ID: 55282
Title: Retrieval of boreal forest LAI using a forest reflectance model and empirical regressions
Author: Janne Heiskanen, Miina Rautiainen, Lauri Korhonen, Matti Mottus, Pauline Stenberg
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 4, August 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Leaf area index, Spectral invariants, PARAS, Vegetation index, Neural networks, kNN
Abstract: Spectral invariants provide a novel approach for characterizing canopy structure in forest reflectance models and for mapping biophysicla variables using satellite images. We applied a photon recollision probability (p) based forest reflectance model (PARAS) to retrieve leaf area index (LAI) from fine resolution SPOT HRVIR and Landsat ETM + satellite data. First , PARAS was parameterized using an extensive database of LAI-2000 measurements from five conifer-dominated boreal forest sites in Finland, and mixtures of field-measured forest understory spectra. The selected vegetation indices (e.g. reduced simple ratio, RSR), neural networks and kNN method were used to retrieve effective LAI (Le) based on reflectance model simulations. For comparison, we established empirical vegetation index-LAI regression models for our study sites. The empirical RSR-Le regression performed best when applied to an independent test site in southern Finland [RMSE 0.57 ( 24.2%)]. However, the difference to the best reflectance model based retrievals produced by neural networks was only marginal [RMSE 0.59 (25.1%)]. According to this study, the PARAS model provides a simple and flexible modelling tool for calibrating algorithms for LAI retrieval in conifer-dominated boreal forests. The advantage of PARAS is that it directly uses field mesurements to parameterize canopy structure (LAI-2000, hemispherical photographs) and optical properties of foliage and understory.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55281
Title: Quantitative urban climate mapping based on a geographical database: A simulation approach using Hong Kong as a case study
Author: Liang Chen, Edward Ng
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 4, August 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Urban climate mapping, Geographical information system, Urban simulation, Sky view factor, Frontal area density
Abstract: The urban environment has been dramatically changed by artificial constructions. How the modified urban geometry affects the urban climate and therefore human thermal comfort has become a primary concern for urban planners. The present study takes a simulation approach to analyze the influence of urban geometry on the urban climate and maps this climatic understanding from a quantitative perspective. A geographical building database is used to characterize two widely discussed aspects: urban heat island effect (UHI) and wind dynamics. The parameters of the sky view factor (SVF) and the frontal area density (FAD) are simulated using ArcGIS-embedded computer programs to link urban geometry with the UHI and wind dynamic conditions. The simulated results are synergized and classified to evaluate different urban cliamatic conditions based on thermal comfort consideration. A climatic map is then generated implementing the classification. The climatic map shows reasonable agreement with thermal comfort understanding, as indicated by the biometerological index of the physiological equivalent temperature (PET) obtained in an earlier study. The proposed climate mapping approach can provide both quantitative and visual evaluation of the urban environment for urban planners with climatic conerns. The map could be used as a decision support tool in planning and policy-making processes. An urban area in Hong Kong is used as a case study.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55280
Title: Detecting land-use/ land-cover change in rural-urban fringe areas using extended change-vector analysis
Author: Chunyang He, Anni Wei, Peijun shi Qiaofeng Zhang, Yuanyuan Zhao
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 4, August 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Change -vector analysism, Land -use/land-cover change, Rural-urban fringe area, texture information
Abstract: Detecting land-use/land-cover (LULC) changes in rural-urban fringe areas (RUFAs) timely and accurately using satellite imagery is essential for land-use planning and management in China. Although traditional spectral-based change-vector analysis (CVA) can effectively detect LULC change in many cases, it encounters difficulties in RUFAs because of deficiencies in the spectral information of satellite images. To detect LULC changes in RUFAs effectively, this paper proposes an extended CVA approach that incorporates textual change information into the traditional spectral-based CVA. The extended CVA was applied to three different pilot RUFAs in China with different remotely sensed data, including Landsat Thematic Mapper (TM), China-Brazil Earth Resources Satellite (CBERS) and Advanced Land Observing Satellite (ALOS) images. The results demonstrated the improvement of the extended CVA compared to teh traditional spectral-based CVA with the overall accuracy inceased between 4.66% and 8.00% and the kappa coefficient increased between 0.10 and 0.15, respectively. The advantage of the extended CVA lies in its integration of both spectal and textural change information to detect LULC changes, allowing for effective discrimination of LULC changes that are spectrally similar but textually different in RUFAs. The extended CVA has great potential to be widely used for LULC-change detection in RUFAs, which are often heterogeneous and fragmental in nature, with rich textural information.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55279
