Archaeological excavations play a major role in gaining knowledge about prehistoric landscapes and ways of living. However, archaeological excavations are destructive acts and very resource intensive, so they cannot be performed in every area of interest. Therefore prospection methods have been developed, where feedbacks of e.g. lidar, radar or magnetic sensors are utilized to get an overview of the distribution, extent and complexity of underground structures in larger areas. After automated pre-processing of the sensor data arrays (and images) of these, grid data is provided as an input for exploration, analysis and annotation using geographic information system tools like QGIS. Annotating the images has been a fully manual task, performed by domain scientists. In this work we demonstrate a tool that supports domain scientists through automated annotation prediction. The implementation is integrated in the prevalent scientific workflow using available input and required output formats. The implementation is based on a pre-trained Rotated Retina Net. The manually annotated data of underground house remains from one of three archaeological sites is then used to pre-process and augment a feasible amount of training data for this specific task. One challenge was that global normalization of pixel values in the images did not yield useful results, because of modern infrastructure (such as utility pipes) distorting the magnetic feedback. A separated portion of the annotated data has been used for a quantitative evaluation of model performance. The system has also been applied to two additional, formerly unseen and non-annotated datasets where predicted annotations were found to be valuable for domain scientists. The system's output data can be used in GIS tools to edit annotations by experts, explore the sites, identify promising excavation sites and perform e.g. cluster analysis on house sizes and other features.

Mining spatio-temporal correlation patterns for traffic prediction is a well-studied field. However, most approaches are based on the assumption of the availability of and accessibility to a sufficiently dense data source, which is rather the rare case in reality. Traffic sensors in road networks are generally highly sparse in their distribution: fleet-based traffic sensing is sparse in space but also sparse in time. There are also other traffic application, besides road traffic, like moving objects in the marine space, where observations are sparsely and arbitrarily distributed in space. In this paper, we tackle the problem of traffic prediction on sparse and spatially irregular and non-deterministic traffic observations. We draw a border between imputations and this work as we consider high sparsity rates and no fixed sensor locations. We advance correlation mining methods with a Sparse Unstructured Spatio Temporal Reconstruction (SUSTeR) framework that reconstructs traffic states from sparse non-stationary observations. For the prediction the framework creates a hidden context traffic state which is enriched in a residual fashion with each observation. Such an assimilated hidden traffic state can be used by existing traffic prediction methods to predict future traffic states. We query these states with query locations from the spatial domain.

Research papers are often the primary source of scientific information dissemination, as researchers encapsulate their findings in these documents. Generally such findings are of complex types, diverse expressions and also carry rich context. The traditional approach for extracting certain scientific information from these documents is manual extraction, which is very time consuming. Due to the rapid increase in number of publications, using the full potential of these rich data sources by manual extraction is becoming infeasible. In this paper, we propose a framework for the automatic extraction of targeted (user defined) quantitative information, e.g. temperature sensor values, with its geo-spatial context from scientific documents. Given a database of scientific documents and a targeted user-defined geo-tagable measurement variables, mass accumulation rate (MAR) and sedimentation rate (SR), the problem we are addressing is to retrieve all the values together with their geo-spatial information respectively. Though there has been done a lot in information retrieval, to the best of our knowledge, this problem has not been explored, yet. We design a novel heterogeneous linking solution, that links measurements with locations, which are found by our tailored extraction pipeline. In experimental studies based on our novel dataset of Marine Geology papers, we showcase the capabilities of our linking framework using common geo-tagable Marine Geology measurements.

Damage detection in materials and structures plays a critical role in engineering and science applications like structural health monitoring. A particular challenge is presented by micro-scale cracks, which are imperceptible to the naked eye or in images, but may ultimately evolve into larger, potentially dangerous cracks. In this work, we propose spatio-temporal pattern recognition techniques to enable the detection of such imperceptible micro-cracks. In order to make these cracks detectable, we generate seismic waves on the surface area of interest and monitor how cracks interfere with the spatial propagation of the wave over time. On the resulting propagation image series we then apply segmentation techniques using deep encoder-decoder CNNs to predict the location of cracks, which otherwise could not be directly observed. Our solution is evaluated through extensive experiments on highly-realistic finite element simulations, which were developed by domain experts.

Quantitative information derived from scientific documents provides an important source of data for studies in almost all domains, however, manual extraction of this information is very time consuming. In this paper we will introduce a system Geo-Quantities that supports the automatic extraction of quantitative, spatial and temporal information of a given measurement entity from scientific literature using text mining techniques. The difficulty of automatic measurement recognition is mainly caused by the diverse expressions in the papers. Geo-Quantities offers an interactive interface for the visualization of extracted user-defined information, in particular spatial and temporal context. In our demonstration, we will showcase the capabilities of our system by retrieving measurements such as “mass accumulation rates” and “sedimentation rates” from scientific publications in the field of marine geology, which could have high impact in studies for building global mass accumulation rate maps. For training and evaluation of Geo-Quantities we use a corpus of domain-relevant papers.