Thursday schedule

Full Programme
Wednesday, OCT 11
Thursday, OCT 12
Friday, OCT 13

Thursday, October 12th, 2023


Morning Coffee and Tea



How to improve Energy Efficiency at the Data Center level

Saving energy is a very important lever for the goal of becoming a carbon-neutral society. Unfortunately, energy consumption of Data Centers is going in the opposite direction and increasing constantly. In this session we will looks at examples on what can be done at the level of software, hardware and data center to compensate that trend and make Data Centers a driver for carbon-neutral.


Main Track: Technology for Sustainability
Proposing a Framework to address the Sustainable Development Goals

Reducing poverty, protecting the planet, and improving life on earth for everyone are the essential goals of the “2030 Agenda for Sustainable Development” committed by the United Nations (UN). Achieving those goals will require technological innovation as well as their implementation in almost all areas of our business and day-to-day life. This paper proposes a high-level framework that collects and structures different uses cases addressing the goals defined by the UN. Hence, it contributes to the discussion by proposing technical innovations that can be used to achieve those goals. As an example, the goal “Climate Action” is discussed in detail by describing use cases related to tackling biodiversity loss in order to conservate ecosystems.

Eco-innovation performance in European Union
The existing literature lacks a standardized approach to measuring and analyzing eco-innovation. Challenges include establishing micro-level indicators, addressing life cycle considerations, differentiating eco-efficiency from economic aspects, defining levels of analysis, and developing data aggregation methods. The impacts of eco-innovation are multifaceted, ranging from micro-level product and process improvements to sectoral and macro-level effects. Despite initial investment, eco-innovation often yields long-term benefits in terms of reduced environmental impact and enhanced company performance. This article’s primary objective is to validate the idea that eco-innovation contributes to long-term economic growth. It also aims to explore low eco-innovation index values in Central European countries by analyzing Eco-innovation observatory data. The research question examines whether less developed economies exhibit lower eco-innovation performance. The study draws from secondary data analysis obtained from the Eco-innovation observatory, assessing European countries’ eco-innovation performance and trends. Poland’s placement in the low eco-innovation performance category, alongside other Eastern and some Western European countries, highlights the need for greater eco-innovation implementation within Polish enterprises. The study underscores the significance of eco-innovation as a pivotal factor in Poland’s third transformation, complementing the earlier transitions of system transformation and EU accession.
News from Europe’s Digital Gateway: A Proof of Concept for Mapping Data Centre News Coverage
The Netherlands has been described as Europe’s Digital Gateway, owing in part to the disproportionate number of data centres located in the relatively small country. Data centres have become a much-discussed issue in Dutch media, with 11,842 news articles about data centres having been published between 1 January 1990 and 23 January 2023. This study explores this news coverage to identify possible sustainability concerns experienced in society as a result of data centre operation and construction. Identifying such concerns could help in informing discussion and future decisions regarding location, design, and operation of data centres as well as potential measures to mitigate sustainability concerns. This study explores Dutch data centre news coverage by combining manual and automated content analysis to determine commonly discussed themes. The results are subsequently spatialised using GIS software, which was later adapted into a PowerBI tool, allowing for an interactive exploration of the data. Through this exploration, we identify a strong trend towards increased public attention and debate about data centres in the Netherlands, underscored by a significant increase in media coverage since 2020. Most notably, the topic “space” is prominent throughout the entire study period, receiving the highest number of mentions each year and quadrupling in coverage from 2015 to 2021. Furthermore, matters relating to the categories “technology” and “environment” experienced the highest relative growth in the same time period. Overall, our results indicate an increasing importance of data centres in public discourse.
Towards a warning system for beekeepers: Detecting anomalous changes in sensor data from honey bee colonies
Beekeepers in most parts of the world are challenged by colony losses induced by diseases, parasites, shortage of nectar and pollen, and various other causes. For a better understanding of these causes and to inform beekeepers when to intervene and to perform certain beekeeping activities to protect their colonies, monitoring systems using sensor technology in the hives can be implemented. Currently, most monitoring systems available at the market provide a visualisation of the measured sensor values, but do no integrate further analysis or an interpretation of the values, e.g. by time series classification or by comparing to time series prediction data. We describe a system architecture where predictions made for a specific colony can be used to find aberrations, potentially indicating an anomalous development of the bee colony. We summarise challenges of such an implementation and evaluate the system using data from a German Citizen Science Project, consisting of temperature, humidity and weight measurements and a log of all activities and observations made by the beekeepers in a web app.
