@article{PhilippDietzUllmannetal.2022,
  author    = {Philipp, Marius and Dietz, Andreas and Ullmann, Tobias and Kuenzer, Claudia},
  title     = {Automated extraction of annual erosion rates for Arctic permafrost coasts using Sentinel-1, Deep Learning, and Change Vector Analysis},
  series = {Remote Sensing},
  volume    = {14},
  journal   = {Remote Sensing},
  number    = {15},
  issn      = {2072-4292},
  doi       = {10.3390/rs14153656},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-281956},
  year      = {2022},
  abstract  = {Arctic permafrost coasts become increasingly vulnerable due to environmental drivers such as the reduced sea-ice extent and duration as well as the thawing of permafrost itself. A continuous quantification of the erosion process on large to circum-Arctic scales is required to fully assess the extent and understand the consequences of eroding permafrost coastlines. This study presents a novel approach to quantify annual Arctic coastal erosion and build-up rates based on Sentinel-1 (S1) Synthetic Aperture RADAR (SAR) backscatter data, in combination with Deep Learning (DL) and Change Vector Analysis (CVA). The methodology includes the generation of a high-quality Arctic coastline product via DL, which acted as a reference for quantifying coastal erosion and build-up rates from annual median and standard deviation (sd) backscatter images via CVA. The analysis was applied on ten test sites distributed across the Arctic and covering about 1038 km of coastline. Results revealed maximum erosion rates of up to 160 m for some areas and an average erosion rate of 4.37 m across all test sites within a three-year temporal window from 2017 to 2020. The observed erosion rates within the framework of this study agree with findings published in the previous literature. The proposed methods and data can be applied on large scales and, prospectively, even for the entire Arctic. The generated products may be used for quantifying the loss of frozen ground, estimating the release of stored organic material, and can act as a basis for further related studies in Arctic coastal environments.},
  language  = {en}
}
@article{UllmannSauerbreyHoffmeisteretal.2019,
  author    = {Ullmann, Tobias and Sauerbrey, Julia and Hoffmeister, Dirk and May, Simon Matthias and Baumhauer, Roland and Bubenzer, Olaf},
  title     = {Assessing Spatiotemporal Variations of Sentinel-1 InSAR Coherence at Different Time Scales over the Atacama Desert (Chile) between 2015 and 2018},
  series = {Remote Sensing},
  volume    = {11},
  journal   = {Remote Sensing},
  number    = {24},
  issn      = {2072-4292},
  doi       = {10.3390/rs11242960},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-193836},
  pages     = {2960},
  year      = {2019},
  abstract  = {This study investigates synthetic aperture radar (SAR) time series of the Sentinel-1 mission acquired over the Atacama Desert, Chile, between March 2015 and December 2018. The contribution analyzes temporal and spatial variations of Sentinel-1 interferometric SAR (InSAR) coherence and exemplarily illustrates factors that are responsible for observed signal differences. The analyses are based on long temporal baselines (365-1090 days) and temporally dense time series constructed with short temporal baselines (12-24 days). Results are compared to multispectral data of Sentinel-2, morphometric features of the digital elevation model (DEM) TanDEM-X WorldDEM™, and to a detailed governmental geographic information system (GIS) dataset of the local hydrography. Sentinel-1 datasets are suited for generating extensive, nearly seamless InSAR coherence mosaics covering the entire Atacama Desert (>450 × 1100 km) at a spatial resolution of 20 × 20 meter per pixel. Temporal baselines over several years lead only to very minor decorrelation, indicating a very high signal stability of C-Band in this region, especially in the hyperarid uplands between the Coastal Cordillera and the Central Depression. Signal decorrelation was associated with certain types of surface cover (e.g., water or aeolian deposits) or with actual surface dynamics (e.g., anthropogenic disturbance (mining) or fluvial activity and overland flow). Strong rainfall events and fluvial activity in the periods 2015 to 2016 and 2017 to 2018 caused spatial patterns with significant signal decorrelation; observed linear coherence anomalies matched the reference channel network and indicated actual episodic and sporadic discharge events. In the period 2015-2016, area-wide loss of coherence appeared as strip-like patterns of more than 80 km length that matched the prevailing wind direction. These anomalies, and others observed in that period and in the period 2017-2018, were interpreted to be caused by overland flow of high magnitude, as their spatial location matched well with documented heavy rainfall events that showed cumulative precipitation amounts of more than 20 mm.},
