@article{UereyenBachoferKuenzer2022,
  author    = {Uereyen, Soner and Bachofer, Felix and Kuenzer, Claudia},
  title     = {A framework for multivariate analysis of land surface dynamics and driving variables — a case study for Indo-Gangetic river basins},
  series = {Remote Sensing},
  volume    = {14},
  journal   = {Remote Sensing},
  number    = {1},
  issn      = {2072-4292},
  doi       = {10.3390/rs14010197},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-255295},
  year      = {2022},
  abstract  = {The analysis of the Earth system and interactions among its spheres is increasingly important to improve the understanding of global environmental change. In this regard, Earth observation (EO) is a valuable tool for monitoring of long term changes over the land surface and its features. Although investigations commonly study environmental change by means of a single EO-based land surface variable, a joint exploitation of multivariate land surface variables covering several spheres is still rarely performed. In this regard, we present a novel methodological framework for both, the automated processing of multisource time series to generate a unified multivariate feature space, as well as the application of statistical time series analysis techniques to quantify land surface change and driving variables. In particular, we unify multivariate time series over the last two decades including vegetation greenness, surface water area, snow cover area, and climatic, as well as hydrological variables. Furthermore, the statistical time series analyses include quantification of trends, changes in seasonality, and evaluation of drivers using the recently proposed causal discovery algorithm Peter and Clark Momentary Conditional Independence (PCMCI). We demonstrate the functionality of our methodological framework using Indo-Gangetic river basins in South Asia as a case study. The time series analyses reveal increasing trends in vegetation greenness being largely dependent on water availability, decreasing trends in snow cover area being mostly negatively coupled to temperature, and trends of surface water area to be spatially heterogeneous and linked to various driving variables. Overall, the obtained results highlight the value and suitability of this methodological framework with respect to global climate change research, enabling multivariate time series preparation, derivation of detailed information on significant trends and seasonality, as well as detection of causal links with minimal user intervention. This study is the first to use multivariate time series including several EO-based variables to analyze land surface dynamics over the last two decades using the causal discovery algorithm PCMCI.},
  language  = {en}
}
@article{RiyasSyedKumaretal.2021,
  author    = {Riyas, Moidu Jameela and Syed, Tajdarul Hassan and Kumar, Hrishikesh and Kuenzer, Claudia},
  title     = {Detecting and analyzing the evolution of subsidence due to coal fires in Jharia coalfield, India using Sentinel-1 SAR data},
  series = {Remote Sensing},
  volume    = {13},
  journal   = {Remote Sensing},
  number    = {8},
  issn      = {2072-4292},
  doi       = {10.3390/rs13081521},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-236703},
  year      = {2021},
  abstract  = {Public safety and socio-economic development of the Jharia coalfield (JCF) in India is critically dependent on precise monitoring and comprehensive understanding of coal fires, which have been burning underneath for more than a century. This study utilizes New-Small BAseline Subset (N-SBAS) technique to compute surface deformation time series for 2017-2020 to characterize the spatiotemporal dynamics of coal fires in JCF. The line-of-sight (LOS) surface deformation estimated from ascending and descending Sentinel-1 SAR data are subsequently decomposed to derive precise vertical subsidence estimates. The most prominent subsidence (~22 cm) is observed in Kusunda colliery. The subsidence regions also correspond well with the Landsat-8 based thermal anomaly map and field evidence. Subsequently, the vertical surface deformation time-series is analyzed to characterize temporal variations within the 9.5 km\(^2\) area of coal fires. Results reveal that nearly 10\% of the coal fire area is newly formed, while 73\% persisted throughout the study period. Vulnerability analyses performed in terms of the susceptibility of the population to land surface collapse demonstrate that Tisra, Chhatatanr, and Sijua are the most vulnerable towns. Our results provide critical information for developing early warning systems and remediation strategies.},
  language  = {en}
}