Developing a Digitization Dashboard for Industry-Level Analysis of the ICT Sector
The digital revolution in the Information and Communications Technology (ICT) sector necessitates advanced analytical tools to understand industry dynamics and support strategic decision-making. This article presents the development of a digitization Dashboard for industry-level analysis of the ICT sector. The study aims to fill the research gap in comprehensive industry-level analytical instruments and provide valuable insights for managers, policymakers, and industry stakeholders. The research questions focus on identifying technological advancements, understanding interconnections between technologies, and predicting industry growth. A comprehensive literature review was conducted, covering various sectors related to ICT, digitization trends, and industry-level analysis. The review highlighted the need for a specialized Dashboard to integrate and visualize data across diverse technological domains within the ICT sector. The methodology employed a hybrid approach using Design Science Research, combining quantitative data analysis with qualitative data for software development. Industry data, including patent analysis and technological trends, were collected, and processed during the analysis phase. Prototypes of the Dashboard were developed based on requirements from literature and industry standards in the design and development phase. The Dashboard underwent iterative improvements based on user feedback and usability testing. The evaluation of the digitization Dashboard assessed its functionality, usability, and effectiveness in providing industry-level insights. The results demonstrate that the Dashboard offers valuable visual representations, trend analysis, and forecasting capabilities, empowering stakeholders to make informed decisions. Limitations of the study include the reliance on qualitative data analysis, limiting the inclusion of quantitative insights, and the need for further validation of the Dashboard’s impact in real-world scenarios and diverse groups of users. Future research should explore the integration of more machine learning techniques on patent data sources and user-centric evaluations to enhance the comprehensiveness and applicability of the digitization Dashboard. Continuous updates and expansions of the Dashboard functionalities are needed to accommodate emerging technological trends and evolving industry dynamics.
Design of a recommender system to improve the environmental impact of companies based on their material and energy balances
As worldwide agreements aiming to reduce the carbon footprint keep coming into effect, many companies aim to become more efficient in their production process. However, it is costly to hire environmental experts to help with the efficiency and carbon reduction process. This research aims to analyze the possibility of creating a Recommender System (RS) which suggests Carbon Reduction Measures (CRM) to the users based on their Life Cycle Assessment (LCA) reports. Based on the literature review into the latest RS techniques and the available databases, a study was conducted into creating a RS prototype. Analysis of the results demonstrates, that with the currently available databases, it is not possible to create an effective RS. The results indicate that in order to be able to create a functional and useful RS more detailed data needs to be extractable from the LCA tool. Further research is needed into the exports from other Environmental Management Information Systems (EMIS) and the identification of other factors that could strengthen the effectiveness of the RS.
Assessment Power of ChatGPT in the Context of Environmental Compliance Management – Experiments with a Real-World Regulation Cadastre
In multiple research disciplines use cases built on Large Language Models in particular ChatGPT are at the centre of today’s discussions. For example, in various ongoing projects of the LegalTech area ChatGPT is evaluated in terms of its potential to replace routine work of lawyers. In a recently started project we are investigating the use of ChatGPT for a specific corporate compliance management task. In particular, based on a real-world test data set ChatGPT is prompted to assess the relevance of environmental regulations. The ChatGPT output is compared to the respective judgements of the human experts in order to obtain a first indication of the assessment power of ChatGPT in the compliance management domain. This research in progress article gives an overview of the evaluation approach and presents first results of a set of 142 test cases covering regulations from four different areas of environmental legislation.
Design of IT structures in vaguely defined application environments - Experiences from actor interaction in the blue bioeconomy
This contribution focuses at appropriate IT structures for innovative market segments which form an application environment that is only fundamentally defined in digitization efforts. The core feature are vague application profiles for IT structures to be set up, which players in such market segments can use internally, but especially in environmental and social interaction. For the example of the emerging blue bioeconomy, experiences in setting up a cross-location, distributed IT structure are presented, which is geared towards advising and supporting actors in the blue bioeconomy by a diverse team of experts. Key findings lie in (i) the need to integrate different dimensions of vagueness in the treatment of increasingly defined information in a three-layer model of the IT structure, (ii) the development of the IT structure in an open process that takes into account the dynamics of the market sector, and (iii) the constant training of the members of the expert team on content, routines and limitations of the IT structure in consulting of actors.