Title: Change in habitat selection by Japanese macaques (Macaca fuscata) and habitat fragmentation analysis using temporal remotely sensed data in Niigata Prefecture, Japan
Author: Shota Mochizuki, Takuhiko Murakami
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 4, August 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Habitat selection, Random Forest model, Object-oriented image classification, change detection, forest fragmentation, Japanese macaques
Abstract: The aim of this study was to evaluate changes in macaque habitat selection during a 29- year period. We focused on the 1970s, when little crop damage was caused by Japanese macaques (Macaca fuscata), and the 2000s, when the damage became remarkable. Landsat/MSS from 1978 and ALOS/AVNIR-2 from 2007 were employed for land-cover mapping. For the 2007 land-cover classification, we applied an object-oriented image classification and a classification and regression tree. The Kappa coefficient of the 2007 land-cover map was 0.89 . For the 1978 land-cover classification, change detection using principal component analysis and object-oriented image classification were applied to reduce resolution difference errors. The Kappa coefficient of the 1978 land-cover map was 0.84. We applied a Random Forest model for machine learning and data mining to predict the habitat selection of macaques. Several important environmental factors were identified for macaque habitat selection: the ratio of coniferous forest to farmland, distance to farmland, and maximum snow depth. The Random Forest model was extrapolated to the 1978 land-cover map. Over the 29-year period, coniferous forest changed to broad-leaved forest and/or mixed forest within the macaque habitat area. Coniferous forests were not selected as food resources by Japanese macaques. Furthermore, large-scale patches of farmland were used as food resources over the 29-year period. These changes indicated that habitat selection by Japanese macaques changed over the study period. The results show that the home range of macaques expanded, and macaques may now be distributed over a wider area as a result of changes in landscape configuration. Thus, forest planning, such as sustainable management of artificial conifer forests, is important for reducing crop damage.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55278
Title: Geothermal area detection using Landsat ETM + thermal infrared data and its mechanistic analysis - A case study in Tengchong, China
Author: Qiming Qin, Ning Zhang, Peng Nan, Leilei Chai
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 4, August 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: LST, Mechanism of geothermal anomaly, Landsat ETM+, Geothermal detection
Abstract: Thermal infrared (TIR) remote sensing is an important technique in the exploration of geothermal survey is conducted in Tengchong area of Yunnan province in China using TIR data from Landsat -7 Enhanced Thematic Mapper Plus (ETM+) sensor. Based on radiometric calibration, atmospheric correction and emissivity calculation, a simple but efficient single channel algorithm with acceptable precision is applied to retrieve the land surface temperature (LST) of study area. The LST anomalous areas with temperature about 4-10 K higher than background area are discovered. Four geothermal areas are identified with the discussion of geothermal mechanism and the further analysis of regional geologic structure. The research reveals that the distribution of geothermal areas is consistent with the fault development in study area. Magmatism contributes abundant thermal source to study area and the faults provide thermal channels for heat transfer from interior earth land surface and facilitate the present of geothermal anomalies. Finally, we conclude that TIR remote sensing is a cost-effective technique to detect LST anomalies. Combining TIR remote sensing with geological analysis and the understanding of geothermal mechanism is an accurate and efficient approach to geothermal area detection.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55277
Title: Glacier surface velocity estimation using SAR interferometry technique applying ascending and descending passes in Himalayas
Author: V Kumar, G Venkataramana, KA Hogda
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 4, August 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Himalaya, SAR, InSAR, Glacier, Velocity
Abstract: In this study ascending and descending passes interferometric synthetic aperture radar (InSAR) techniques are used for glacier surface velocity estimation in the Himalaya. Single-track interferometric measurements are sensitive to only a single component of the three dimensional (3-D) velocity vectors. European Remote Sensing satellites (ERS - 1/2) tandem mission data in ascending and descending tracks provide an opportunity to resolve the three velocity components under the assumption that glacier flow is parallel to its surface. Using the surface slope as an essential input in this technique the velocity pattern of Siachen glacier in Himalaya has been modelled. Glaciers in the Himalayan region maintain excellent coherence of SAR return signals in one-day temporal difference. As a result we could obtain spatially continuous surface velocity field with a precision of fraction of radar wavelength. The results covering the main course of glacier are analysed in terms of spatial and temporal variations. A maximum velocity of 43 cm/day has been observed in the upper middle protion of the glacier. This technique has been found accurate for monitoring the flow rates in this region, suggesting that routine monitoring of diurnal movement Himalayan glaciers would be immensely useful in the present day context of climate change.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55276
