Wednesday Schedule - EnviroInfo 2023

Full Programme

Wednesday, OCT 11

Thursday, OCT 12

Friday, OCT 13

Wednesday, October 11th, 2023

08:30

Welcome coffee and Tea and Registration

10:00

Opening and Welcome

10:30

Earth Observation and Machine Learning for Environmental Sciences – The terrabyte HPDA system as a game changer for research

11:15

Big Data and Deep Learning for Climate Sciences - Climate Change and Hydro-Meteorological Extremes in Europe

12:00

Lunch Break

13:00

Urban air-quality estimation using visual cues and a Deep Convolutional Neural Network

13:30

Main Track: Environmental Monitoring

Towards Fine-Grained Sensor-Based Probabilistic Individual Air Pollution Exposure Prediction using Wind Information

Abstract

The estimation of pollutant exposure is highly dependent on the spatial and temporal resolution of the underlying model. This work presents a street-level Gaussian Process Regression model for urban air quality that uses a novel covariance kernel based on physical considerations to process wind information. This model can be driven by information from observations from low-cost sensor networks. We present the model, including the construction of the wind angle kernel, and discuss the inconclusive evaluation to date, the current challenges, and the way forward.

everWeather: A Low-Cost and Self-Powered AIoT Weather Forecasting Station for Remote Areas

Abstract

Weather constitutes a crucial factor that impacts many of the human outdoor activities, whether they are related to obligations or pleasure. In the contemporary era, due to climate change, the weather is more unstable and the forecasting task is more challenging than ever. By combining the Internet of Things (IoT) with Artificial Intelligence (AI), a new research field emerges that is called Artificial Intelligence of Things (AIoT) and could offer significant possibilities for the research community in order to efficiently tackle the short-term weather forecasting. Renewable energy sources constitute solutions for the achievement of sustainability development goals and could also offer power autonomy in a weather forecasting station. In the present research study, everWeather is proposed as a low-cost, self-powered weather forecasting station based on the AIoT paradigm and renewable energy. The proposed solution combines a variety of low-cost environmental sensors, the prowess of solar energy and an appropriate lightweight Machine Learning (ML) algorithm such as the Multiple Linear Regression (MLR) in order to forecast physical weather for the next half hour. Preliminary experiments have been conducted for the proposed solution validation and the corresponding results highlighted that the performance of the everWeather station is quite satisfactory, in terms of reliability and forecasting accuracy.

Management of climate protection measures in peatland areas in Schleswig-Holstein

Abstract

The peatland database application Schleswig-Holstein is presented, a web application for the management of geospatial and non-geospatial data covering peatland protection, which was designed and implemented on behalf of the nature conservation departments of the Ministry for Energy Transition, Climate Protection, Environment and Nature of Schleswig-Holstein (MEKUN) and the State Agency for the Environment of Schleswig-Holstein (LfU). The development of the web application was based on the IT requirements for the collection, research, evaluation, and reporting of peatland data. Other applications already used by the nature conservation authorities, such as a nature conservation measures database and a protected areas register, were linked to the peatland database. The implementation was carried out as a PHP application that was integrated into the Disy Cadenza evaluation and GIS platform. Particular challenges included dynamic integration of measures from the nature conservation measures database. For restoration measures, a function is provided that automatically determines the reduction of CO2 emissions.

Sustainable Mobility

Data Management of Heterogeneous Bicycle Infrastructure Data

Abstract

Data that is related to traffic and specially to cycling is already commonly used in bicycle infrastructure planning processes. Data supports the understanding of bicycle use. What becomes more relevant is data about the state of the bike infrastructure. In general, cycling data sources have become in-creasingly heterogeneous what increases the need for suitable data management. This contribution presents the data management solution of the INFRASense research project that aims at the quality assessment of bicycle infrastructure. As a first step, the state of the art of data applications in cycling planning is presented. The data pipeline of the research project that considers many of these data sources is based on a Data Lake approach where the raw data sets are stored before transforming these individually for further data processing. The available data sources can be divided between time series and non-times series data. The related data models that allow the combination of different tables inside the database will be presented. As a last step, the contribution gives an outlook to forthcoming applications that will build up on the presented data management solution (interactive dashboard for data analysis).

Evaluation of Incentive Systems in the Context of SusCRM in a Local Online Retail Platform

Abstract

The current consumption patterns observed in both offline and online retail present sustainability challenges related to environmental impacts associ-ated with products, last-mile delivery, personal mobility, and packaging. Different choices in delivery methods and individual mobility to overcome the last mile lead to varying levels of emissions. To address these environ-mental impacts, this study examines the application of a Sustainability Customer Relationship Management (SusCRM) approach to a local retail platform, aiming to meet customer expectations while promoting sustaina-ble and conscious consumption within the various stages of the e-commerce customer journey. Consumers nowadays tend to act in a more sustainable way at the same time, they hold retailers and logistics compa-nies responsible for creating these offers. Designing such a platform ad-dressing the demand for sustainable supply is the key goal of the research project ” R3 – Resilient, Regional, Retail in the Metropolitan Region Northwest”. To explore potential incentive systems that can be implement-ed within the platform, a survey was conducted. The survey results indicate that most respondents demonstrated a high level of acceptance towards the proposed incentive systems.