AI and Sustainability I
Reviewing explainable Artificial Intelligence towards better air quality modelling
The increasing complexity of machine learning models used in environmental studies necessitates robust tools for transparency and interpretability. This paper systematically explores the transformative potential of Explainable Artificial Intelligence (XAI) techniques within the field of air quality research. A range of XAI methodologies, including Permutation Feature Importance (PFI), Partial Dependence Plot (PDP), SHapley Additive exPlanations (SHAP), and Local Interpretable Model-Agnostic Explanations (LIME), have been effectively investigated to achieve robust, comprehensible outcomes in modeling air pollutant concentrations worldwide. The integration of advanced feature engineering, visual analytics, and methodologies like DeepLIFT and Layer-Wise Relevance Propagation further enhance the interpretability and reliability of deep learning models. Despite these advancements, a significant proportion of air quality research still overlooks the implementation of XAI techniques, resulting in biases and redundancies within datasets. This review highlights the pivotal role of XAI techniques in facing these challenges, thus promoting precision, transparency, and trust in complex models. Furthermore, it underscores the necessity for a continued commitment to the integration and development of XAI techniques, pushing the boundaries of our understanding and usability of Artificial Intelligence in environmental science. The comprehensive insights offered by XAI can significantly aid in decision-making processes and lead to transformative strides within the fields of Internet of Things and air quality research.
Commonalities and differences in ML-piplines for Air Quality Systems
This paper compares three ML-pipelines in Air Quality (AQ) Systems, namely a fog layer management model for IoT-systems, a low-cost AQ sensor system with sensor calibration and data fusion competences and a ML-method research based on low-cost OpenSensorMap. The three ML-pipelines are described, commonalities and differences worked out and the advantages of every technique are led over in an effort of a combined ML-pipeline which could be realised in a scientific cooperation of the three groups.
Optimal stacking identification for the machine learning assisted improvement of air quality dispersion modeling in operation
Air quality modeling plays a crucial role in understanding and predicting the dispersion of pollutants in the atmosphere, aiding in the development of effective strategies for mitigating the adverse impacts of air pollution. Traditional air quality modeling commonly relies on deterministic models that simulate pollutant transport, and dispersion based on physical and chemical principles leading to analytical numerical simulations towards the identification of pollutant concentrations in ambient air. However, these models often face challenges in accurately capturing the complex and dynamic nature of pollutant behavior due to uncertainties in emission inventories, meteorological conditions, and local-scale variations in terrain and land use. ENFUSER is a local scale air quality model that operates in the greater Helsinki area in Finland that successfully addresses most of the mentioned challenges. In previous research [2] we formalized a machine learning-based methodology to assist the operational ENFUSER dispersion model in estimating the coarse particle concentrations. Here, we continue this line of research and evaluate the genetic algorithm hybrid stacking with a novel validation procedure coined spatiotemporal cross validation. The development of the validation procedure was deemed necessary to simulate closely the operational requirements of ENFUSER. Furthermore, we introduce a fitness function based on robust statistics (median and standard deviation) that forces the predictions to follow the distribution of the reference stations. Results obtained using the greater Helsinki area (including Vantaa and Espoo) as a testbed suggest that the combination of ENFUSER with the proposed framework can provide estimations with higher confidence and improves the correlation from 0.61 to 0.71, the coefficient of determination from 0.34 to 0.50 and reduces the RMSE by 2.2 μg/m3.
Concepts for Open Access Interdisciplinary Remote Sensing with ESA Sentinel-1 SAR Data
Earth observation with advanced, large-scale technologies as satellite piloted Synthetic Aperture Radar (SAR) appear essential to monitor agricultural ecosystems in the near future. Radar backscatter, for example, allows insights into crop conditions, soil properties, and direct mapping of vegetation growth. Precise SAR pre-processing is a substantial prerequisite to perform machine learning on SAR data, e.g., for early prediction of optimal sowing, harvesting, and fertilization time points. This is essential not only for successful, resource-efficient, and environmentally friendly farming but also for a wide range of other fields concerning environmental observations. Open access technologies offer the best solutions for collaborative efforts, thus minimizing financial and legal constraints in comparison to technologies residing in the commercial sector. Here, we combine expertise from the area of computer science, data science, software engineering, agriculture, and geo-information systems to build on state-of-the-art, open-source (OS) tools and technologies in Germany. Our goal is to provide an easy-to-employ Sentinel-1 SAR pre-processing tool as well as a Germany-wide, open access, pre-processed, analysis-ready database of Sentinel-1 SAR data. With the employment of modern software developing methods, including the Model View Controller (MVC) architecture and a procedural and object-oriented design, these solutions can be extended, adapted, and tested. This solution is available and accessible.