  language  = {en}
}
@article{NillUllmannKneiseletal.2019,
  author    = {Nill, Leon and Ullmann, Tobias and Kneisel, Christof and Sobiech-Wolf, Jennifer and Baumhauer, Roland},
  title     = {Assessing Spatiotemporal Variations of Landsat Land Surface Temperature and Multispectral Indices in the Arctic Mackenzie Delta Region between 1985 and 2018},
  series = {Remote Sensing},
  volume    = {11},
  journal   = {Remote Sensing},
  number    = {19},
  issn      = {2072-4292},
  doi       = {10.3390/rs11192329},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-193301},
  year      = {2019},
  abstract  = {Air temperatures in the Arctic have increased substantially over the last decades, which has extensively altered the properties of the land surface. Capturing the state and dynamics of Land Surface Temperatures (LSTs) at high spatial detail is of high interest as LST is dependent on a variety of surficial properties and characterizes the land-atmosphere exchange of energy. Accordingly, this study analyses the influence of different physical surface properties on the long-term mean of the summer LST in the Arctic Mackenzie Delta Region (MDR) using Landsat 30 m-resolution imagery between 1985 and 2018 by taking advantage of the cloud computing capabilities of the Google Earth Engine. Multispectral indices, including the Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI) and Tasseled Cap greenness (TCG), brightness (TCB), and wetness (TCW) as well as topographic features derived from the TanDEM-X digital elevation model are used in correlation and multiple linear regression analyses to reveal their influence on the LST. Furthermore, surface alteration trends of the LST, NDVI, and NDWI are revealed using the Theil-Sen (T-S) regression method. The results indicate that the mean summer LST appears to be mostly influenced by the topographic exposition as well as the prevalent moisture regime where higher evapotranspiration rates increase the latent heat flux and cause a cooling of the surface, as the variance is best explained by the TCW and northness of the terrain. However, fairly diverse model outcomes for different regions of the MDR (R2 from 0.31 to 0.74 and RMSE from 0.51 °C to 1.73 °C) highlight the heterogeneity of the landscape in terms of influential factors and suggests accounting for a broad spectrum of different factors when modeling mean LSTs. The T-S analysis revealed large-scale wetting and greening trends with a mean decadal increase of the NDVI/NDWI of approximately +0.03 between 1985 and 2018, which was mostly accompanied by a cooling of the land surface given the inverse relationship between mean LSTs and vegetation and moisture conditions. Disturbance through wildfires intensifies the surface alterations locally and lead to significantly cooler LSTs in the long-term compared to the undisturbed surroundings.},
  language  = {en}
}
@article{KleinOppeltKuenzer2021,
  author    = {Klein, Igor and Oppelt, Natascha and Kuenzer, Claudia},
  title     = {Application of remote sensing data for locust research and management — a review},
  series = {Insects},
  volume    = {12},
  journal   = {Insects},
  number    = {3},
  issn      = {2075-4450},
  doi       = {10.3390/insects12030233},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-234090},
  year      = {2021},
  abstract  = {Recently, locust outbreaks around the world have destroyed agricultural and natural vegetation and caused massive damage endangering food security. Unusual heavy rainfalls in habitats of the desert locust (Schistocerca gregaria) and lack of monitoring due to political conflicts or inaccessibility of those habitats lead to massive desert locust outbreaks and swarms migrating over the Arabian Peninsula, East Africa, India and Pakistan. At the same time, swarms of the Moroccan locust (Dociostaurus maroccanus) in some Central Asian countries and swarms of the Italian locust (Calliptamus italicus) in Russia and China destroyed crops despite developed and ongoing monitoring and control measurements. These recent events underline that the risk and damage caused by locust pests is as present as ever and affects 100 million of human lives despite technical progress in locust monitoring, prediction and control approaches. Remote sensing has become one of the most important data sources in locust management. Since the 1980s, remote sensing data and applications have accompanied many locust management activities and contributed to an improved and more effective control of locust outbreaks and plagues. Recently, open-access remote sensing data archives as well as progress in cloud computing provide unprecedented opportunity for remote sensing-based locust