Search Results (6)

The classification of maritime boats and ship targets using optical satellite imagery is a challenging subject. This research introduces a unique and rich ship dataset named Very High-Resolution Ships (VHRShips) from Google Earth images, which includes diverse ship types, different ship sizes, several inshore locations, and different data acquisition conditions to improve the scalability of ship detection and mapping applications. In addition, we proposed a deep learning-based multi-stage approach for ship type classification from very high resolution satellite images to evaluate the performance of the VHRShips dataset. Our “Hierarchical Design (HieD)” approach is an end-to-end structure that allows the optimization of the Detection, Localization, Recognition, and Identification (DLRI) stages, independently. We focused on sixteen parent ship classes for the DLR stages, and specifically considered eight child classes of the navy parent class at the identification stage. We used the Xception network in the DRI stages and implemented YOLOv4 for the localization stage. Individual optimization of each stage resulted in F1 scores of 99.17%, 94.20%, 84.08%, and 82.13% for detection, recognition, localization, and identification, respectively. The end-to-end implementation of our proposed approach resulted in F1 scores of 99.17%, 93.43%, 74.00%, and 57.05% for the same order. In comparison, end-to-end YOLOv4 yielded F1-scores of 99.17%, 86.59%, 68.87%, and 56.28% for DLRI, respectively. We achieved higher performance with HieD than YOLOv4 for localization, recognition, and identification stages, indicating the usability of the VHRShips dataset in different detection and classification models. In addition, the proposed method and dataset can be used as a benchmark for further studies to apply deep learning on large-scale geodata to boost GeoAI applications in the maritime domain. Full article

The Environmental Data Portal EnviDat aims to fuse data publication repository functionalities with next-generation web-based environmental geospatial information systems (web-EGIS) and Earth Observation (EO) data cube functionalities. User requirements related to mapping and visualization represent a major challenge for current environmental data portals. The new Cloud Optimized Raster Encoding (CORE) format enables an efficient storage and management of gridded data by applying video encoding algorithms. Inspired by the cloud optimized GeoTIFF (COG) format, the design of CORE is based on the same principles that enable efficient workflows on the cloud, addressing web-EGIS visualization challenges for large environmental time series in geosciences. CORE is a web-native streamable format that can compactly contain raster imagery as a data hypercube. It enables simultaneous exchange, preservation, and fast visualization of time series raster data in environmental repositories. The CORE format specifications are open source and can be used by other platforms to manage and visualize large environmental time series. Full article

The analysis of the geoecological state of basin geosystems was carried out by evaluation of the anthropogenic pressure on the basin. As indicators that directly or indirectly reflect the anthropogenic impact, the following were used: population density in the basin, density of the road network, and agricultural development of the basin territory. The spatial and statistical distributions of indicators were analyzed after the indicators were brought to a unified scale (transformation, normalization). The integral indicator of anthropogenic pressure, calculated as a linear combination of individual variables, was ranked to six categories of anthropogenic pressure: “absent”, “very low”, “low”, “moderate”, “high”, and “very high”. Using the developed methodology and prepared geodata, for the first time at scale of 1:200,000, the territory of the Volga Federal District was zoned according to the anthropogenic pressure on each river basin. Basins with a high and very high pressure are concentrated around large cities. Most of the basins belonging to the categories of low and moderate anthropogenic pressure are located in the forest-steppe and steppe zones with maximal agricultural development. Basins with zero and very low pressure lie in the north of the study area, in the forest zone, and in the southern Ural. Full article

Water areas occupy over 70 percent of the Earth’s surface and are constantly subject to research and analysis. Often, hydrographic remote sensors are used for such research, which allow for the collection of information on the shape of the water area bottom and the objects located on it. Information about the quality and reliability of the depth data is important, especially during coastal modelling. In-shore areas are liable to continuous transformations and they must be monitored and analyzed. Presently, bathymetric geodata are usually collected via modern hydrographic systems and comprise very large data point sequences that must then be connected using long and laborious processing sequences including reduction. As existing bathymetric data reduction methods utilize interpolated values, there is a clear requirement to search for new solutions. Considering the accuracy of bathymetric maps, a new method is presented here that allows real geodata to be maintained, specifically position and depth. This study presents a description of a developed method for reducing geodata while maintaining true survey values. Full article

Knowledge of the German building stock is largely based on census data and annual construction statistics. Despite the wide range of statistical data, they are constrained in terms of temporal, thematic and spatial resolution, and hence do not satisfy all requirements of spatial planning and research. In this paper, we describe a new workflow for data integration that allows the quantification of the structure and dynamic of national building stocks by analyzing authoritative geodata. The proposed workflow has been developed, tested and demonstrated exemplarily for the whole country of Germany. We use nationwide and commonly available authoritative geodata products such as building footprint and address data derived from the real estate cadaster and land use information from the digital landscape model. The processing steps are (1) data preprocessing; (2) the calculation of building attributes; (3) semantic enrichment of the building using a classification tree; (4) the intersection with spatial units; and finally (5) the quantification and cartographic visualization of the building structure and dynamic. Applying the workflow to German authoritative geodata, it was possible to describe the entire building stock by 48 million polygons at different scale levels. Approximately one third of the total building stock are outbuildings. The methodological approach reveals that 62% of residential buildings are detached, 80% semi-detached and 20% terraced houses. The approach and the novel database will be very valuable for urban and energy modeling, material flow analysis, risk assessment and facility management. Full article

Among the machine learning tools being used in recent years for environmental applications such as forestry, self-organizing maps (SOM) and the k-nearest neighbor (kNN) algorithm have been used successfully. We applied both methods for the mapping of organic carbon (C_org) in riparian forests due to their considerably high carbon storage capacity. Despite the importance of floodplains for carbon sequestration, a sufficient scientific foundation for creating large-scale maps showing the spatial C_org distribution is still missing. We estimated organic carbon in a test site in the Danube Floodplain based on RapidEye remote sensing data and additional geodata. Accordingly, carbon distribution maps of vegetation, soil, and total C_org stocks were derived. Results were compared and statistically evaluated with terrestrial survey data for outcomes with pure remote sensing data and for the combination with additional geodata using bias and the Root Mean Square Error (RMSE). Results show that SOM and kNN approaches enable us to reproduce spatial patterns of riparian forest C_org stocks. While vegetation C_org has very high RMSEs, outcomes for soil and total C_org stocks are less biased with a lower RMSE, especially when remote sensing and additional geodata are conjointly applied. SOMs show similar percentages of RMSE to kNN estimations. Full article