Optimizing Market Scenarios for Battery Electric Vehicles through a Machine Learning based Manufacturer Agent

Abstract

The automotive industry is transitioning to electromobility to meet the global climate goals by 2050. This shift is changing people's purchasing priorities and the composition of the vehicle market. The manufacturers are therefore at a critical point in terms of product development and resource and supply chain management, requiring a deeper understanding of future vehicle design. To analyze possible upcoming vehicle models, a machine learning based manufacturer agent was developed, incorporating a comprehensive technology database and historical vehicle data. Over 3,000 new battery electric vehicle models are generated and evaluated according to their possible year of market entry. The most relevant models are then integrated into the VECTOR21 vehicle technology scenario model to assess their market potential against competing drivetrain types. The results of the battery diversification scenario show a market share for vehicles with lithium iron phosphate cell chemistry of more than 18% in 2030, while nickel rich cells will remain competitive especially in the long-range vehicle variants with up to 53% market potential by 2035. Vehicles that feature sodium-ion batteries could capture a market share of around 9% by 2030, with a potential to increase to more than 17% if cell prices would fall below 50 EUR/kWh. As long as there is no disruptive increase in energy density or a noticeable reduction in expected production costs, the market potential for solid state batteries in the German passenger vehicle market would only be 2% in 2035.