management and research. Additionally, unmanned aerial vehicle (UAV) systems bring up new prospects for a more effective and faster locust control. Nevertheless, the full capacity of available remote sensing applications and possibilities have not been exploited yet. This review paper provides a comprehensive and quantitative overview of international research articles focusing on remote sensing application for locust management and research. We reviewed 110 articles published over the last four decades, and categorized them into different aspects and main research topics to summarize achievements and gaps for further research and application development. The results reveal a strong focus on three species — the desert locust, the migratory locust (Locusta migratoria), and the Australian plague locust (Chortoicetes terminifera) — and corresponding regions of interest. There is still a lack of international studies for other pest species such as the Italian locust, the Moroccan locust, the Central American locust (Schistocerca piceifrons), the South American locust (Schistocerca cancellata), the brown locust (Locustana pardalina) and the red locust (Nomadacris septemfasciata). In terms of applied sensors, most studies utilized Advanced Very-High-Resolution Radiometer (AVHRR), Satellite Pour l'Observation de la Terre VEGETATION (SPOT-VGT), Moderate-Resolution Imaging Spectroradiometer (MODIS) as well as Landsat data focusing mainly on vegetation monitoring or land cover mapping. Application of geomorphological metrics as well as radar-based soil moisture data is comparably rare despite previous acknowledgement of their importance for locust outbreaks. Despite great advance and usage of available remote sensing resources, we identify several gaps and potential for future research to further improve the understanding and capacities of the use of remote sensing in supporting locust outbreak- research and management.},
  language  = {en}
}
@article{HuthGessnerKleinetal.2020,
  author    = {Huth, Juliane and Gessner, Ursula and Klein, Igor and Yesou, Herv{\´e} and Lai, Xijun and Oppelt, Natascha and Kuenzer, Claudia},
  title     = {Analyzing water dynamics based on Sentinel-1 time series — a study for Dongting Lake wetlands in China},
  series = {Remote Sensing},
  volume    = {12},
  journal   = {Remote Sensing},
  number    = {11},
  issn      = {2072-4292},
  doi       = {10.3390/rs12111761},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-205977},
  year      = {2020},
  abstract  = {In China, freshwater is an increasingly scarce resource and wetlands are under great pressure. This study focuses on China's second largest freshwater lake in the middle reaches of the Yangtze River — the Dongting Lake — and its surrounding wetlands, which are declared a protected Ramsar site. The Dongting Lake area is also a research region of focus within the Sino-European Dragon Programme, aiming for the international collaboration of Earth Observation researchers. ESA's Copernicus Programme enables comprehensive monitoring with area-wide coverage, which is especially advantageous for large wetlands that are difficult to access during floods. The first year completely covered by Sentinel-1 SAR satellite data was 2016, which is used here to focus on Dongting Lake's wetland dynamics. The well-established, threshold-based approach and the high spatio-temporal resolution of Sentinel-1 imagery enabled the generation of monthly surface water maps and the analysis of the inundation frequency at a 10 m resolution. The maximum extent of the Dongting Lake derived from Sentinel-1 occurred in July 2016, at 2465 km\(^2\), indicating an extreme flood year. The minimum size of the lake was detected in October, at 1331 km\(^2\). Time series analysis reveals detailed inundation patterns and small-scale structures within the lake that were not known from previous studies. Sentinel-1 also proves to be capable of mapping the wetland management practices for Dongting Lake polders and dykes. For validation, the lake extent and inundation duration derived from the Sentinel-1 data were compared with excerpts from the Global WaterPack (frequently derived by the German Aerospace Center, DLR), high-resolution optical data, and in situ water level data, which showed very good agreement for the period studied. The mean monthly extent of the lake in 2016 from Sentinel-1 was 1798 km\(^2\), which is consistent with the Global WaterPack, deviating by only 4\%. In summary, the presented analysis of the complete annual time series of the Sentinel-1 data provides information on the monthly behavior of water expansion, which is of interest and relevance to local authorities involved in water resource management tasks in the region, as well as to wetland conservationists concerned with the Ramsar site wetlands of Dongting Lake and to local researchers.},
