first nine MNF transformed bands; involving further features did not increase classification accuracy. SVM and RF provided high accuracies with the transformed bands, especially in the case of the aggregated groups. Even MLC provided high accuracy with 30 training pixels (80.78%), but the use of a smaller training dataset (10 training pixels) significantly reduced the accuracy of classification (52.56%). Our results suggest that in alkali landscapes, the application of SVM is a feasible solution, as it provided the highest accuracies compared to RF and MLC. SVM was not sensitive in the training sample size, which makes it an adequate tool when only a limited number of training pixels are available for some classes. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Open AccessArticle Categorizing Grassland Vegetation with Full-Waveform Airborne Laser Scanning: A Feasibility Study for Detecting Natura 2000 Habitat Types
Remote Sens. 2014, 6(9), 8056-8087; doi:10.3390/rs6098056
Received: 20 June 2014 / Revised: 19 August 2014 / Accepted: 19 August 2014 / Published: 27 August 2014
Cited by 12 | PDF Full-text (26835 KB) | HTML Full-text | XML Full-text | Supplementary Files
Abstract
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 [...] Read more.
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 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. Full article
(This article belongs to the Special Issue Remote Sensing and GIS for Habitat Quality Monitoring)
Figures

Journal Contact

MDPI AG
Remote Sensing Editorial Office
St. Alban-Anlage 66, 4052 Basel, Switzerland
remotesensing@mdpi.com
Tel. +41 61 683 77 34
Fax: +41 61 302 89 18
Editorial Board
Contact Details Submit to Remote Sensing
Back to Top