A machine learning based method for parametric environmental impact model for electric vehicles

Aug 3, 2026

Environmental managers seek to integrate precautionary principles into decision-making, yet machine learning–driven tools for early warnings of lifecycle environmental impacts remain limited. This paper proposes an approach supporting electric-vehicle design by merging Life Cycle Assessment (LCA) with machine learning foundations. A six-phase workflow builds models from design features using regression and supervised methods, producing quantitative results from limited inputs. The database and hypothesis uniqueness improve coherence and comparability, achieving design-phase accuracy comparable to more comprehensive analyses.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Design, environmental assessment, and electric vehicles

Journal of Cleaner Production 454 (2024) 142308 Contents lists available at ScienceDirect Journal of Cleaner Production journal [homepage: www.elsevier.com/locate/jclepro](homepage: www.elsevier.com/locate/jclepro) | A machine learning based method for parametric environmental impact model for electric vehicles | | | | | --- | --- | --- | --- | | *
Luca Manuguerra , Federica Cappelletti , Michele Germani
Universit`a Politecnica delle Marche, Faculty of Engineering, Department of Industrial Engineering and Mathematical Sciences, Via Brecce Bianche 12, 60131, Ancona, Italy | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Handling Editor: Tomas B. Ramos | | Environmental managers attempt to increasingly incorporate precautionary principles into decision making. The literature lacks Machine Learning-based approaches for forewarning lifecycle environmental impacts. This paper proposes a method to support electric vehicle design. The main innovation of the work lays in merging Life Cycle Assessment (LCA) and Machine Learning foundations to provide support and awareness to designers. The present approach overcomes the present literature because it provides a method for the design phase, is based on a wellestablished methodology (LCA) and provides quantitative results from little inputs. The approach exploits machine Learning Methods to develop models with the design features of a generic electric vehicle (such as vehicle mass and distance traveled) in six phases (Problem definition; Data collection; Data Preparation; Modeling; Model evaluation; Model interpretation). Differently from existing environmental analyses, all stages of the product life cycle have been considered in building the database; moreover, the model provides quantitative results. Regression models and supervised algorithms were used. The obtained model can be used by product engineers, as well as those not experts on LCA. Moreover, the model guarantees the database and hypothesis’s uniqueness, ensuring the results coherence and comparability. The level of accuracy obtained in the case study (error or 17%) is comparable with studies handling full environmental analysis (that should be more accurate), and outstanding, as the present case is for the design phase. Future works will focus on additional significative indicators, similar electric vehicle design and integration with prospective LCA approaches. | | | Keywords:
Machine learning
Data science Environmental sustainability Eco-design
Life cycle assessment | | | | 1. Introduction Leading the focus from improving the physical manufacturing processes to creating a digital representation of the physical processes to get better insights (Dalzochio et al., 2020), the fourth industrial revolution (I4.0) leveraged advancements in production facilities through the inclusion of big data analysis, information technology, Internet of Things (IoT) and Additive Manufacturing (AM) (Ivanov et al., 2021). Automated and interconnected machinery and many digital technologies brought a consistent contribution to process optimization; however, their construction may require critical materials and their use phase much electricity. The design process is critical in enabling an improvement of their performances along their lifecycle and early design decisions can have a very significant impact on sustainability. Design processes are complex and conducting a Life Cycle Assessment (LCA) is also a complex task. Merging these two processes with proper theoretical knowledge will lead to the successful integration of LCA into early product design stages (Ostad Ahmad Ghorabi et al., 2009). Machine Learning (ML) is one area of data science that can be used to fill the gapsin environmental analysis and therefore support the design process. 1.1. Design, environmental assessment, and electric vehicles Assessing the viability of a product should extend beyond traditional design considerations lik

FAQs

What gap does the paper address in environmental impact assessment for electric vehicles?

It addresses the lack of machine learning-based methods that can forewarn lifecycle environmental impacts during the design phase, since prior work mainly focuses on use phase or battery life.

How does the proposed method combine LCA and machine learning?

It merges Life Cycle Assessment (LCA) with machine learning to build predictive models using design features of a generic electric vehicle.

What modeling workflow and algorithms does the study use?

The approach follows six phases—problem definition, data collection, data preparation, modeling, model evaluation, and model interpretation—and uses regression models and supervised learning algorithms.

Aug 3, 2026

Upload by Valentina