. . "5.0" . "140.0" . "10.0" . . . . . . "F2F" . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . "6.0" . "3.0" . "Both hazard types and frequency, as well as built-up areas and cities are dynamically changing, resulting from climate and global changes. In April 2024, displacing 600.000 people in Brazil due to floods, having hottest day records already in Europe and in Asia are clear examples to the shifting hazard patterns. In such dynamic environments, the interdependency among the risk components amplifies the impact of disasters. In such an environment, disaster risk is constantly changing, and there is a definite limit to our capacity to foresee the failures resulting from unexpected interactions between interdependent components. Indeed, the intensity and extent of the challenges make clear that achieving resilient cities is everybody’s business. Scientists, stakeholders and citizens are faced with the challenge to adapt their disaster risk reduction plans but lack the understanding and tools to account for the cross-sectoral impacts and dynamic nature of the risks involved. In this course, we follow the socio-technical approach in complex city systems and investigate the ways to contribute to cities’ resilience. The main problem in disaster risk management is providing static measures to a dynamically changing system. In this course you will learn looking at the nature of risk as a 'dynamic' concept rather than a static one. You will focus on multi-hazard risk assessment and dynamic risk reduction measures on various sectors."@en . "Planning for Resilient Cities"@en . . "Planning for Resilient Cities"@en . "Planning for Resilient Cities"@en . . "5.0" . "140.0" . "10.0" . . . . . "f2f / blended / online " . . . . . . . . . . . . . . . "Foundation Courses, introduction to Urban Land Futures, Data sharing, Data engineering"@en . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . "4.0" . "3.0" . "Land administration has long been executed through state-based agencies such as cadastral departments,\nland registry offices, ministries of land, or local governments with their own analogue or digital data\nrepositories. These organizations do not act in a vacuum but within larger institutional fields and forces.\nThe broader environment of land governance, in which public organizations operate, is characterized by\nthe interactions of multiple state and non-state actors, formal and informal practices, a multitude of\nregulatory frameworks and increasing global interconnectivity. This environment has been witnessing\npublic sector reforms and increased adoption of (geo)Information and Communication Technologies (ICT),\nincluding automatization techniques, mobile device-generated data, crowdsourcing and advanced remote\nsensing technologies. In many places, more established forms of organizing meet the latest technological\ndevelopments. While some organizations are beginning to digitize paper-based workflows, others may\nfunction through highly automated and digitized processes. At the same time, information technologies and\ndigital data are not merely neutral tools, but they reflect, transport and transform the practices and values\nof organizations and institutional fields.\nIt is important therefore to understand and learn how to describe, explain, and assess organizational\nchange in response to changing environments, (geo-)ICT implementation using workflows and related\nforms of data sharing, uses and dissemination."@en . "Land Information in Practice"@en . . "Land Information in Practice"@en . "Land Information in Practice"@en . . "5.0" . "140.0" . "10.0" . . . . . . "F2F" . . . . . . . . . . . . . . . . "Machine Learning for Geosciences or equivalent"@en . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . "4.0" . "4.0" . "CONCEPT (not yet confirmed by all GEO-AI staff):\nBuilding on the foundations laid in the Machine Learning for Geospatial Sciences course, this advanced program delves into the forefront of machine learning and deep learning technologies tailored for geospatial applications. Here, you will explore sophisticated models and techniques that enable the analysis of both spatial and spatio-temporal data, addressing complex real-world challenges with precision and insight.\nThe course begins with an in-depth exploration of advanced machine learning algorithms, designed to handle the unique complexities of geospatial data. You will learn to apply these algorithms to model intricate spatial patterns and relationships, enhancing your ability to derive meaningful insights from diverse geospatial datasets.\nDeep learning algorithms, known for their capacity to process large and complex datasets, will be a significant focus. You will master techniques for analyzing geospatial imagery, recognizing patterns, and making accurate predictions. Algorithms like Recurrent NN, Transformers and Graph NN empower you to extract detailed and valuable information from high-resolution and divers geospatial data.\nHandling spatio-temporal data requires specialized approaches. You will learn advanced methods for analyzing time series data, predicting temporal changes in geospatial phenomena, and help understanding the dynamics of processes such as weather patterns, urban growth, and environmental shifts.\nState-of-the-art architectures and methods will be introduced, highlighting their remarkable ability to capture and model complex dependencies in data. You will explore their application in geospatial sciences, particularly in tasks requiring attention mechanisms to focus on relevant spatial regions or temporal sequences.