Skip to content

Virtual Tools, Machine Learning and AI

Description:

Recent years have seen a surge in the development and application of machine learning (ML) and artificial intelligence (AI) technologies, revolutionizing how we approach data-driven discoveries across diverse scientific domains. Environmental science, health, and engineering are areas of increasing complexity, where issues such as pollution, climate change, and public health require innovative solutions. AI and ML methods offer a powerful means of addressing these challenges, enabling the prediction of environmental impacts, toxicities, and risks, and supporting better-informed policy and regulatory decisions. We shall invite the submission of abstracts that apply machine learning and AI methodologies to solve pressing problems in environmental science, health, and engineering. Topics of interest include, but are not limited to: Source Attribution, Chemical Toxicity Prediction, Screening of Unknown Pollutants, Human Exposure Assessment, Molecular Mechanisms of Exposure and Disease, Generative Models for Molecular Design and Optimization, Benchmarking Studies.

Organizer:

Joseph Wasswa

Description:

The increasing complexity of global environmental challenges pushes the limits of traditional LCA. The growing need for more accurate, timely, and comprehensive environmental assessments has opened the door to use of Artificial Intelligence (AI), which could revolutionize LCA by enhancing its predictive power and expanding its data processing capabilities. However, LCA modeling, as a data-driven techniques, inherently comes with limitations such as uncertainties and variabilities that can challenge interpretation and decision-making, especially when dealing with complex or futuristic LCA models. We and others have assessed and critique the growing body of ML + LCA literature and think it is of interest to ensure that qualified LCA practitioners establish best practices for integration of AI into LCA, rather than allowing the novelty of ML to erode rigorous LCA practice. We think it will be of interest for the AEESP community who engages in LCA to discuss opportunities and challenges associated with integration of ML and LCA.

Organizers:

Lisa Colosi Peterson, Mehran Akrami