Geospatial Data Processing and Analysis of Cross-Border Rail Infrastructures in Europe

Abstract

The European Union has established two major goals: the interconnection of Europe and achieving climate neutrality by 2050. Rail transport, known as the most environmentally friendly mode of transportation, has the poten-tial to bridge these goals if the right strategies are implemented. However, Europe still faces significant challenges in developing a unified rail transport network, particularly evident in the inadequate infrastructure in border areas. This study aims to address these challenges by first identify-ing all locations in Europe where cross-border rail traffic occurs and then exploring potential factors that influence the development of cross-border rail connections. To achieve this, a comprehensive literature review was conducted to identify potential influencing factors. Subsequently, a quanti-tative data analysis was performed using geographic data to identify rela-tionships and confirm potential influences. Geographical Information Sys-tems were utilized to create comprehensive datasets, providing detailed in-formation on all cross-border rail connections in Europe and their corre-sponding border regions. The analysis confirmed a strong economy and a common language as the most significant factors influencing the emergence of cross-border rail links. Surprisingly, no correlation was observed be-tween population size and the presence of cross-border rail infrastructure in border regions. In this context, it was discovered that many populous re-gions lack a direct rail connection to their neighbouring region when sepa-rated by a national border. This shows the persistent divisive nature of na-tional borders in Europe, despite the existence of the single market and freedom of movement. The datasets generated in this study offer highly ac-curate geospatial data on European cross-border rail infrastructure. These datasets hold great potential for future research endeavours across multiple domains, providing fresh perspectives on the infrastructure of border areas.

Open Search - Advancing Environmental Data Discovery

5-year into the Open Search Initiative: state of play and future perspective

Open Search - new approaches towards a sustainable search infrastructure

OpenSearch@DLR project - new tools for scientific search and access to environmental data

15:00

Coffee and Tea Break

15:30

Main Track: Sustainable Practices

Sustainability Assessment in Semi-automated Solar Panels Production Facility

Abstract

This research work demonstrates the potential of material and energy flow analysis (MEFA) digital tool to address sustainability concerns in Semi-automated production lines in SMEs. The paper presents the application of MEFA on a solar panels’ assembly facility in the MENA region. The importance of thorough data collection is highlighted as it allows for accurate mapping of how materials and energy are flowing through a system especially in case of manual assembly lines. The challenges in data acquisition are addressed and the improvement scenarios are presented by using simple innovative methods such as QR codes to streamline the data collection process, saving time and reducing errors. Overall, this paper demonstrates how material and energy flow modelling can be used to identify areas for improvement in sustainability practices in small and medium enterprises using simple digital tools.

A Novel Approach for Sensor Fusion Object Detection in Waste Sorting: The Case of WEEE

Abstract

This paper investigates the application of AI-based methods for characterizing waste materials in sorting processes. With the increasing use of sensors in waste sorting systems, there is an opportunity to integrate data and improve accuracy. AI methods, such as deep object detection models, have the potential to optimize waste management processes and promote sustainability. This research examines the utilization of Sensor Fusion Object Detection in a multi-sensor sorting system, focusing on two different data fusion methods: concatenation and image mirroring. In the first approach, image data is concatenated with data from a hyperspectral near-infrared camera (NIR) and an inductive sensor, where dimensionality reduction techniques are applied to the data from both sensors. The second approach relies on a specific combination of NIR and inductive sensor data to simulate the format of image data. A Siamese Object Detection architecture is developed to train the model. The real-world testing results show that both approaches improve waste characterization accuracy and reliability by augmenting the models’ mean average precision (mAP). These findings demonstrate the potential for AI-based methods to transform the waste separation and management process, leading to more sustainable practices and resource efficiency.

Sustainability Analysis and Optimisation of a PET Recycling Factory in the MENA Region

Abstract

This study demonstrates the use of environmental informatics methods in the MENA region, where sustainability approaches still face major challenges. The following case study focuses on the analysis and optimisation of the environmental performance of BariQ, a PET recycling factory in the MENA region. Through the application of a MEFA, an LCA and an environmental benchmarking with a competitor in Europe, the Egyptian company’s level of performance and areas with potential for improvement are identified. Additionally, a photovoltaic system is set up and evaluated as an optimisation attempt of BariQs environmental impact.

Green Coding - Session I

Software Life Cycle Assessment (SLCA) in the wild

Abstract

Software Life Cycle Assessment (SLCA) is gaining attention for its environmental impacts in production, deployment, usage, and disposal. Unlike LCA for physical products, SLCA is still evolving in software. The presentation introduces a practical SLCA approach for code, discussing concepts and tradeoffs for smaller projects. The SLCA process is outlined, analyzing software phases for environmental impacts. Challenges in estimating energy during development are highlighted, proposing a Software Carbon Database for continuous assessment. Deployment’s energy during Docker builds is briefly mentioned. To address usage phase complexities, a middleware solution tracking energy per API call and updating the Software Carbon Database in real-time is proposed. Disposal phase considers energy during software component removal using the Green Metrics Tool. The talk concludes with a contemporary SLCA approach for agile software development. It relies on real-life data, promotes traceability, and can be adopted by development teams for sustainable practices. Recommendations to improve data quality for disposal and delivery phases are discussed.