\nAn important component of this course is Explainable AI (XAI), ensuring transparency and interpretability of your models. You will learn techniques to make complex models understandable, fostering trust and facilitating informed decision-making in geospatial applications. We will discuss the ethical implications of AI in geospatial sciences, emphasizing the importance of responsible data use, privacy concerns, and the societal impact of AI-driven decisions.\nBy the end of this course, you will be proficient in leveraging advanced machine learning and deep learning techniques for geospatial sciences, equipped to tackle sophisticated spatial and spatio-temporal challenges ethically and transparently. Join us to advance your expertise and contribute to the transformative power of AI in geospatial sciences!"@en . "Advanced Machine Learning for Geospatial Sciences"@en . . "Advanced Machine Learning for Geospatial Sciences"@en . "Advanced Machine Learning for Geospatial Sciences"@en . . "5.0" . "140.0" . "10.0" . . . . . . . . . . . . . . "MGEO - foundation course"@en . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . "5.0" . "4.0" . "Fieldwork is often an essential component to acquire reference data for calibration and validation of the remotely sensed observations. This course provides skills and techniques to plan, execute and report on field observations. The course starts with an introduction to in-situ field measurement devices and lab equipment, and demonstrates standard operational procedures when analysing samples in the laboratory. Subsequently, students have to design their own field data collection based on a self-defined objective, e.g. which parameters are required and how to conduct sampling, which instruments are required, how to measure, sampling procedures and storing of samples. Considering focus group interviews how to prepare the questionnaires and review of ethical considerations. Another element would be the timing related to eventual satellite overpass or image acquisition in the terrain and collection of available information from installed in-situ measuring devices. \n\nBeing well prepared, a 3 day fieldwork is envisaged for practical collecting data in a fieldwork area with participants from multiple disciplines: water, natural and earth resources. \n\nOnce back, the data collected has to be analysed in the lab or subject to further processing. In the end, students are required to present their results obtained and have to report on the procedures applied, reflect on the quality of obtained results, and describe their analysis conducted into more detail. "@en . "Lab & Field Work Skills (LiLa and GSL)"@en . . "Lab & Field Work Skills (LiLa and GSL)"@en . "Lab & Field Work Skills (LiLa and GSL)"@en . . "5.0" . "140.0" . "10.0" . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . "4.0" . "3.0" . "[CONCEPT] Monitoring of physical and chemical atmospheric, land and ocean variables with remote sensing requires an understanding of Earth’s ecosystems. Understanding of systems can be based on expert knowledge, experimental relations or physical relations, and this understanding can be captured in a descriptive model. Models are to understand, detect, predict, and describe interactions within and between ecosystems and the atmosphere across scales that range from local to global.\n\nRemote sensing can be used for parameter input in models, but also for spatial and temporal interpolation or extrapolation. This course provides an introduction to knowledge-driven, data-driven and physical modelling, starting with appropriate model selection given a specific problem or data availability. The course therefore deals with basic concepts and boundary conditions. Much emphasis is on integration of remote sensing observations into models, and selecting optimal object / pixel / time based mapping method for a given problem "@en . "Modeling & Mapping"@en . . "Modeling & Mapping"@en . "Modeling & Mapping"@en . . "5.0" . "140.0" . "10.0" . . . . . . . . . . . . . . . . "Q2 (QRS) and preferably Q3 - Modelling and Mapping / open for second year as elective"@en . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . "4.0" . "3.0" . "[CONCEPT] The earth surface is a dynamic environment that constantly undergoes change. Various process interact at various time scales, ranging from minutes in atmospheric processes to days in land processes and even millions of years in geological processes. Monitoring of natural resources therefore deals with monitoring of a changing earth surface cover. Even when observing geological processes, the observational environment still changes by the minute. \n\nIn this course, remote sensing is applied for monitoring changes in land cover and land use, covering both system drivers (e.g., changes in land use) and response variables. Attention is given to linking the physical world with ethical and social considerations, environment and social aspects of technology, consulting different stakeholders in the management of the resources. "@en . "Impact monitoring and management"@en . . "Impact monitoring and management"@en . "Impact monitoring and management"@en . . . . . . . . . . . . "Presentation of field analysis results"@en . "Lab & Field Work Skills (LiLa and GSL): LU5"@en . . . . . . . . "SWOT (Practical)"@en . "Land Information in Practice: LU6"@en . . . . . . . "Final presentation"@en . "Planning for Resilient Cities: LU10"@en . . . . . . . "Literature Review "@en . "Land Information in Practice: LU5"@en . . . . . . . . . . "Optimal modelbased mapping"@en . "Modeling & Mapping: LU5"@en . . . . . . "Assignment"@en . "Advanced Machine Learning for Geospatial Sciences: LU10"@en . . . . . . . "Communication to different stakeholders"@en . "Impact monitoring and management: LU5"@en . . . . "MGEO 5.0 BoK"@en . . "presentation"