Title: Rapid response flood detectin using the MSG geostationery satellite
Author: Simon Richard Proud, Rasmus Fensholt, Laura Vang Rasmussen, Inge Sandholt
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 4, August 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: meteosat second generation, flooding, BRDF, Anisotropy, SEVIRI
Abstract: A novel technique for the detection of flooded land using satellite data is presented. This new method takes advantage of the high temporal resolution of the Spinning Enhanced Visible and InfraRed Imager (SEVIRI) aboard teh Meteosat Second Generation (MSG) series of satellites to derive several parameters that describe the sensitivity of land surface reflectivity to variation in solar position throughout the day. Examination of these parameters can then yield information describing the nature of the surface being viewed, including the presence of water due to flooding, on a 3-day basis. An analysis of data gathered during the 2009 flooding events in West Africa shows that the presented method can detect floods of comparable size to the SEVIRI pixel resolution on a short timescale, making it a valuable tool for large scale flood mapping.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55275
Title: High positive correlation between soil temperature and NDVI from 1982 to 2006 in alpine meadow of the Three-River source region on the Qinghai-Tibetan Plateau
Author: Weixin Xu, Song Gu, XinQuan Zhao, Jianshe Xiao, Yanhong Tang, Jingyun Fang, Juan Zhang, Sha Jiang
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 4, August 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: NDVI (Normalized Differential Vegetation Index), Qinghai-Tibetan Plateau, Temperature, vegetation
Abstract: Using satellite-observed Normalized Difference Vegetation Index (NDVI) data adn Rotated Empirical Orthogonal Function (REOF) method, we analyzed the spatio-temporal variation of vegetation during growing seasons from May to September in the Three-River Source Region, alpine meadow in the Qinghai- Tibetan Plateau from 1982 to 2006. We found that NDVI in the centre and east of the centre and east of the region, where the vegetation cover is low, showed a consistent but slight increase before 2003 and remarkable increase in 2004 and 2005. Impact factors analysis indicate that among air temperature, precipitation, humid index, soil surface temperature, and soil temperature at 10 cm and 20 cm depth, annual variation of NDVI was highly positive correlation with the soil surface temperature of the period from March to July. Further analysis revealed that the correlation between the vegetation and temperature was insignificant before 1995, but statistically significant from 1995. The study indicates that temperature is the major controlling factor of vegetation change in the Three-River Source Region, and the currently increase of temperature may increase vegetation coverage and /or density in the area. In addition, ecological restoration project started from 2005 in Three-River Source Region, and the currently increase of termperature may increase vegetation coverage and/ or density in the area. In addition, ecological restoration project started from 2005 in Three - River Source Region has a certain role in promoting the recovery of vegetation.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55274
Title: The potential of multitemporal Aqua and Terra MODIS apparent thermal inertia as a soil moisture indicator
Author: Jasper Van doninck, Jan Peters, Bernard De Baets, Eva M De Clercq, Els Ducheyne, Niko E C Verhoest
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 6, Dec 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Apparent thermal inertia, soil moisture, thermal infrared, MODIS, AMSR-E, Multitemporal analysis
Abstract: Variations in surface thermal inertia-the resistance to temperature variations -can be indicative for variations in soil moisture. In this paper, we present a flexible multitemporal approach to derive an approximation of thermal inertia, called apparent thermal inertia (ATI), from daily Aqua and Terra MODIS observations. In a first step, a varying number of land surface temperature measurements were, together with the time of observation, fit to a sinusoidal function to obtain diurnal surface temperature amplitudes. These were subsequently combined with surface albedo to drive ATI. This was done for the southern part of the African continent for the year 2009. Apparent thermal inertia was compared both spatially and temporally to AMSR-E soil moisture, generated by the algorithm developed by the Vrije Universiteit Amsterdam and NASA. The temporal behavior of apparent thermal inertia, derived using MODIS data only, showed a strong correspondence to that of AMSR - E soil moisture, especially in arid and semi-arid environments. The approach showed some limitations for vegetated terrains. Further post-processing is required to filter meteorologically induced noise and to transform ATI to actual soil moisture content.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55273
Title: Discrimination of common Mediterranean plant species using field spectroradiometry
Author: Kiril Manevski, Ioannis Manakos, George P Petropoulos, Chariton Kalaitzidis
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 6, Dec 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Mediterranean plants, Field spectroradiometry, MUFSPEM@MED, Spectral discrimination, statistical analysis, continuum removal