Workshop on Integration of Green Coding in Curricula

Abstract

The workshop investigates the integration of technology and sustainability, focusing on incorporating Green Coding into curricula. It explores challenges, opportunities, and potential implementations. The workshop comprises in-depth discussions about initial efforts introducing Green Coding through a course at HTW Berlin, titled “Design and implementation of a lecture teaching current Green Coding approaches and practices at HTW Berlin,” offering foundational insights. Additionally, a presentation on integrating Green Coding into existing study programs provides practical applications. Participants are encouraged to share experiences and insights into integrating Green Coding into curricula, with qualitative inputs analyzed for a comprehensive understanding. Outcomes will shape academic guidelines for wider dissemination. Join this transformative platform shaping the future of tech education, uniting sustainability and technology through Green Coding. It welcomes researchers, educators, and curriculum developers passionate about sustainable tech education, valuing your contributions to the discourse on Green Coding’s educational impact.

Design and implementation of a lecture for teaching current Green Coding approaches and practices at the HTW Berlin

Abstract

In the research project “Potentials of Green Coding,” involving the ‘Gesellschaft für Informatik e. V.’ (GI), the ‘Umweltcampus Birkenfeld’ (UCB), and the ‘Hochschule für Technik und Wirtschaft’ (HTW Berlin), three research questions on ‘green coding’ were addressed. These focused on current ‘green coding’ concepts in software development and the Internet industry, as well as the implementation of these concepts in software development processes and existing degree program curricula. Within the third research question, led by HTW Berlin, a pilot module was developed for the Master’s program “Industrial Environmental Informatics.” The module aimed to integrate environmentally conscious and energy-efficient software development principles. Titled “Current Development Trends in Environmental Informatics,” the course imparts foundational concepts and techniques in the field, emphasizing software that is energy efficient and environmentally friendly. Students learn to optimize energy efficiency through algorithms and enhanced server performance. The modular course includes internal and external lectures, culminating in a practical component for hands-on learning. The course is influenced by current research at HTW Berlin and external experts, enhancing students’ knowledge of ‘Green IT’ and ‘green coding.’ Practical measurement exercises, based on the “Blue Angel for Software Products” standard, are conducted to explore ‘green coding’ topics, resulting in LNI short papers. This talk presents and discusses the short papers’ findings, evaluating the course concept and execution.

Abstract

Unser Workshop beleuchtet hierbei neben dem Stand der Technik zukünftige Implementationsmöglichkeiten und die damit verbundenen Chancen und Hindernisse.

Workshop-Highlights:

Aktuelle Beispiele: Mit einem Eröffnungs-Talk zu ersten Implementierungsversuchen eines Green Coding Kurses an der HTW-Berlin mit dem Titel „Design and implementation of a lecture of teaching current Green Coding approaches and practices at the HTW-Berlin” sowie der folgenden Vorstellung einer aktuellen Masterarbeit zum Thema “How can Green Coding concepts be implemented into the curricula of existing study programs?” wird Ihnen für die folgende Diskussion beziehungsweise Experteninterviews eine Gundlage und Einstieg gegeben.

Experteninterviews: Die Teilnehmer sind eingeladen, ihre persönlichen Erfahrungen und Reflexionen zur Integration von Green Coding in Curricula zu teilen. Diese qualitativen Erkenntnisse werden methodisch erfasst, analysiert und ausgewertet um vertiefte Einsichten in den Implementierungsprozess zu gewinnen. Die erfassten Ideen und Ergebnisse werden folgend in akademische Leitlinien verarbeitet und veröffentlicht.

Seien Sie Teil dieser wissenschaftlichen Erkundung und gestalten Sie die Zukunft der Technologie mit einem fundierten Ansatz zur Integration von Green Coding in Curricula. Dieser Workshop richtet sich an Forschende, Pädagogen:innen, Curriculum-Entwickler:innen und alle, die sich für die Verknüpfung von Nachhaltigkeit und Technologiebildung in der Lehre interessieren.

Smart Water

Machine Learning for the Detection of Water Pollutants in the Danube

IoT-Driven Data Solutions for Water Scarcity: The Nutzwasser project approach

Abstract

The Nutzwasser project aims to tackle increasing water scarcity due to climate change in the dry plateau near Schweinfurt. It focuses on turning wastewater into usable water using special treatment processes. The project uses IoT sensors to collect data on irrigation, weather, and water levels. This data is transmitted using the Lora WAN technology and securely stored in virtual machines to prevent data loss. The project monitors data deliveries to ensure accuracy and uses email alerts in case of issues. It also facilitates communication through the bidirectional rest interface for ALB (Arbeitsgemeinschaft Landtechnik und Landwirtschaftliches Bauwesen), with secure access for authorised personnel. The Nutzwasser project offers an innovative and data driven solution to address water scarcity and promote sustainable water management. Its approach can be a model for similar challenges worldwide

18:30

Conference Dinner