Ron Hagensieker’s research while affiliated with Freie Universität Berlin and other places

In recent years, the concept of Local Climate Zones (LCZs) has become a new standard in the research of urban landscapes. LCZs outline a classification scheme, which is designed to categorize urban and rural surfaces according to their climate-relevant properties, irrespective of local building materials or cultural background. We present a novel workflow for a high-resolution derivation of LCZs using multi-temporal Sentinel 2 (S2) composites and supervised Convolutional Neural Networks (CNNs). We assume that CNNs, due to their potential invariance to size and illumination of objects, are best suited to predict the highly context-based LCZs on a large scale. As a first step, the proposed workflow includes a fully automated generation of cloud-free S2 composites. These composites serve as training data basis for the LCZ classifications carried out over eight German cities. Results show that by using a CNN, overall accuracies can be increased by an average of 16.5 and 4.8 percentage points when compared to a pixel-based and a texture-based Random Forest approach, respectively. If sufficient training data is available, CNN models proved to be robust in classifying unknown cities and achieved overall accuracies of up to 86.5%. The proposed method constitutes a feasible approach for automated, large scale mapping of LCZs, and could be the preferred alternative for LCZ classifications in upcoming studies.

Deforestation in the Amazon has important implications for biodiversity and climate change. However, land cover monitoring in this tropical forest is a challenge because it covers such a large area and the land cover change often occurs quickly, and sometimes cyclically. Here we adapt a method which eliminates the need to collect new training data samples for each update of an existing land cover map. We use the state-of-the-art probabilistic classifier Import Vector Machines and Landsat 8 Operational Land Imager (OLI) scenes of the area surrounding Novo Progresso, northern Brazil, to create an initial land cover map for 2013 with associated classification probabilities. We then conduct spectral change detection between 2013 and 2015 using a pair of Landsat images in order to identify the areas where land cover has changed between the two dates, and then reclassify these areas using a supervised classification algorithm, using pixels from the unchanged areas of the map as training data. In this study, we use the pixels with the highest classification probabilities to train the classifier for 2015 and compare the results to those obtained when pixels are chosen randomly. The use of probabilities in the selection of training samples improves the results compared to a random selection, with the highest overall accuracy achieved when 250 training samples with high probabilities are used. For training sample sizes greater than 1000, the differences in overall accuracy between the two approaches to training sample selection are reduced. The final updated 2015 map has an overall accuracy of 80.1%, compared to an overall accuracy of 82.5% for the 2013 map. The results show that this probabilistic method has potential to efficiently map the dynamic land cover change in the Amazon with limited training data, although some challenges remain.

Earth Observation (EO) data plays a major role in supporting surveying compliance of several multilateral environmental treaties, such as UN-REDD+ (United Nations Reducing Emissions from Deforestation and Degradation). In this context, land cover maps of remote sensing data are the most commonly used EO products and development of adequate classification strategies is an ongoing research topic. However, the availability of meaningful multispectral data sets can be limited due to cloud cover, particularly in the tropics. In such regions, the use of SAR systems (Synthetic Aperture Radar), which are nearly independent form weather conditions, is particularly promising. With an ever-growing number of SAR satellites, as well as the increasing accessibility of SAR data, potentials for multi-frequency remote sensing are becoming numerous. In our study, we evaluate the synergistic contribution of multitemporal L-, C-, and X-band data to tropical land cover mapping. We compare classification outcomes of ALOS-2, RADARSAT-2, and TerraSAR-X datasets for a study site in the Brazilian Amazon using a wrapper approach. After preprocessing and calculation of GLCM texture (Grey Level Co-Occurence), the wrapper utilizes Random Forest classifications to estimate scene importance. Comparing the contribution of different wavelengths, ALOS-2 data perform best in terms of overall classification accuracy, while the classification of TerraSAR-X data yields higher accuracies when compared to the results achieved by RADARSAT-2. Moreover, the wrapper underlines potentials of multi-frequency classification as integration of multi-frequency images is always preferred over multi-temporal, mono-frequent composites. We conclude that, despite distinct advantages of certain sensors, for land cover classification, multi-sensoral integration is beneficial.