Lunch Break


Green Coding II
Measuring Resource Efficiency of LaTeX Paper Templates
Scientific work is mostly communicated via scientific papers, which are often published in journals or conference proceedings, either in print or digital form. These journals and conferences usually demand that submitted papers follow a specific formatting style, for which they provide style templates. The choice of a template influences different properties of the generated document, like its file size or the number of pages that it would use in printed form, directly affecting its impact on the environment. We built a system to automatically compare different LaTeX templates with regard to different factors relevant to the environmental impact. We test our approach with seven templates used by different conferences and journals, and find that the most efficient templates have roughly one third of the file size, and require about one half of the resources for paper production of the least efficient.
Energy and resource comparison of current applications with a focus on statistical analyses and evaluations using the example of Matlab and R/RStudio
This paper presents a comprehensive comparison of the energy and resource efficiency between MATLAB and R, two widely used programming languages in scientific computing and data analysis. The study utilizes a system under test, comprising a load driver and an automation software, PowerBI, to measure and evaluate the performance of both languages. Prior to the experiment, specific mathematical operations and execution methods were implemented in MATLAB and R scripts. The measurement steps and evaluation were conducted using the Oscar framework. The findings indicate that R outperforms MATLAB in baseline and statistical operations, while MATLAB excels in matrix calculations. These results provide valuable insights into selecting the most suitable programming language based on specific computational requirements, thereby optimizing energy consumption and resource utilization.
Power Consumption of Common Symmetric Encryption Algorithms on Low-Cost Microchips
In the Internet of Things (IoT), many devices are battery-operated, making them particularly susceptible to power-hungry applications. Symmetric encryption is a regularly performed task on such devices, as it ensures the confidentiality of the data they send. While previous work has compared the power consumption of common symmetric encryption algorithms on commodity hardware, no such evaluation exists for low-cost microchips, which are often used in IoT devices. In this paper, we compare the power consumption of an ESP8266 executing common symmetric encryption algorithms with varying parameters such as key size, data authentication, or payload size. We find that the power consumption depends on several factors, but that overall AES-GCM has the lowest power consumption when the encrypted data is also authenticated, while Blowfish-CTR has the lowest power consumption when no authentication is applied.
Measuring the energy consumption of software with simple tools
In my talk, I would like to present a simple and low-threshold approach to measuring the energy consumption of software on local development environments. With the help of a measurement script executed in parallel to one’s own application, which is documented at, it is easy to examine the energy efficiency of one’s own code in any programming language or complete applications. The measurement results can then be used to make the code more energy-efficient. I present the results of a test series in which the “softwarefootprint” measurement script was executed on different hardware platforms with different load drivers and show its possible areas of application and limitations.
The Bike Path Radar: A Dashboard to provide new information about Bicycle Infrastructure Quality
Data can support the decision making process in bicycle infrastructure planning. Dashboards may make a positive contribution to learn more about infrastructure shortcomings if these provide relevant Key Performance Indicators (KPIs) and visualizations. Existing dashboards do not reflect the perspective of different types of users, only provide limited data sources and do not provide much information about bike path damages. The Bike Path Radar (Radweg Radar) should fill this research gap by providing relevant information about cycling infrastructure. The frontend enables the end user to create different KPIs regarding cycling accidents, citizen reportings, traffic volume etc. of highest interest. A role concept enables the provision of a suitable degree of information traffic planning experts and citizens. The most important KPIs were identified based on expert interviews. The dashboard is connected to a database in the background that includes heterogeneous cycling and bicycle infrastructure data by an API. In addition to that, the dashboard gives new opportunities for citizen engagement. Users can upload images of bike path damages in a reporting tool. The images will be processed by an object detection algorithm. The detected damages will be displayed on a map by a marker to find locations with surface shortcomings. This contribution will give a short overview about the current state of development of the Bike Path Radar. The outlook provides some additional information about the forthcoming working steps.
Determination of Citizen Groups and Added Value for a Daily-Integrated Environmental Information Portal
Environmental and climate protection are becoming increasingly important in society. Despite the advancement of digitization in recent years, the publicly available environmental information portals (EIP) in Germany are not technically up-to-date and fall short of expectations. A thorough investigation of requirements and citizen groups is essential for the development of a novel environmental information portal. This work deals with the identification of the requirements and various citizen groups, especially the general public. Based on these findings, a concept for a tailored environmental information portal is developed. The first chapter, the introduction, addresses the motivation, the problem statement, and the research questions. Subsequently, the current state of research on environmental information and environmental information portals is examined. In the third chapter, the results of survey studies on the identification of citizen groups and their requirements are discussed. Based on this, a concept of a demand-driven environmental information portal tailored to the identified citizen groups is presented. In the concluding part, a summary and an outlook on further research areas of this work are provided.
