====== Seminar: Computer Science for Environmental Sustainability (CS4ES) ======

Data-driven approaches and computational methods are essential in addressing key environmental challenges such as climate change, biodiversity loss, and pollution control. This course explores the application of computer science concepts, techniques, and tools for advancing environmental sustainability. Students will learn how computational solutions are applied in various environmental domains, including big data analytics, machine learning, and high-performance computing.

===== Key Information =====
|| Contact || [[about:people:julian_kunkel|Julian Kunkel]], [[about:people:michael_bidollahkhani|Michael Bidollahkhani]] ||
|| Location || [[https://meet.academiccloud.de/gl/rooms/mic-pfz-4cj-npu|Virtual]] ||
|| Time || Monday 16:15-17:45 ||
|| Language || English or German (individual presentation) ||
|| Module || M.Inf.1712: Vertiefung Informatik für Umweltverträglichkeit ||
|| SWS || 2 ||
|| Credits || 5 ||
|| Contact time || 28 hours ||
|| Independent study || 122 hours ||

As part of this seminar, students will create a presentation and report revolving around a research topic of their choice in English or German. Students will regularly meet with an assigned supervisor and work towards the presentation and report. The seminar will be offered in two formats: seminar and pro-seminar. The seminar will focus on scientific research, while the pro-seminar emphasizes presentation techniques. Pro-seminar students will attend two additional sessions focused on presentation skills.

The presentation time is 35 minutes (plus discussion).
A short report accompanying the slides is expected (max 15 pages).

Please note that we plan to record sessions (lectures and seminar talks) with the intent of providing the recordings
via BBB to other students but also to publish and link the recordings on YouTube or other interactive platforms for future terms.
If you appear in any of the recordings via voice, camera or screen share, we need your consent to publish the recordings.
See also this {{ :teaching:templates:dataprivacy_student_notice_slide.pdf |Slide}}.


===== Learning Objectives =====

  * Understand and apply computer science concepts to solve environmental sustainability challenges.
  * Compose a research-based presentation covering selected topics related to environmental informatics.
  * Analyze and critique computational tools for environmental problem-solving.
  * Propose innovative solutions for issues like climate change, biodiversity loss, and pollution using computational methods.

===== Topics =====

This is the list of topics we will assign during the first meeting. Each topic is centered around a research paper. Students are expected to study the paper and implement or experimentally evaluate the proposed approach, reproduce selected results, or test the method on additional data. Students are also encouraged to propose their own topics.

  * **AI and Its Environmental Impact**
    * Investigate the direct environmental impact of AI systems, including energy consumption and carbon footprint. Students may reproduce measurements or estimate the environmental cost of training or running models.
    * **References**:    
      * Wu, C. J., et al. (2022). Sustainable AI: Environmental Implications, Challenges, and Opportunities. *Proceedings of Machine Learning and Systems*, 4, 795-813.  
      * https://piktochart.com/blog/carbon-footprint-of-chatgpt/

  * **Satellite-Based Deforestation Detection**
    * Explore machine learning methods that detect deforestation from satellite imagery. Students may reproduce a classification approach or test models on open satellite datasets.
    * **References**:
      * Hansen, M. C., et al. (2013). High-Resolution Global Maps of 21st-Century Forest Cover Change. *Science*, 342(6160), 850–853.
      * https://earthenginepartners.appspot.com/science-2013-global-forest

  * **Deep Learning for Wildlife Monitoring**
    * Investigate how deep learning models detect and classify animals in camera trap images. Students may reproduce a classification pipeline or test pretrained models.
    * **References**:
      * Norouzzadeh, M. S., et al. (2018). Automatically Identifying, Counting, and Describing Wild Animals in Camera-Trap Images with Deep Learning. *PNAS*, 115(25).
      * https://lila.science/datasets/snapshot-serengeti/

  * **Air Pollution Prediction Using Machine Learning**
    * Study machine learning approaches for predicting air pollution levels from environmental and meteorological data. Students may reproduce regression models and evaluate prediction accuracy.
    * **References**:
      * Zheng, Y., et al. (2015). Forecasting Fine-Grained Air Quality Based on Big Data. *Proceedings of KDD*.
      * https://genxp-2506.github.io/datasets/beijing/

  * **Urban Heat Island Detection with Remote Sensing**
    * Analyze urban heat island effects using satellite data. Students may reproduce analysis using open datasets and implement temperature estimation or spatial analysis.
    * **References**:
      * Voogt, J., & Oke, T. (2003). Thermal Remote Sensing of Urban Climates. *Remote Sensing of Environment*.
      * https://developers.google.com/earth-engine/datasets

