. . . . "ITC Bok"@en . . "https://ltb.itc.utwente.nl/page/792/concept/152727" . . "Random forest"@en . . . . "https://ltb.itc.utwente.nl/page/792/concept/152878" . . "Support vector machine"@en . . . . "201900064" . "GIP_0001" . "5"^^ . "140"^^ . "10"^^ . "2022-11-10T23:00:00Z"^^ . "f2f" . "online" . "In this course, students will learn the fundamentals of big geodata processing. Then, they will be introduced (via lectures, demos and exercises) to various distributed big data solutions as well as the role of cloud computing. After that, they will work on a real-life problem involving a big geo-dataset. They will work in groups and create the necessary workflows to process the data. This requires programming skills and critical thinking to select the \"best\" algorithm and computational solution.\n\nIn this course, there will also be a strong emphasis on Open Science principles, with a focus on scientific reproducibility and triangulation. Lectures on archiving data and code will be provided too."@en . . . . . . . "Basic Programming skills ,The knowledge gained during the Scientific Geocomputing course is advantageous but not strictly necessary to follow this course. Some self-study material will be provided through Canvas for students that do not follow the Geoinformatics specialisation. You are advised to contact the course coordinator to discuss the materials' relevance for you."@en . . . . . . . . . "3"^^ . "1" . "1A " . . "2022-09-04T22:00:00Z"^^ . "Thanks to the digital, mobile and sensor revolutions, massive amounts of data are becoming available at unprecedented spatial, temporal, and thematic scales. This leads to the practical problem of transforming big geodatasets into actionable information that can support a variety of decision-making processes. In this respect, geodata science workflows are not only key to processing big geospatial datasets but also to sharing the extracted information and knowledge and to ensuring the reproducibility of the results.\n\nTo handle and analyse massive and potentially heterogeneous amounts of spatio-temporal data, scientists need to 1) understand the particular characteristics of big geodata, 2) learn to work with scalable data management and processing systems, and 3) develop scalable and robust data mining and machine learning workflows. Hence, this course presents theories, methods, and techniques to build scalable solutions for handling and analysing big geodata."@en . "Big Geodata Processing"@en . . "Big Geodata Processing"@en . "Big Geodata Processing"@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" . . . . . . . . "F2F" . . . . . . . . . . . . . . . . . . "Statistics, calculus, linear algebra, analytics geometry, programming (Python)"@en . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . "4.0" . "3.0" . "CONCEPT (not yet confirmed by all GEO-AI staff):\nThis course is designed to guide you through the intersection of machine learning and geospatial sciences, providing you with the expertise to address pressing societal and environmental challenges. You will be introduced to the foundations of supervised and unsupervised learning algorithms, exploring their applications in the geospatial domain. You will learn popular learning algorithms to address various inference tasks, such as clustering, regression and classification.\nFrom satellite imagery to GIS datasets you'll master the tools and methodologies required to preprocess, analyze, integrate and visualize them. You will gain the skills needed to extract meaningful patterns and insights from these geospatial datasets.\nFeature extraction and engineering are critical steps in building effective machine learning models. You will explore techniques to transform raw geospatial data into relevant features enabling your models to learn and predict more effectively.\nClustering techniques, for exploratory spatial data analysis, will be introduced to help you to discover hidden structures and trends within geospatial datasets.\nClassification and regression methods like decision trees, random forests, support vector machines and neural networks are pivotal machine learning tasks that you'll apply to a wide array of geospatial problems. Whether it's land use classification, predicting environmental changes, or estimating spatial variables like temperature or population density, you'll develop models that provide precise and actionable insights.\nThroughout the course real-world case studies will demonstrate the transformative impact of machine learning on geospatial sciences. You'll work on projects that tackle contemporary issues such as urban planning, environmental monitoring, and disaster management.\nBy the end of this course, you will be adept at applying machine learning techniques to geospatial sciences."@en . "Machine Learning for Geospatial Sciences"@en . . "Machine Learning for Geospatial Sciences"@en . "Machine Learning for Geospatial Sciences"@en . . "201900065" . "EOS_0003" . "5"^^ . "140"^^ . "10"^^ . "2022-11-10T23:00:00Z"^^ . "f2f" . "Image analysis requires theoretical concepts and practical skills. Lectures will be used to introduce the topics, followed by reading textbook material. Research articles will also be recommended for those students who are interested in learning more about a specific concept, method, algorithm etc. Practical classes will consist of a mixture of demos, individual work following written instructions, and presentations of the outcomes during feedback sessions. In the practical classes, students will work with existing program codes and modify them (to a limited degree). In this way, the students can get insight into the intermediate stages of the image analysis algorithms and make decisions on the outcomes. Furthermore, a reflection on theoretical concepts will be made. In this way, a solid integration of theory and practice will be achieved."@en . . . . . "Programming skills \n\nImage analysis knowledge ,All students in Geoinformatics specialization are accepted. Students following other specializations should have background in programming and image analysis."@en . . . . . . . . . "4"^^ . "1" . "1A " . . . . "2022-09-04T22:00:00Z"^^ . "In this course, the students will be introduced to advanced image analysis methods dedicated to enriching their geo-information problem-solving abilities. Image processing and analysis methods treated in previous courses, such as conventional hard pixel-based classification, do not take into account spatial correlations in images and, therefore, do not completely exploit the information contained in images. In this course, we aim to introduce more specialized image analysis methods. In particular, Support Vector Machine and Random Forest will be taught for multisource classification at the pixel level. Convolutional Neural Networks (CNNs) and Fully Convolutional Neural Networks (FCN) will be introduced for contextual classification. Advantages and challenges related to multi-temporal image analysis will also be discussed. The methods introduced in this course will be applied to real case studies. "@en . "Advanced Image Analysis"@en . . "Advanced Image Analysis"@en . "Advanced Image Analysis"@en . . . . . . . . . . . . . . . . . "Machine Learning for Geosciences 2"@en . "Machine Learning for Geospatial Sciences: LU6"@en . . . . . . . . . . . "Introduction to ML"@en . "Machine Learning for Geospatial Sciences: LU1"@en . . . . . . . . "Introduction to ML"@en . "Machine Learning for Geospatial Sciences: LU2"@en . . . . . . . . . . . "Introduction to ML"@en . "Machine Learning for Geospatial Sciences: LU3"@en . . . . . . . . "Introduction to ML"@en . "Machine Learning for Geospatial Sciences: LU4"@en . "https://ltb.itc.utwente.nl/page/792/concept/152853" . . "Machine learning"@en .