  language  = {en}
}
@article{MahmoudDukerConradetal.2016,
  author    = {Mahmoud, Mahmoud Ibrahim and Duker, Alfred and Conrad, Christopher and Thiel, Michael and Ahmad, Halilu Shaba},
  title     = {Analysis of Settlement Expansion and Urban Growth Modelling Using Geoinformation for Assessing Potential Impacts of Urbanization on Climate in Abuja City, Nigeria},
  series = {Remote Sensing},
  volume    = {8},
  journal   = {Remote Sensing},
  number    = {3},
  doi       = {10.3390/rs8030220},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-146644},
  pages     = {220},
  year      = {2016},
  abstract  = {This study analyzed the spatiotemporal pattern of settlement expansion in Abuja, Nigeria, one of West Africa's fastest developing cities, using geoinformation and ancillary datasets. Three epochs of Land-use Land-cover (LULC) maps for 1986, 2001 and 2014 were derived from Landsat images using support vector machines (SVM). Accuracy assessment (AA) of the LULC maps based on the pixel count resulted in overall accuracy of 82\%, 92\% and 92\%, while the AA derived from the error adjusted area (EAA) method stood at 69\%, 91\% and 91\% for 1986, 2001 and 2014, respectively. Two major techniques for detecting changes in the LULC epochs involved the use of binary maps as well as a post-classification comparison approach. Quantitative spatiotemporal analysis was conducted to detect LULC changes with specific focus on the settlement development pattern of Abuja, the federal capital city (FCC) of Nigeria. Logical transitions to the urban category were modelled for predicting future scenarios for the year 2050 using the embedded land change modeler (LCM) in the IDRISI package. Based on the EAA, the result showed that urban areas increased by more than 11\% between 1986 and 2001. In contrast, this value rose to 17\% between 2001 and 2014. The LCM model projected LULC changes that showed a growing trend in settlement expansion, which might take over allotted spaces for green areas and agricultural land if stringent development policies and enforcement measures are not implemented. In conclusion, integrating geospatial technologies with ancillary datasets offered improved understanding of how urbanization processes such as increased imperviousness of such a magnitude could influence the urban microclimate through the alteration of natural land surface temperature. Urban expansion could also lead to increased surface runoff as well as changes in drainage geography leading to urban floods.},
  language  = {en}
}
@article{TimmermansvanderTolTimmermansetal.2015,
  author    = {Timmermans, Wim J. and van der Tol, Christiaan and Timmermans, Joris and Ucer, Murat and Chen, Xuelong and Alonso, Luis and Moreno, Jose and Carrara, Arnaud and Lopez, Ramon and Fernando de la Cruz, Tercero and Corcoles, Horacio L. and de Miguel, Eduardo and Sanchez, Jose A. G. and Perez, Irene and Belen, Perez and Munoz, Juan-Carlos J. and Skokovic, Drazen and Sobrino, Jose and Soria, Guillem and MacArthur, Alasdair and Vescovo, Loris and Reusen, Ils and Andreu, Ana and Burkart, Andreas and Cilia, Chiara and Contreras, Sergio and Corbari, Chiara and Calleja, Javier F. and Guzinski, Radoslaw and Hellmann, Christine and Herrmann, Ittai and Kerr, Gregoire and Lazar, Adina-Laura and Leutner, Benjamin and Mendiguren, Gorka and Nasilowska, Sylwia and Nieto, Hector and Pachego-Labrador, Javier and Pulanekar, Survana and Raj, Rahul and Schikling, Anke and Siegmann, Bastian and von Bueren, Stefanie and Su, Zhongbo (Bob)},
  title     = {An Overview of the Regional Experiments for Land-atmosphere Exchanges 2012 (REFLEX 2012) Campaign},
  series = {Acta Geophysica},
  volume    = {63},
  journal   = {Acta Geophysica},
  number    = {6},
  doi       = {10.2478/s11600-014-0254-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-136491},
  pages     = {1465-1484},
  year      = {2015},
  abstract  = {The REFLEX 2012 campaign was initiated as part of a training course on the organization of an airborne campaign to support advancement of the understanding of land-atmosphere interaction processes. This article describes the campaign, its objectives and observations, remote as well as in situ. The observations took place at the experimental Las Tiesas farm in an agricultural area in the south of Spain. During the period of ten days, measurements were made to capture the main processes controlling the local and regional land-atmosphere exchanges. Apart from multi-temporal, multi-directional and multi-spatial space-borne and airborne observations, measurements of the local meteorology, energy fluxes, soil temperature profiles, soil moisture profiles, surface temperature, canopy structure as well as leaf-level measurements were carried out. Additional thermo-dynamical monitoring took place at selected sites. After presenting the different types of measurements, some examples are given to illustrate the potential of the observations made.},