  * **Machine Learning for Renewable Energy Forecasting**
    * Investigate methods for predicting solar or wind energy production using machine learning models. Students may implement forecasting models and evaluate performance.
    * **References**:
      * Voyant, C., et al. (2017). Machine Learning Methods for Solar Radiation Forecasting: A Review. *Renewable Energy*.
      * https://www.nrel.gov/grid/solar-power-data.html

  * **Flood Detection from Satellite Images**
    * Study computer vision approaches for detecting floods from satellite imagery. Students may implement a segmentation or classification model and test it on open datasets.
    * **References**:
      * Bonafilia, D., et al. (2020). Sen1Floods11: A Georeferenced Dataset for Flood Detection in SAR Images. *CVPR Workshops*.
      * https://github.com/cloudtostreet/Sen1Floods11

  * **Estimating Carbon Emissions with Data Analysis**
    * Explore computational methods to estimate carbon emissions using large datasets. Students may analyze emissions datasets and build predictive or analytical models.
    * **References**:
      * Andrew, R. M. (2020). Global CO₂ Emissions from Cement Production. *Earth System Science Data*.
      * https://ourworldindata.org/co2-and-greenhouse-gas-emissions

  * **Biodiversity Mapping with Machine Learning**
    * Investigate machine learning approaches for mapping species distribution and biodiversity. Students may build classification models using ecological datasets.
    * **References**:
      * Elith, J., et al. (2011). A Statistical Explanation of MaxEnt for Ecologists. *Diversity and Distributions*.
      * https://www.gbif.org/

  * **Smart Energy Consumption Prediction**
    * Study machine learning methods for predicting energy consumption in buildings or cities. Students may reproduce forecasting models and evaluate their performance.
    * **References**:
      * Candanedo, L., et al. (2017). Data Driven Prediction Models of Energy Use of Appliances in a Low-Energy House. *Energy and Buildings*.
      * https://archive.ics.uci.edu/ml/datasets/Appliances+energy+prediction

===== Examination =====

The exam is conducted as part of the presentation (50% of the mark) and report (50%). The focus for pro-seminars lies in effective presentation skills, while the focus for seminars is the depth of the scientific topic.

===== Agenda =====

  * **13.04.2026** - **Introduction to Course & Environmental Challenges**
    * Course overview, introduction to environmental challenges, formation of research groups.

  * **20.04.2026** - **Lecture 1: Data Science Applications in Environmental Studies**
      * Topics: IoT, Machine Learning (ML), Big Data in environmental monitoring.

  * **27.04.2026** - **Lecture 2: Computer Science Methods for Climate Change, Biodiversity, and Pollution Control**
      * High-Performance Computing (HPC) for climate modeling, GIS for biodiversity conservation, and pollution control.

  * **04.05.2026** - **Research Topic Discussion & Selection**
      * Topic discussion and finalization. Group research begins with regular check-ins.

  * **11.05.2026** - **Lecture 3: Applications in Sustainable Agriculture, Renewable Energy, and Waste Management**
    * AI-driven precision agriculture, renewable energy system optimization, and waste management with computer science.

  * **18.05.2026** - **Group Work & Check-ins**
    * Begin group research with regular supervisor check-ins and guidance.

  * **25.05.2026** - **No Session (Whit Monday / Pfingstmontag)**

  * **01.06.2026** - **Group Presentations (Pre-Midterms)**
    * First round of group presentations on selected research topics.

  * **08.06.2026** - **Group Presentations (Continuation)**

  * **15.06.2026** - **Lecture 4: Ethical Considerations in Environmental Sustainability**
    * Ethical issues in AI and computer science solutions for environmental protection.

  * **22.06.2026** - **Advanced Research & Report Writing**
    * Research finalization and guidance on writing the report.

  * **29.06.2026** - **Final Presentations**
    * Group presentations of the final research results.

  * **30.09.2026** - **Deadline for Submission of the Final Report**
    * Submission of final reports (max. 15 pages).

===== Literature & Resources =====

Relevant reading materials will be shared throughout the course. Students are encouraged to contact the instructors for early preparation and recommended readings.

===== Topic Distribution =====

|| **Student** || **Supervisor** || **Topic** || **Submissions** ||
|| Your Name || Your Supervisor || Your Topic || {{https://hpc-team.pages-ce.gwdg.de/latex-templates/hps-report.pdf |Report in Pdf}} {{https://hpc-team.pages-ce.gwdg.de/latex-templates/hps-report.zip |Report in LaTeX or pptx}} ||