A Latent Space Framework for Modeling Transient Engine Emissions Using Joint Embedding Predictive Architectures

TL;DR

This paper presents a novel latent space modeling framework using Joint Embedding Predictive Architectures to improve transient engine emission predictions, achieving higher accuracy and efficiency than traditional methods for real-time vehicle control.

Contribution

It introduces a structured latent space approach with JEPA for modeling emission dynamics, enhancing data efficiency, accuracy, and computational efficiency over existing models.

Findings

Outperforms LSTM baselines in predictive accuracy and generalization.

Supports pruning and quantization for real-world deployment.

Reduces inference time and memory with negligible accuracy loss.

Abstract

Accurately modeling and controlling vehicle exhaust emissions during transient events, such as rapid acceleration, is critical for meeting environmental regulations and optimizing powertrains. Conventional data-driven methods, such as Multilayer Perceptrons (MLPs) and Long Short-Term Memory (LSTM) networks, improve upon phenomenological models but often struggle with the complex nonlinear dynamics of emission formation. These monolithic architectures are sensitive to dataset variability and typically require deep, computationally expensive structures to perform well, limiting their practical utility. This paper introduces a novel approach that overcomes these limitations by modeling emission dynamics within a structured latent space. Leveraging a Joint Embedding Predictive Architecture (JEPA), the proposed framework learns from a rich dataset that combines real-world Portable Emission Measurement System (PEMS) data with high-frequency hardware-in-the-loop measurements. The model abstracts away irrelevant noise, encoding only the key factors governing emission behavior into a compact, robust representation. This results in superior data efficiency and predictive accuracy across diverse transient regimes, significantly outperforming high-performing LSTM baselines in generalization. To ensure suitability for real-world deployment, the JEPA framework is structured to support pruning and post-training quantization. This strategy drastically reduces the computational footprint, minimizing inference time and memory demand with negligible accuracy loss. The result is a highly efficient model ideal for on-board implementation of advanced strategies, such as model predictive control or model-based reinforcement learning, in conventional and hybrid powertrains. These findings offer a clear pathway toward more robust emission control systems for next-generation vehicles.