  language  = {en}
}
@article{KnauerGessnerFensholtetal.2016,
  author    = {Knauer, Kim and Gessner, Ursula and Fensholt, Rasmus and Kuenzer, Claudia},
  title     = {An ESTARFM Fusion Framework for the Generation of Large-Scale Time Series in Cloud-Prone and Heterogeneous Landscapes},
  series = {Remote Sensing},
  volume    = {8},
  journal   = {Remote Sensing},
  number    = {5},
  doi       = {10.3390/rs8050425},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-180712},
  pages     = {425},
  year      = {2016},
  abstract  = {Monitoring the spatio-temporal development of vegetation is a challenging task in heterogeneous and cloud-prone landscapes. No single satellite sensor has thus far been able to provide consistent time series of high temporal and spatial resolution for such areas. In order to overcome this problem, data fusion algorithms such as the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) have been established and frequently used in recent years to generate high-resolution time series. In order to make it applicable to larger scales and to increase the input data availability especially in cloud-prone areas, an ESTARFM framework was developed in this study introducing several enhancements. An automatic filling of cloud gaps was included in the framework to make best use of available, even partly cloud-covered Landsat images. Furthermore, the ESTARFM algorithm was enhanced to automatically account for regional differences in the heterogeneity of the study area. The generation of time series was automated and the processing speed was accelerated significantly by parallelization. To test the performance of the developed ESTARFM framework, MODIS and Landsat-8 data were fused for generating an 8-day NDVI time series for a study area of approximately 98,000 km\(^{2}\) in West Africa. The results show that the ESTARFM framework can accurately produce high temporal resolution time series (average MAE (mean absolute error) of 0.02 for the dry season and 0.05 for the vegetative season) while keeping the spatial detail in such a heterogeneous, cloud-prone region. The developments introduced within the ESTARFM framework establish the basis for large-scale research on various geoscientific questions related to land degradation, changes in land surface phenology or agriculture},
  language  = {en}
}
@article{ElsebergBorrmannNuechter2013,
  author    = {Elseberg, Jan and Borrmann, Dorit and N{\"u}chter, Andreas},
  title     = {Algorithmic Solutions for Computing Precise Maximum Likelihood 3D Point Clouds from Mobile Laser Scanning Platforms},
  series = {Remote Sensing},
  volume    = {5},
  journal   = {Remote Sensing},
  number    = {11},
  doi       = {10.3390/rs5115871},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-130478},
  pages     = {5871-5906},
  year      = {2013},
  abstract  = {Mobile laser scanning puts high requirements on the accuracy of the positioning systems and the calibration of the measurement system. We present a novel algorithmic approach for calibration with the goal of improving the measurement accuracy of mobile laser scanners. We describe a general framework for calibrating mobile sensor platforms that estimates all configuration parameters for any arrangement of positioning sensors, including odometry. In addition, we present a novel semi-rigid Simultaneous Localization and Mapping (SLAM) algorithm that corrects the vehicle position at every point in time along its trajectory, while simultaneously improving the quality and precision of the entire acquired point cloud. Using this algorithm, the temporary failure of accurate external positioning systems or the lack thereof can be compensated for. We demonstrate the capabilities of the two newly proposed algorithms on a wide variety of datasets.},
  language  = {en}
}
@phdthesis{Loew2013,
  author    = {L{\"o}w, Fabian},
  title     = {Agricultural crop mapping from multi-scale remote sensing data - Concepts and applications in heterogeneous Middle Asian agricultural landscapes},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-102093},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2013},
