. . "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 . . . . . . . . "Understand and account for ethical considerations in applying deep learning algorithms in Geoscience use cases"@en . . . . . . . . . . . . . . . . . . "Fieldwork design"@en . "Lab & Field Work Skills (LiLa and GSL): LU2"@en . . . . "MGEO 5.0 BoK"@en . . "ethical considerations"@en .