Abstract: Field spectroradiometry of land surface objects supports remote sensing analysis, facilitates the discrimination of vegetation species and enhances the mapping efficiency. Especially in the Mediterranean, spectral discrimination of common vegetaion types, such as phrygana and maquis species, remains a challenge. Both phrygana and maquis may be used as a direct indicator for grazing management, fire history and severity, and the state of the wider ecosystem equilibrium. This study aims to investigate the capacity of field spectroradiometry supporting remote sensing analysis of the land cover of a characteristic Mediterranean area. Five common Mediterranean maquis and phrygana species were examined. Spectra acquisition was performed during an intensive field campaign deployed in spring 2010, supported by a novel platform MUFSPEM@MED (Mobile Unit for Field SPEctral Measurements at the MEDiterranean) for high canopy measurements. Parametric and non-parametric statistical tests have been applied to the continuum - removed reflectance of the species in the visible to shortwave infrared spectral range. Interpretation of the results indicated distinct discrimination between the studied species at specific spectral regions. Statistically significant wavelengths were principally found in both the visible and the near infrared regions of the electromagnetic spectrum. Spectral bands in the shortwave infrared demonstrated significant discrimination features for the examined species adapted to Mediterranean drought. All in all, results confirmed the prospect for a more accurate mapping of the species spatial distribution using remote sensing imagery coupled with in situ spectral information.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55272
Title: Determination of chlorophyll content of small water bodies (kettle holes) using hyperspectral airborne data
Author: Rahmatulla M Igamberdiev, Goerres Grenzdoerffer, Ralf Bill, Hendrik Schubett, Martin Bachmann, Bernd Lennartz
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 6, Dec 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Small shallow water body (kettle hole), hyperspectral imagery, chlorophyll mapping
Abstract: This study presents an approach for chlorophyll content determination of small shallow water bodies (kettle holes) from hyperspectral airborne ROSIS and HyMap data (acquired on 15 May and 29 July 2008 respectively). Investigated field and airborne spectra for almost all kettle holes do not correspond to each other due to differences in ground sampling distance. Field spectra were collected from the height of 30-35cm (i.e. area of 0.01-0.015 m2). Airborne pixels of ROSIS and HyMap imgeries cover an area of 4 m2 and 16 m2 respectively and their spectra are highly influenced by algae or bottom properties of the kettle holes. Analysis of airborne spectra revealed that chlorophyll absorption near 677 nm is the same for both datasets. In order to enhance absorption properties, both airborne hyperspectral datasets were normalized by the coninuum removal approach. Linear regression algorithms for ROSIS HyMap datasets were derived using normalized average chlorophyll absorption spectra for each kettle hole. Overall accuracy of biomass mapping for ROSIS data was 71%, and for HyMap 64%. Biomass mapping results showed that, depending on the type of kettle hole, algae distribution, the ' packaging effect ' and bottom reflection lead to miscalculations of the chlorophyll content using hyperspectral airborne data.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55271
Title: A high throughput geocomputing system for remote sensing quantitative retrieval and a case study
Author: Yong Xue, Zigiang Chen, Hui Xu, Jianwen Ai, Shuzheng Jiang, Yingjie Li, Ying Wang, Jie Guang, Linlu Mei, Xijuan Jiao, Xingwei He, Tingting Hou
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 6, Dec 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Grid computing, workflow, service, Remote sensing quantitative retrieval, scheduling, aerosol
Abstract: The quality and accuracy of remote sensing instruments have been improved significantly, however, rapid processing of large-scale remote sensing data becomes the bottleneck for remote sensing quantitative retrieval applications. The remote sensing quantitative retrieval applications. The remote sensing quantitative retrieval is a data-intensive computation application, which is one of the research issues of high throughput computation. The remote sensing quantitative retrieval Grid workflow is a high-level core component of remote sensing Grid, which is used to support the modeling, reconstruction and implementation of large-scale complex applications of remote sensing science. In this paper, we intend to study middleware components of the remote sensing Grid- the dynamic Grid workflow based on the remote sensing quantitative retrieval application on Grid platform. We designed a novel architecture for the remote sensing Grid workflow. According to this architecture, we constructed the Remote Sensing Information Service Grid Node (RSSN) with Condor. We developed a graphic user interface (GUI) tools to compose remote sensing processing Grid workflows, and took the aerosol optical depth (AOD) retrieval as an example. The case study showed that significant improvement in the system performance could be achieved with this implementation. The results also give a perspective on the potential of applying Grid workflow practices to remote sensing quantitative retrieval problems using commodity class PCs.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55270