@article{ReinermannGessnerAsametal.2019,
  author    = {Reinermann, Sophie and Gessner, Ursula and Asam, Sarah and Kuenzer, Claudia and Dech, Stefan},
  title     = {The Effect of Droughts on Vegetation Condition in Germany: An Analysis Based on Two Decades of Satellite Earth Observation Time Series and Crop Yield Statistics},
  series = {Remote Sensing},
  volume    = {11},
  journal   = {Remote Sensing},
  number    = {15},
  doi       = {10.3390/rs11151783},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-225165},
  pages     = {1783, 1-21},
  year      = {2019},
  abstract  = {Central Europe experienced several droughts in the recent past, such as in the year 2018, which was characterized by extremely low rainfall rates and high temperatures, resulting in substantial agricultural yield losses. Time series of satellite earth observation data enable the characterization of past drought events over large temporal and spatial scales. Within this study, Moderate Resolution Spectroradiometer (MODIS) Enhanced Vegetation Index (EVI) (MOD13Q1) 250 m time series were investigated for the vegetation periods of 2000 to 2018. The spatial and temporal development of vegetation in 2018 was compared to other dry and hot years in Europe, like the drought year 2003. Temporal and spatial inter- and intra-annual patterns of EVI anomalies were analyzed for all of Germany and for its cropland, forest, and grassland areas individually. While vegetation development in spring 2018 was above average, the summer months of 2018 showed negative anomalies in a similar magnitude as in 2003, which was particularly apparent within grassland and cropland areas in Germany. In contrast, the year 2003 showed negative anomalies during the entire growing season. The spatial pattern of vegetation status in 2018 showed high regional variation, with north-eastern Germany mainly affected in June, north-western parts in July, and western Germany in August. The temporal pattern of satellite-derived EVI deviances within the study period 2000-2018 were in good agreement with crop yield statistics for Germany. The study shows that the EVI deviation of the summer months of 2018 were among the most extreme in the study period compared to other years. The spatial pattern and temporal development of vegetation condition between the drought years differ.},
  language  = {en}
}
@article{KnauerGessnerFensholtetal.2017,
  author    = {Knauer, Kim and Gessner, Ursula and Fensholt, Rasmus and Forkuor, Gerald and Kuenzer, Claudia},
  title     = {Monitoring agricultural expansion in Burkina Faso over 14 years with 30 m resolution time series: the role of population growth and implications for the environment},
  series = {Remote Sensing},
  volume    = {9},
  journal   = {Remote Sensing},
  number    = {2},
  doi       = {10.3390/rs9020132},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-171905},
  year      = {2017},
  abstract  = {Burkina Faso ranges amongst the fastest growing countries in the world with an annual population growth rate of more than three percent. This trend has consequences for food security since agricultural productivity is still on a comparatively low level in Burkina Faso. In order to compensate for the low productivity, the agricultural areas are expanding quickly. The mapping and monitoring of this expansion is difficult, even on the basis of remote sensing imagery, since the extensive farming practices and frequent cloud coverage in the area make the delineation of cultivated land from other land cover and land use types a challenging task. However, as the rapidly increasing population could have considerable effects on the natural resources and on the regional development of the country, methods for improved mapping of LULCC (land use and land cover change) are needed. For this study, we applied the newly developed ESTARFM (Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model) framework to generate high temporal (8-day) and high spatial (30 m) resolution NDVI time series for all of Burkina Faso for the years 2001, 2007, and 2014. For this purpose, more than 500 Landsat scenes and 3000 MODIS scenes were processed with this automated framework. The generated ESTARFM NDVI time series enabled extraction of per-pixel phenological features that all together served as input for the delineation of agricultural areas via random forest classification at 30 m spatial resolution for entire Burkina Faso and the three years. For training and validation, a randomly sampled reference dataset was generated from Google Earth images and based on expert knowledge. The overall accuracies of 92\% (2001), 91\% (2007), and 91\% (2014) indicate the well-functioning of the applied methodology. The results show an expansion of agricultural area of 91\% between 2001 and 2014 to a total of 116,900 km\(^2\). While rainfed agricultural areas account for the major part of this trend, irrigated areas and plantations also increased considerably, primarily promoted by specific development projects. This expansion goes in line with the rapid population growth in most provinces of Burkina Faso where land was still available for an expansion of agricultural area. The analysis of agricultural encroachment into protected areas and their surroundings highlights the increased human pressure on these areas and the challenges of environmental protection for the future.},