  abstract  = {Agriculture is mankind's primary source of food production and plays the key role for cereal supply to humanity. One of the future challenges will be to feed a constantly growing population, which is expected to reach more than nine billion by 2050. The potential to expand cropland is limited, and enhancing agricultural production efficiency is one important means to meet the future food demand. Hence, there is an increasing demand for dependable, accurate and comprehensive agricultural intelligence on crop production. The value of satellite earth observation (EO) data for agricultural monitoring is well recognized. One fundamental requirement for agricultural monitoring is routinely updated information on crop acreage and the spatial distribution of crops. With the technical advancement of satellite sensor systems, imagery with higher temporal and finer spatial resolution became available. The classification of such multi-temporal data sets is an effective and accurate means to produce crop maps, but methods must be developed that can handle such large and complex data sets. Furthermore, to properly use satellite EO for agricultural production monitoring a high temporal revisit frequency over vast geographic areas is often necessary. However, this often limits the spatial resolution that can be used. The challenge of discriminating pixels that correspond to a particular crop type, a prerequisite for crop specific agricultural monitoring, remains daunting when the signal encoded in pixels stems from several land uses (mixed pixels), e.g. over heterogeneous landscapes where individual fields are often smaller than individual pixels. The main purposes of the presented study were (i) to assess the influence of input dimensionality and feature selection on classification accuracy and uncertainty in object-based crop classification, (ii) to evaluate if combining classifier algorithms can improve the quality of crop maps (e.g. classification accuracy), (iii) to assess the spatial resolution requirements for crop identification via image classification. Reporting on the map quality is traditionally done with measures that stem from the confusion matrix based on the hard classification result. Yet, these measures do not consider the spatial variation of errors in maps. Measures of classification uncertainty can be used for this purpose, but they have attained only little attention in remote sensing studies. Classifier algorithms like the support vector machine (SVM) can estimate class memberships (the so called soft output) for each classified pixel or object. Based on these estimations, measures of classification uncertainty can be calculated, but it has not been analysed in detail, yet, if these are reliable in predicting the spatial distribution of errors in maps. In this study, SVM was applied for the classification of agricultural crops in irrigated landscapes in Middle Asia at the object-level. Five different categories of features were calculated from RapidEye time series data as classification input. The reliability of classification uncertainty measures like entropy, derived from the soft output of SVM, with regard to predicting the spatial distribution of error was evaluated. Further, the impact of the type and dimensionality of the input data on classification uncertainty was analysed. The results revealed that SMVs applied to the five feature categories separately performed different in classifying different types of crops. Incorporating all five categories of features by concatenating them into one stacked vector did not lead to an increase in accuracy, and partly reduced the model performance most obviously because of the Hughes phenomena. Yet, applying the random forest (RF) algorithm to select a subset of features led to an increase of classification accuracy of the SVM. The feature group with red edge-based indices was the most important for general crop classification, and the red edge NDVI had an outstanding importance for classifying crops. Two measures of uncertainty were calculated based on the soft output from SVM: maximum a-posteriori probability and alpha quadratic entropy. Irrespective of the measure used, the results indicate a decline in classification uncertainty when a dimensionality reduction was performed. The two uncertainty measures were found to be reliable indicators to predict errors in maps. Correctly classified test cases were associated with low uncertainty, whilst incorrectly test cases tended to be associated with higher uncertainty. The issue of combining the results of different classifier algorithms in order to increase classification accuracy was addressed. First, the SVM was compared with two other non-parametric classifier algorithms: multilayer perceptron neural network (MLP) and RF. Despite their comparatively high classification performance, each of the tested classifier algorithms tended to make errors in different parts of the input space, e.g. performed different in classifying crops. Hence, a combination of the complementary outputs was envisaged. To this end, a classifier combination scheme was proposed, which is based on existing algebraic operators. It combines the outputs of different classifier algorithms at the per-case (e.g. pixel or object) basis. The