Title: Monitoring of the water-area variations of Lake Dongting in China with ENVISAT ASAR images
Author: Xian Wen Ding, XiaoFeng Li
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 6, Dec 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Lake Dongting, SAR, ENVISAT, Water area, Water level, Yangtze river
Abstract: As an active microwave remote sensing sensor, synthetic radar (SAR) can image the Earth surface with high spatial resolution in both day and night under all weather conditions. In this paper, a digital image processing technique was implemented to extract water area information from SAR images and the result is used to monitor the water area variation of Lake Dongting, the second largest freshwater lake in China. 8-year time series of Europena Space Agency ' s ENVISAT ASAR (Advanced Synthetic Aperture Radar) images acquired between 2002 and 2009 were obtained and a land-water classification scheme was implemented. Using independent in situ water level data measured at a lake -side hydrologica station during study period, we derived the relationship between water level and water area of Lake Dongting. The results show that, (1) during dry seasons, the water area is 518 km2 larger than that in the 1990s reported by Yangtze BHYRWRC (Bureau of Hydrology and Yangtze River Wate Resources Commission), 2000; (2) the water area of Lake Dongting increased significantly in the 2000s after the Chinese Government ' s "return land to lake" policy took effect in 1998; (3) the waer level of Lake Dongting could be low during a rainy season due to drought; but could be high in a dry season due to discharges from the upstream Three Gorges Dam. In addition, the relationship between water storage change and water area/level change is obtained.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55269
Title: Comparing object-based and pixel -based classifications for mapping savannas
Author: Timothy G Whiteside,Guy S Boggs, Stefan W Maier
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 6, Dec 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Object-based image analysis, accuracy assessment, tropical savanna, Northern Australia
Abstract: The development of robust object-based classification methods suitable for medium to high resolution satellite imagery provides a valid alternative to ' traditional ' pixel-based methods. This paper compares the results of an object-based classification to a supervised per-pixel classification for mapping land cover in the tropical north of the Northern territory of Australia. The object-based approach involved segmentation of image data into objects at multiple scale levels. Objects were assigned classes using training objects and the Nearest Neighbour supervised and fuzzy classification algorithm. The supervised pixel-based classification involved the selection of training areas and a classification using the maximum likelihood classifier algorithm. Site-specific accuracy assessment using confusion matrices of both classifications were undertaken based on 256 reference sites. A comparison of the results shows a statistically significant higher overall accuracy of the object-based classification over the pixel-based classification. The incorporation of a digital elevation model (DEM) layer and associated class rules into the object-bsed classification produced slightly higher accuracies overall and for certain classes; however this was object-based analysis has good potential for extracting land cover information from satellite imagery captured over spatially heterogeneous land covers of tropical Australia.
Location: 231
Literature cited 1: None
Literature cited 2: None
ID: 55268
Title: The use of a multilayer perceptron for detecting new human settlements from a time series of MODIS images
Author: B P Salmon, J C olivier, W Kleynhans, K J Wessels, F Van den Bergh, K C Steenkamp
Editor: Alfred Stein
Year: 2011
Publisher: Elsevier, Vol 13, Issue 6, Dec 2011
Source: Centre for Ecological Sciences
Reference: None
Subject: International Journal of Applied Earth Observation and Geoinformation
Keywords: Change detection, classification, feedforward neural networks, satellite, time series
Abstract: This paper presents a novel land cover change detection method that employs a sliding window over hyper-temporal multi-spectral images acquired from the 7 bands of the MoDerage- resolution Imaging Spectroradiometer (MODIS) land surface reflectance product. The method uses a Feedforward Multilayer perceptron (MLP) for supervised change detection that operates on multi-spectral time series extracted with a sliding window from the dataset. The method was evaluated on both real and simulated land cover change examples. The simulated land cover change comprises of concatenated time series that are produced by blending actual time series of pixels from human settlements to those from adjacent areas covered by natural vegetation. The method employs an iteratively retrained MLP to capture all local patterns and to compensate for the time- varying climate change in the geographical area. The iteratively retained MLP was compared to a classical batch mode trained MLP. Depending on the length of the temporal sliding window used, an overall change detection accuracy between 83% adn 90% was achieved. It is shown that a sliding window of 6 months using all 7 bands of MODIS data is sufficient to detect land cover change reliably. Window sizes of 18 months and longer provide minor improvements to classification accuracy and change detection performance at the cost of longer time delays.
Location: 231
Literature cited 1: None
Literature cited 2: None