  language  = {en}
}
@article{DirscherlDietzKneiseletal.2020,
  author    = {Dirscherl, Mariel and Dietz, Andreas J. and Kneisel, Christof and Kuenzer, Claudia},
  title     = {Automated mapping of Antarctic supraglacial lakes using a Machine Learning approach},
  series = {Remote Sensing},
  volume    = {12},
  journal   = {Remote Sensing},
  number    = {7},
  issn      = {2072-4292},
  doi       = {10.3390/rs12071203},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-203735},
  year      = {2020},
  abstract  = {Supraglacial lakes can have considerable impact on ice sheet mass balance and global sea-level-rise through ice shelf fracturing and subsequent glacier speedup. In Antarctica, the distribution and temporal development of supraglacial lakes as well as their potential contribution to increased ice mass loss remains largely unknown, requiring a detailed mapping of the Antarctic surface hydrological network. In this study, we employ a Machine Learning algorithm trained on Sentinel-2 and auxiliary TanDEM-X topographic data for automated mapping of Antarctic supraglacial lakes. To ensure the spatio-temporal transferability of our method, a Random Forest was trained on 14 training regions and applied over eight spatially independent test regions distributed across the whole Antarctic continent. In addition, we employed our workflow for large-scale application over Amery Ice Shelf where we calculated interannual supraglacial lake dynamics between 2017 and 2020 at full ice shelf coverage. To validate our supraglacial lake detection algorithm, we randomly created point samples over our classification results and compared them to Sentinel-2 imagery. The point comparisons were evaluated using a confusion matrix for calculation of selected accuracy metrics. Our analysis revealed wide-spread supraglacial lake occurrence in all three Antarctic regions. For the first time, we identified supraglacial meltwater features on Abbott, Hull and Cosgrove Ice Shelves in West Antarctica as well as for the entire Amery Ice Shelf for years 2017-2020. Over Amery Ice Shelf, maximum lake extent varied strongly between the years with the 2019 melt season characterized by the largest areal coverage of supraglacial lakes (~763 km\(^2\)). The accuracy assessment over the test regions revealed an average Kappa coefficient of 0.86 where the largest value of Kappa reached 0.98 over George VI Ice Shelf. Future developments will involve the generation of circum-Antarctic supraglacial lake mapping products as well as their use for further methodological developments using Sentinel-1 SAR data in order to characterize intraannual supraglacial meltwater dynamics also during polar night and independent of meteorological conditions. In summary, the implementation of the Random Forest classifier enabled the development of the first automated mapping method applied to Sentinel-2 data distributed across all three Antarctic regions.},
  language  = {en}
}
@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{MayrKleinRutzingeretal.2021,
  author    = {Mayr, Stefan and Klein, Igor and Rutzinger, Martin and Kuenzer, Claudia},
  title     = {Systematic water fraction estimation for a global and daily surface water time-series},
  series = {Remote Sensing},
  volume    = {13},
  journal   = {Remote Sensing},
  number    = {14},
  issn      = {2072-4292},
  doi       = {10.3390/rs13142675},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-242586},
  year      = {2021},