Towards Gamification of Advanced Value Stream Analysis and Design: A Game Based Learning Concept
Advancing the traditional methodology of value stream analysis and design to include aspects such as material flow cost accounting, information logistics and external influential factors, overall application complexity and increasing data volumes are causing a shift in how improvement teams should think and operate. As a result, also the professional training of students and professionals needs to change and requires new solutions. Existing research efforts have not yet resulted in a solution that can convey advanced value stream analysis and design, including its methodological complexity. To address this gap, this paper applies a tailored CRISP gamification framework to develop a game-based learning concept to enable teaching of advanced value stream analysis and design to students and professionals focusing on identification of multi-stage resource-efficient optimization strategies. Activity cycles and progression stairs of the resulting simulation game concept facilitates innovative education while aiming to promote cognitive, motivational, and behavioral learning.
Proof of concept: local precipitation-dependent rainwater management with smart water tanks
The effects of extreme weather events are increasingly having a negative impact on the water and wastewater infrastructure. Due to increasing land sealing in urban areas and more intense rain events, new concepts are needed to relieve the water and wastewater infrastructure. One possible approach is the usage of private rain storage as retention volume without negatively affecting the owner. Therefore, a smart approach is used to manage the rain storage in a situational way. This paper therefore presents a first prototype of a smart water tank, which was used to cover and test initial requirements. The goal was to develop an operational and portable hardware and software prototype early in the project.
AI and Sustainability II
Assessing Sustainable Artificial Intelligence via Societal Impact Analysis: The Case of Earth Observation
The pursuit of ecological and social sustainability in the face of climate challenges has brought attention to the potential of artificial intelligence (AI) as a transformative tool. While AI’s ecological applications like data analysis and decision automation have been extensively researched, their societal implications often remain less apparent due to their indirect nature and focus. This paper addresses this gap by proposing a comprehensive societal impact analysis grid and applying it to the context of Earth Observation (EO) driven by satellite data. The suggested societal impact analysis grid not only extends existing technology assessment frameworks to incorporate critical social and data protection theory aspects but also makes it particularly suitable for assessing the societal implications of AI and data-related technologies. Applying this grid to EO reveals both practical benefits and emerging societal issues. EO’s capacity for valuable sustainability insights, such as environmental monitoring, underscores AI’s potential. However, the analysis also unveils challenges like an observer-observed relationship and global data-related inequities. By constructing this impact grid and examining the EO case, this paper contributes to the evolving discourse on sustainable AI, aligning ecological and social considerations.
How do the European Court of Human Rights rulings in environment-related cases affect the future of Environmental Informatics?
In recent years, significant developments in environmental and human rights have taken place within international bodies. The United Nations granted the right to live in a healthy environment as a Human Right in 2021. Following this, the Council of Europe updated its instruction on Article 46 of the Convention in 2022. The President of the ECHR, in April 2023, highlighted issues within the Tribunal related to the implementation and execution of judgments, emphasizing the importance of the Rule of Law and the need to address clear issues. This ongoing research delves into the potential of Environmental Informatics and ESG reporting to predict the consequences of the ECHR Great Chamber’s case on prioritizing climate actions and their costs. The study examines the intersection of Fundamental Rights and Environmental Informatics, particularly in the context of climate action. It explores how these elements can be integrated into software and considers the various perspectives of stakeholders, including developers and regulators. The research embraces a multidisciplinary approach to tackle complex questions surrounding automated decision-making, data aggregation, and users’ responsibility, aiming to contribute to discussions on sustainable and ethical software development.
How to facilitate the Creation of Machine Learning predictive Models
This work presents a methodology that facilitates the creation of machine learning predictive models. This procedure merges several mathematical and statistical tools which we call Predictive Factor Association (PFA). PFA is applied to predicting pollution emergencies. This knowledge in used to determine the impact pollution has in population health as health risk factors for different types of population are developed. Artificial intelligence is used to enhance chemical and physical air pollution modelling as input for determining population health risks.
Physics-informed Machine Learning for Green Applications
Modern deep learning methods require a lot of computational resources for training. The topic of energy efficiency will therefore be of crucial importance for the development of new algorithms in the future. One way to develop more energy-efficient methods is to intrinsically consider physical laws and constraints and thus, for example, significantly limit the data space for training. In my talk, I will give an overview of Physics-informed Machine Learning and show possible application areas within our current projects in the environmental domain.


