Advanced hydrological modeling with machine learning and earth observations
Vortragende/r (Mitwirkende/r) | |
---|---|
Nummer | 0000000938 |
Art | Vorlesung mit integrierten Übungen |
Umfang | 2 SWS |
Semester | Sommersemester 2025 |
Unterrichtssprache | Englisch |
Stellung in Studienplänen | Siehe TUMonline |
Termine | Siehe TUMonline |
- 23.04.2025 11:45-13:15 N3823, Seminarraum
- 23.04.2025 13:15-14:45 N3823, Seminarraum
- 07.05.2025 11:45-13:15 N3823, Seminarraum
- 07.05.2025 13:15-14:45 N3823, Seminarraum
- 14.05.2025 11:45-13:15 N3823, Seminarraum
- 14.05.2025 13:15-14:45 N3823, Seminarraum
- 21.05.2025 11:45-13:15 N3823, Seminarraum
- 21.05.2025 13:15-14:45 N3823, Seminarraum
- 28.05.2025 11:45-13:15 N3823, Seminarraum
- 28.05.2025 13:15-14:45 N3823, Seminarraum
- 04.06.2025 11:45-13:15 N3823, Seminarraum
- 04.06.2025 13:15-14:45 N3823, Seminarraum
Teilnahmekriterien
Siehe TUMonline
Anmerkung: Elective module for the Master students in Environmental Engineering
Anmerkung: Elective module for the Master students in Environmental Engineering
Lernziele
Upon completion of the module, students are able to:
• acquire knowledge of commonly used machine learning models in hydrology.
• gain adequate Python skills for hydrological data analysis and Machine learning API application in hydrology.
• implement GIS toolbox and some programming software such as Python to process various satellite products in the different data formats.
• apply the earth observation products to Machine learning models to perform hydrological modeling.
• compare and evaluate outputs of multiple Machine learning models.
• develop Machine learning model frames for specific cases depending on available data.
• acquire knowledge of commonly used machine learning models in hydrology.
• gain adequate Python skills for hydrological data analysis and Machine learning API application in hydrology.
• implement GIS toolbox and some programming software such as Python to process various satellite products in the different data formats.
• apply the earth observation products to Machine learning models to perform hydrological modeling.
• compare and evaluate outputs of multiple Machine learning models.
• develop Machine learning model frames for specific cases depending on available data.
Beschreibung
This module focuses on the practical joint applications of two important elements (Machine learning and Earth observation) in hydrological modeling domain. In step one, students start with an intensive Python tutorial to gain fundamental skills for further data processing and analysis and machine learning API adaptation and application. In step two, students learn practical skills to process earth observed hydrological data (such as precipitation, vegetation index products, surface temperature products, ET products, and soil moisture products) into required format with well-organized structure with programming. In step three, with the Earth Observation data from step two, the machine learning models including Linear Models, Support Vector Machines, Decision Trees, Ensemble models, and Neural network models will be taught. Regression, Classification, Clustering and Dimensionality reduction will be involved depending on the thematic topic of specific modeling tasks.
Inhaltliche Voraussetzungen
• Basics of programming in Python.
• Basics of GIS.
• Adequate knowledge of hydrology and hydrological modelling (relevant course records).
• Knowledge of Remote Sensing is an asset.
• Basics of GIS.
• Adequate knowledge of hydrology and hydrological modelling (relevant course records).
• Knowledge of Remote Sensing is an asset.
Lehr- und Lernmethoden
The module will be organized in an interactive manner as a lecture with integrated computational hand-on exercises. The lectures’ contents are presented by the lecturer using the digital slides and programming tutorials. During the exercises, the students independently solve practical examples and learn programming skills in Python. The students work in groups (max 3 persons per group) on one compulsory assignment, which tests the achievement of the study goals and competences based on more extensive case studies. A written report by each group is required to be submitted at the end.
Studien-, Prüfungsleistung
The examination consists of a project work. It will verify the learning outcomes of the module, including i) understanding of basic concepts of machine learning in hydrology; ii) python skills to implement codes to process earth observation data, apply machine learning models, and analyze data; iii) systematic ideas to develop a machine learning model frame considering data availability of realistic case studies. The assignment has to be completed by group work (max 3 students per group). Students are expected to demonstrate that they are able to complete the tasks in a team environment by presenting the results together both in written (70% of the grade) and oral (30% of the grade) form. Their contribution to the group work should be properly indicated in the written and the oral presentation of the results. The contribution statement should contain categories including earth observation data processing, machine learning model frame design, coding, data analysis, and report writing.
Empfohlene Literatur
- Nearing, G.S., Kratzert, F., Sampson, A.K., Pelissier, C.S., Klotz, D., Frame, J.M., Prieto, C. and Gupta, H.V., 2021. What role does hydrological science play in the age of machine learning? Water Resources Research, 57(3), p.2020WR028091.
- Capolongo, D., Refice, A., Bocchiola, D., D'Addabbo, A., Vouvalidis, K., Soncini, A., Zingaro, M., Bovenga, F. and Stamatopoulos, L., 2019. Coupling multitemporal remote sensing with geomorphology and hydrological modeling for post flood recovery in the Strymonas dammed river basin (Greece). Science of the Total Environment, 651, p.1958-1968.
- Kopp, M., Tuo, Y. and Disse, M., 2019. Fully automated snow depth measurements from time-lapse images applying a convolutional neural network. Science of The Total Environment, 697, p.134213.
- Xu, T. and Liang, F., 2021. Machine learning for hydrologic sciences: An introductory overview. Wiley Interdisciplinary Reviews: Water, 8(5), p.1533.
- Zounemat-Kermani, M., Batelaan, O., Fadaee, M. and Hinkelmann, R., 2021. Ensemble machine learning paradigms in hydrology: A review. Journal of Hydrology, 598, p.126266.
- Yang, S., Yang, D., Chen, J., Santisirisomboon, J., Lu, W. and Zhao, B., 2020. A physical process and machine learning combined hydrological model for daily streamflow simulations of large watersheds with limited observation data. Journal of Hydrology, 590, p.125206.
- Capolongo, D., Refice, A., Bocchiola, D., D'Addabbo, A., Vouvalidis, K., Soncini, A., Zingaro, M., Bovenga, F. and Stamatopoulos, L., 2019. Coupling multitemporal remote sensing with geomorphology and hydrological modeling for post flood recovery in the Strymonas dammed river basin (Greece). Science of the Total Environment, 651, p.1958-1968.
- Kopp, M., Tuo, Y. and Disse, M., 2019. Fully automated snow depth measurements from time-lapse images applying a convolutional neural network. Science of The Total Environment, 697, p.134213.
- Xu, T. and Liang, F., 2021. Machine learning for hydrologic sciences: An introductory overview. Wiley Interdisciplinary Reviews: Water, 8(5), p.1533.
- Zounemat-Kermani, M., Batelaan, O., Fadaee, M. and Hinkelmann, R., 2021. Ensemble machine learning paradigms in hydrology: A review. Journal of Hydrology, 598, p.126266.
- Yang, S., Yang, D., Chen, J., Santisirisomboon, J., Lu, W. and Zhao, B., 2020. A physical process and machine learning combined hydrological model for daily streamflow simulations of large watersheds with limited observation data. Journal of Hydrology, 590, p.125206.