  abstract  = {Fresh water is a vital natural resource. Earth observation time-series are well suited to monitor corresponding surface dynamics. The DLR-DFD Global WaterPack (GWP) provides daily information on globally distributed inland surface water based on MODIS (Moderate Resolution Imaging Spectroradiometer) images at 250 m spatial resolution. Operating on this spatiotemporal level comes with the drawback of moderate spatial resolution; only coarse pixel-based surface water quantification is possible. To enhance the quantitative capabilities of this dataset, we systematically access subpixel information on fractional water coverage. For this, a linear mixture model is employed, using classification probability and pure pixel reference information. Classification probability is derived from relative datapoint (pixel) locations in feature space. Pure water and non-water reference pixels are located by combining spatial and temporal information inherent to the time-series. Subsequently, the model is evaluated for different input sets to determine the optimal configuration for global processing and pixel coverage types. The performance of resulting water fraction estimates is evaluated on the pixel level in 32 regions of interest across the globe, by comparison to higher resolution reference data (Sentinel-2, Landsat 8). Results show that water fraction information is able to improve the product's performance regarding mixed water/non-water pixels by an average of 11.6\% (RMSE). With a Nash-Sutcliffe efficiency of 0.61, the model shows good overall performance. The approach enables the systematic provision of water fraction estimates on a global and daily scale, using only the reflectance and temporal information contained in the input time-series.},
  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{HoeserBachoferKuenzer2020,
  author    = {Hoeser, Thorsten and Bachofer, Felix and Kuenzer, Claudia},
  title     = {Object detection and image segmentation with deep learning on Earth Observation data: a review — part II: applications},
  series = {Remote Sensing},
  volume    = {12},
  journal   = {Remote Sensing},
  number    = {18},
  issn      = {2072-4292},
  doi       = {10.3390/rs12183053},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-213152},
  year      = {2020},
  abstract  = {In Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes. The increase in data with a very high spatial resolution enables investigations on a fine-grained feature level which can help us to better understand the dynamics of land surfaces by taking object dynamics into account. To extract fine-grained features and objects, the most popular deep-learning model for image analysis is commonly used: the convolutional neural network (CNN). In this review, we provide a comprehensive overview of the impact of deep learning on EO applications by reviewing 429 studies on image segmentation and object detection with CNNs. We extensively examine the spatial distribution of study sites, employed sensors, used datasets and CNN architectures, and give a thorough overview of applications in EO which used CNNs. Our main finding is that CNNs are in an advanced transition phase from computer vision to EO. Upon this, we argue that in the near future, investigations which analyze object dynamics with CNNs will have a significant impact on EO research. With a focus on EO applications in this Part II, we complete the methodological review provided in Part I.},
  language  = {en}
}
@article{HoeserKuenzer2020,
  author    = {Hoeser, Thorsten and Kuenzer, Claudia},
  title     = {Object detection and image segmentation with deep learning on Earth observation data: a review-part I: evolution and recent trends},
  series = {Remote Sensing},
  volume    = {12},
  journal   = {Remote Sensing},
  number    = {10},
  issn      = {2072-4292},
  doi       = {10.3390/rs12101667},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-205918},
  year      = {2020},
  abstract  = {Deep learning (DL) has great influence on large parts of science and increasingly established itself as an adaptive method for new challenges in the field of Earth observation (EO). Nevertheless, the entry barriers for EO researchers are high due to the dense and rapidly developing field mainly driven by advances in computer vision (CV). To lower the barriers for researchers in EO, this review gives an overview of the evolution of DL with a focus on image segmentation and object detection in convolutional neural networks (CNN). The survey starts in 2012, when a CNN set new standards in image recognition, and lasts until late 2019. Thereby, we highlight the connections between the most important CNN architectures and cornerstones coming from CV in order to alleviate the evaluation of modern DL models. Furthermore, we briefly outline the evolution of the most popular DL frameworks and provide a summary of datasets in EO. By discussing well performing DL architectures on these datasets as well as reflecting on advances made in CV and their impact on future research in EO, we narrow the gap between the reviewed, theoretical concepts from CV and practical application in EO.},
  language  = {en}
}