Information about clouds is important for observing and predicting weather and climate as well as for generating and distributing solar power. Most existing approaches extract cloud information from satellite data by classifying individual pixels instead of using closely integrated spatial information, ignoring the fact that clouds are highly dynamic, spatially continuous entities. This paper proposes a novel cloud classification method based on deep learning. Relying on a Convolutional Neural Network (CNN) architecture for image segmentation, the presented Cloud Segmentation CNN (CS-CNN), classifies all pixels of a scene simultaneously rather than individually. We show that CS-CNN can successfully process multispectral satellite data to classify continuous phenomena such as highly dynamic clouds. The proposed approach produces excellent results on Meteosat Second Generation (MSG) satellite data in terms of quality, robustness, and runtime compared to other machine learning methods such as random forests. In particular, comparing CS-CNN with the CLAAS-2 cloud mask derived from MSG data shows high accuracy (0.94) and Heidke Skill Score (0.90) values. In contrast to a random forest, CS-CNN produces robust results and is insensitive to challenges created by coast lines and bright (sand) surface areas. Using GPU acceleration, CS-CNN requires only 25 ms of computation time for classification of images of Europe with $508\times 508$ pixels.

Data on the distribution of tree species are often requested by forest managers, inventory agencies, foresters as well as private and municipal forest owners. However, the automated detection of tree species based on passive remote sensing data from aerial surveys is still not sufficiently developed to achieve reliable results independent of the phenological stage, time of day, season, tree vitality and prevailing atmospheric conditions. Here, we introduce a novel tree species classification approach based on high resolution RGB image data gathered during automated UAV flights that overcomes these insufficiencies. For the classification task, a computationally lightweight convolutional neural network (CNN) was designed. We show that with the chosen CNN model architecture, average classification accuracies of 92% can be reached independently of the illumination conditions and the phenological stages of four different tree species. We also show that a minimal ground sampling density of 1.6 cm/px is needed for the classification model to be able to make use of the spatial-structural information in the data. Finally, to demonstrate the applicability of the presented approach to derive spatially explicit tree species information, a gridded product is generated that yields an average classification accuracy of 88%.

Fog has a substantial influence on various ecosystems and it impacts economy, traffic systems and human life in many ways. In order to be able to deal with the large number of influence factors, a spatially explicit high-resoluted data set of fog frequency distribution is needed. In this study, a hybrid approach for fog retrieval based on Meteosat Second Generation (MSG) data and ground truth data is presented. The method is based on a random forest (RF) machine learning model that is trained with cloud base altitude (CBA) observations from Meteorological Aviation Routine Weather Reports (METAR) as well as synoptic weather observations (SYNOP). Fog is assumed where the model predicts CBA values below a dynamically derived threshold above the terrain elevation. Cross validation results show good accordance with observation data with a mean absolute error of 298 m in CBA values and an average Heidke Skill Score of 0.58 for fog occurrence. Using this technique, a 10 year fog baseline climatology with a temporal resolution of 15 min was derived for Europe for the period from 2006 to 2015. Spatial and temporal variations in fog frequency are analyzed. Highest average fog occurrences are observed in mountainous regions with maxima in spring and summer. Plains and lowlands show less overall fog occurrence but strong positive anomalies in autumn and winter.

Fog plays a major role in many ecological aspects and it influences human life in various ways. In this study, a temporally highly resolved and spatially explicit analysis of variations in fog occurrence was conducted for Europe and links to general weather conditions were investigated. To this end, a high‐resolution fog product based on Meteosat Second Generation data was developed. Characteristic fog distributions were identified by applying a Self Organizing Map approach to the dataset. It was found that the resulting fog patterns are primarily determined by terrain characteristics. Simultaneous occurrences between these patterns and the predominant general weather situations were analyzed. The results show that the general weather situations can be categorized into three main groups, each responsible for the formation of a different group of fog patterns. Additionally, distinct regional differences could be identified in the diurnal and annual fog frequency cycles and the derived region‐specific frequency variations were used to draw conclusions about the fog types prevailing in these regions.

Coherent wind doppler lidar (CWDL) is a cost-effective way to estimate wind power potential at hub height without the need to build a meteorological tower. However, fog and low stratus (FLS) can have a negative impact on the availability of lidar measurements. Information about such reductions in wind data availability for a prospective lidar deployment site in advance is beneficial in the planning process for a measurement strategy. In this paper, we show that availability reductions by FLS can be estimated by comparing time series of lidar measurements, conducted with WindCubes v1 and v2, with time series of cloud base altitude (CBA) derived from satellite data. This enables us to compute average maps (2006–2017) of estimated availability, including FLS-induced data losses for Germany which can be used for planning purposes. These maps show that the lower mountain ranges and the Alpine regions in Germany often reach the critical data availability threshold of 80% or below. Especially during the winter time special care must be taken when using lidar in southern and central regions of Germany. If only shorter lidar campaigns are planned (3–6 months) the representativeness of weather types should be considered as well, because in individual years and under persistent weather types, lowland areas might also be temporally affected by higher rates of data losses. This is shown by different examples, e.g., during radiation fog under anticyclonic weather types.