Processing of time series of remote sensing data is a challenging goal of today’s and future research. Global Earth observation programmes provide extensive image archives dated back to several decades. Aerial images and LiDAR point clouds are acquired on the national level in two to three years cycles. Specific localities are monitored on regular (hourly, weekly, monthly, yearly) basis for research purposes such as monitoring resistance of plants to droughts, invasive species encroachment, melting of mountainous snow and glaciers, desertification, decrease of biodiversity, deforestation or urbanization. Thus, processing methods of the time series of remote sensing data of different time and spatial scales, the combination of heterogeneous and multi-modal data sources and accuracy assessment of the obtained results are becoming a key part of remote sensing and geo(infor)matics curricula. The project’s objective is to develop a comprehensive research-oriented open e-learning course on time series analysis in remote sensing for environmental monitoring beyond the existing partners’ curricula. The course offers a multidisciplinary approach connecting themes from computer science, geography, and environmental studies. It combines well established and latest technologies of remote sensing (satellite and UAV sensing, multispectral and hyperspectral sensing, 3D point clouds) and methods of artificial intelligence (machine and deep learning) in order to use these technological developments to understand environmental changes and interaction of human activities and environment. It shows how the same environmental phenomenon can be analysed from the perspective of different data sources, scales and time frequencies. Moreover, it increases students’ digital literacy in time series analysis in remote sensing, which comprises the improvement in methodological and practical data handling skills. The students also gain the skills for critical reflection and communication of complex data processing tasks, enabling them for transformative and interdisciplinary research missions. The e-learning course consists of four modules. The first one provides a general overview on methods for time series analysis and the three others focus on specific processing steps connected to different types of data and their use in case studies on environmental monitoring: 1. Methods of Time Series Analysis in Remote Sensing 2. Satellite Multispectral Images Time Series Analysis 3. 3D/4D Geographic Point Cloud Time Series Analysis 4. Airborne Imaging Spectroscopy Time Series Analysis An open e-learning course covering all these perspectives is currently missing in partners curricula. Furthermore, it can be used beyond the geographic applications by other disciplines working with time series of remote sensing data on different spatial scales. Materials and data will be hosted on open repositories which policy is long term data hosting. The primary target group are MSc and PhD students of geoinformatics and geography who specialize in remote sensing for monitoring Earth surface dynamic and changes. The e-learning course is expected to become a part of the curricula at all four partner universities. The course will be also disseminated among potential users from other universities offering education in remote sensing. The secondary target group are MSc and PhD students in the fields related to environmental studies, ecology, or geology and potential users from public and private sectors dealing with applications of remote sensing such as practitioners of national environmental and conservation agencies, research institutes or companies offering services in remote sensing. The number of participants is estimated to be about 80 per year from the four partners universities and at least 100 worldwide. Participants and target groups of the project will benefit from the extended course portfolio in terms of novel, streamlined contents and digital teaching methods as well as internationalisation. It is expected that new research collaborations will evolve from joint teaching activities. Stakeholders from the private sector, public authorities and NGOs are directly involved in the transdisciplinary course development. Stakeholders will benefit from education of their staff and the course will benefit from the application-oriented knowledge from the stakeholders, which shall guarantee a fit-to-use education beyond the academic sector. On the European level, the project gives an example of innovative research-oriented teaching via European collaboration. The output will foster additional courses that can built upon the gained experience as “intellectual infrastructure”. Generating a positive impact on intensifying integrated European collaboration between universities, internationalization of the partners’ study programs, mobility of students and generation an intellectual impact on a sustainable European digital infrastructure for education are expected.
The project “E-learning course on Time Series Analysis in RS for Understanding Human-Environment Interactions (E-TRAINEE)” aimed at developing learning materials on Remote Sensing Time Series (RSTS) analysis suitable for MSc curricula in geography and geoinformatics of the four involved universities and beyond. With a vision of open access and e-learning, the goal was to provide a publicly available course comprising state-of-the-art theory of RSTS analysis while also bringing up-to-date open tools for practical implementation. The course was also intended to attract students and teachers at other universities, and practitioners in related fields that use RS, such as geology, ecology, botany, etc. The modular structure should allow only part of the course to be taken. Including self-evaluation tools (quizzes, solutions to the exercises) should allow a pure e-learning approach but combination with contact teaching is possible and recommended for the MSc level. Designing such a content-rich course would not be manageable without joint expertise and collaborative work. Moreover, building the course on results of research activities of the partner universities should initiate future mobility and cooperation in education and research.
Time Series (TS) analysis is an important topic and tool in Remote Sensing (RS). Its importance rapidly increased during the last decade with open access to various archives of Earth Observation missions, aerial imagery, LiDAR point clouds, or research datasets, together with open tools for data processing, including cloud services. These developments brought new possibilities in RS research but also challenges in education. At the time of the project application (2019), the topic of TS analysis in RS began to be incorporated as an essential part of MSc curricula in geoinformatics, geography, and related disciplines, but learning materials systematically covering this field were rare. During discussions within an on-going collaboration, the four research groups from Charles University, Heidelberg University, University of Innsbruck, and University of Warsaw addressed a common need to create comprehensive learning materials focused on TS in RS from different perspectives while improving digital literacy of students to enhance their skills and competitiveness in their future careers.