Dynamic Forces
Testing the Environmental Brundtland Curve Hypothesis for Air Pollution and Economic Growth Nexus View Digital Media
Paper Presentation in a Themed Session Francis Ayensu
Limited literature and scarcity of empirical studies on the Environmental Brundtland Curve (EBC) hypothesis has left a research gap that needs to be filled. Practically, no empirical studies can be found on the topic though sufficient theoretical literature has been discussed on the subject. The debate remains on how relevant is the EBC hypothesis in the search of related theories on the issue of environment and development nexus. The proposed study examines whether economic growth drives air pollution in developing economies. The research approach is deductive since the study seeks to validate or invalidate a theory. The research design is causal since the study seeks to explain the effect of economic growth on environmental degradation. The research method is quantitative since the study relies on secondary quantitative data to study the relationship between environmental degradation and economic growth. The target population represents 81 nations across the globe. From this number, a sample of 79 countries with high air pollution would constitute the sample size. The sample design is a purposive sampling method since the selected countries must meet certain criteria. The source of data is primarily secondary data. Data are gathered from World Bank Development indicators. The analysis method is an observation of cross-sectional panel data over 60 years from 1960 to 2020. Statistical modelling methods include Cross-sectional dependence test, Unit root test, Cointegration test, Causality test, ARDL. Data are analyzed with the assistance of Microsoft Excel, EViews, RStudio, and Stata.
Exploring the Prediction and Influence Factor Analysis of NO2 Emissions Using Machine Learning Models: A Study of Munich City Area View Digital Media
Paper Presentation in a Themed Session Leon Lukas
This research project, in collaboration with the Department for Climate and Environmental Protection (RKU), analyses data from NO2 measuring stations in the Munich city area, provided by the State Office for the Environment. The project used machine learning models to evaluate the prediction of NO2 emissions and perform an influence factor analysis by supplementing the data with traffic measurements from the mobility department and weather data from the German Weather Service. The results showed that prediction and influence factor analysis are possible, but the study also highlighted several limitations to these methods, which are thoroughly discussed. The research project achieved a prediction of NO2 with an RMSE of 13.9 by using available covariates. The study also explored use cases such as special extrapolation with these models. The influence factor analysis was conducted using Forest-Guided Clustering, mean decrease in impurity, Permutation Importance, and Partial Dependence Plots, with the latter yielding the best results. The analysis revealed that wind, temperature, ozone, and humidity significantly influenced NO2 concentrations, while precipitation had no effect.
Integration of Generative AI into a Tool to Assist Participatory Environmental, Social and Corporate Governance (ESG) Double Materiality Assessment for Small and Medium-Sized Enterprises View Digital Media
Paper Presentation in a Themed Session Benedikt Latos
Due to ever increasing EU-wide and national Environmental, Social and Corporate Governance (ESG) regulations, the formulation of a robust sustainability strategy is a major challenge, particularly for small and medium-sized enterprises. The obligatory double materiality assessment very often represents a major obstacle in the initial phases of defining a company specific sustainability strategy. Its major objective is to develop a company-specific sustainability target system based upon a consensual ranking by the stakeholders. The Analytic Hierarchy Process (AHP) method is a widely accepted tool, that can be utilized to generate such a prioritized target system, ensuring that resources and efforts are directed towards the most critical objectives. This paper outlines a concept to conduct the double materiality assessment through the synergistic use of Generative AI and the AHP method. In the first step, we employ interactive, moderated workshops as our chosen methodology to create a tailored set of sustainability target criteria. This process is enriched by the inclusion of Generative AI. The outcome is a comprehensive set of company-specific sustainability target criteria. In the second step, we continue to use interactive, moderated workshops to prioritize the company-specific sustainability target system with the AHP Method. In the third and final step, we rely on a workshop for deriving company-specific measures to achieve the sustainability targets. Finally, the results of a first validation of the process in a medium-sized manufacturing company are presented, discussed as well as future arising research questions are outlined.