per-case class membership estimations of each classifier algorithm were compared, and the reliability of each classifier algorithm with respect to classifying a specific crop class was assessed based on the confusion matrix. In doing so, less reliable classifier algorithms were excluded at the per-class basis before the final combination. Emphasis was put on evaluating the selected classification algorithms under limiting conditions by applying them to small input datasets and to reduced training sample sets, respectively. Further, the applicability to datasets from another year was demonstrated to assess temporal transferability. Although the single classifier algorithms performed well in all test sites, the classifier combination scheme provided consistently higher classification accuracies over all test sites and in different years, respectively. This makes this approach distinct from the single classifier algorithms, which performed different and showed a higher variability in class-wise accuracies. Further, the proposed classifier combination scheme performed better when using small training set sizes or when applied to small input datasets, respectively. A framework was proposed to quantitatively define pixel size requirements for crop identification via image classification. That framework is based on simulating how agricultural landscapes, and more specifically the fields covered by one crop of interest, are seen by instruments with increasingly coarser resolving power. The concept of crop specific pixel purity, defined as the degree of homogeneity of the signal encoded in a pixel with respect to the target crop type, is used to analyse how mixed the pixels can be (as they become coarser) without undermining their capacity to describe the desired surface properties (e.g. to distinguish crop classes via supervised or unsupervised image classification). This tool can be modulated using different parameterizations to explore trade-offs between pixel size and pixel purity when addressing the question of crop identification. Inputs to the experiments were eight multi-temporal images from the RapidEye sensor. Simulated pixel sizes ranged from 13 m to 747.5 m, in increments of 6.5 m. Constraining parameters for crop identification were defined by setting thresholds for classification accuracy and uncertainty. Results over irrigated agricultural landscapes in Middle Asia demonstrate that the task of finding the optimum pixel size did not have a "one-size-fits-all" solution. The resulting values for pixel size and purity that were suitable for crop identification proved to be specific to a given landscape, and for each crop they differed across different landscapes. Over the same time series, different crops were not identifiable simultaneously in the season and these requirements further changed over the years, reflecting the different agro-ecological conditions the investigated crops were growing in. Results further indicate that map quality (e.g. classification accuracy) was not homogeneously distributed in a landscape, but that it depended on the spatial structures and the pixel size, respectively. The proposed framework is generic and can be applied to any agricultural landscape, thereby potentially serving to guide recommendations for designing dedicated EO missions that can satisfy the requirements in terms of pixel size to identify and discriminate crop types. Regarding the operationalization of EO-based techniques for agricultural monitoring and its application to a broader range of agricultural landscapes, it can be noted that, despite the high performance of existing methods (e.g. classifier algorithms), transferability and stability of such methods remain one important research issue. This means that methods developed and tested in one place might not necessarily be portable to another place or over several years, respectively. Specifically in Middle Asia, which was selected as study region in this thesis, classifier combination makes sense due to its easy implementation and because it enhanced classification accuracy for classes with insufficient training samples. This observation makes it interesting for operational contexts and when field reference data availability is limited. Similar to the transferability of methods, the application of only one certain kind of EO data (e.g. with one specific pixel size) over different landscapes needs to be revisited and the synergistic use of multi-scale data, e.g. combining remote sensing imagery of both fine and coarse spatial resolution, should be fostered. The necessity to predict and control the effects of spatial and temporal scale on crop classification is recognized here as a major goal to achieve in EO-based agricultural monitoring.},
  subject      = {Fernerkundung},
  language  = {en}
}