Coffee and Tea Break


Poster Talks and Session
Usage Analysis of Bavarian Citizen Science Information Platform for Climate Research and Science Communication BAYSICS

BAYSICS – Bavarian Citizen Science Information Platform for Climate Research and Science Communication aims to communicate the impacts of climate change through citizen science. The centerpiece of the project, the BAYSICS web portal, was developed in cooperation with Bavarian universities and LRZ, and it has been in operation since April 2020.The BAYSICS web portal offers citizens the opportunity to submit their observations in Bavaria for four categories of interest to the project 1) plants 2) allergenic species 3) tree lines 4) animals. The collected data are visualised on a map and can be freely accessed through API or downloaded in CSV/XLS format. The web portal also provides analysis tools, wikis, and other information bases, making it suitable for use in educational settings. In this study, a usage analysis of BAYSICS web portal is conducted and the findings are shared. 

Optimization of Public Transport using Floating Car Data
This project focuses on optimizing public transportation through the utilization of open data and APIs, conducted by students from Bochum University of Applied Science. Given the urgency of addressing climate concerns, mobility’s significant role in emissions becomes evident. The initiative leverages Floating Car Data from Envirocar, street geometries from Open Street Map (OSM), and routes from OpenRouteService. By applying a Hidden Markov Model for map matching, the data is projected onto OSM’s road network. The resultant tool counts road segment usage, offering insights for public transport and carpooling improvements. This endeavor showcases the value of citizen science APIs in educational integration, culminating in a practical tool for urban infrastructure and transport optimization.
Geo.KW - Coupled Modeling of Geothermal Energy
FAL Meeting
FAL Meeting

Fachausschussleitungstreffen Umweltinformatik
Invitation only 


Brewery Tour and Tasting