Remote sensing satellite data offer the unique possibility to map land use land cover transformations by providing spatially explicit information. However, detection of short-term processes and land use patterns of high spatial-temporal variability is a challenging task. We present a novel framework using multi-temporal TerraSAR-X data and machine learning techniques, namely Discriminative Markov Random Fields with spatio-temporal priors, and Import Vector Machines, in order to advance the mapping of land cover characterized by short-term changes. Our study region covers a current deforestation frontier in the Brazilian state Par\'{a} with land cover dominated by primary forests, different types of pasture land and secondary vegetation, and land use dominated by short-term processes such as slash-and-burn activities. The data set comprises multi-temporal TerraSAR-X imagery acquired over the course of the 2014 dry season, as well as optical data (RapidEye, Landsat) for reference. Results show that land use land cover is reliably mapped, resulting in spatially adjusted overall accuracies of up to $79\%$ in a five class setting, yet limitations for the differentiation of different pasture types remain. The proposed method is applicable on multi-temporal data sets, and constitutes a feasible approach to map land use land cover in regions that are affected by high-frequent temporal changes.

Remote sensing satellite data offer the unique possibility to map land use land cover transformations by providing spatially explicit information. However, detection of short-term processes and land use patterns of high spatial-temporal variability is a challenging task. We present a novel framework using multi-temporal TerraSAR-X data and machine learning techniques, namely Discriminative Markov Random Fields with spatio-temporal priors, and Import Vector Machines, in order to advance the mapping of land cover characterized by short-term changes. Our study region covers a current deforestation frontier in the Brazilian state Par\'{a} with land cover dominated by primary forests, different types of pasture land and secondary vegetation, and land use dominated by short-term processes such as slash-and-burn activities. The data set comprises multi-temporal TerraSAR-X imagery acquired over the course of the 2014 dry season, as well as optical data (RapidEye, Landsat) for reference. Results show that land use land cover is reliably mapped, resulting in spatially adjusted overall accuracies of up to $79\%$ in a five class setting, yet limitations for the differentiation of different pasture types remain. The proposed method is applicable on multi-temporal data sets, and constitutes a feasible approach to map land use land cover in regions that are affected by high-frequent temporal changes.

Hyperspectral remote sensing data offer the opportunity to map urban characteristics in detail. Though, adequate algorithms need to cope with increasing data dimensionality, high redundancy between individual bands, and often spectrally complex urban landscapes. The study focuses on subpixel quantification of urban land cover compositions using simulated environmental mapping and analysis program (EnMAP) data acquired over the city of Berlin, utilizing both machine learning regression and classification algorithms, i.e., multioutput support vector regression (MSVR), standard support vector regression (SVR), import vector machine classifier (IVM), and support vector classifier (SVC). The experimental setup incorporates a spectral library and a reference land cover fraction map used for validation purposes. The library spectra were synthetically mixed to derive quantitative training data for the classes vegetation, impervious surface, soil, and water. MSVR and SVR models were trained directly using the synthetic mixtures. For IVM and SVC, a modified hyperparameter selection approach is conducted to improve the description of urban land cover fractions by means of probability outputs. Validation results demonstrate the high potential of the MSVR for subpixel mapping in the urban context. MSVR outperforms SVR in terms of both accuracy and computational time. IVM and SVC work similarly well, yet with lower accuracies of subpixel fraction estimates compared to both regression approaches.

Clouds cover is one of the main constraints in the field of optical remote sensing. Especially the use of multispectral imagery is affected by either fully obscured data or parts of the image which remain unusable. This study compares four algorithms for the filling of cloud induced gaps in classified land cover products based on Markov Random Fields (MRF), Random Forest (RF), Closest Spectral Fit (CSF) operators. They are tested on a classified image of Sentinel-2 where artificial clouds are filled by information derived from a scene of Sentinel-1. The approaches rely on different mathematical principles and therefore produced results varying in both pattern and quality. Overall accuracies for the filled areas range from 57 to 64 %. Best results are achieved by CSF, however some classes (e.g. sands and grassland) remain critical through all approaches.

This study deals with the historical impacts of mining as a result of the economic development in Eastern Asia. It focuses on landscape changes caused by the emerging copper mining industry in China's south east provinces. Since the ecological aftermath has never been documented in Chinese history, a reconstruction of dynamic landscape processes is performed. A key region for this reconstruction are the mining areas in Yunnan province. This province was the most important supplying region of copper in China during the early and mid Qing dynasty (1725-1855).