From the Rock Floor to the Cloud: A Systematic Survey of State-of-the-Art NLP in Battery Life Cycle

TL;DR

The paper tackles the challenge of mapping natural language processing methods across the entire battery life cycle and the need for standardized data infrastructure to support lifecycle analytics. It adopts a PRISMA-based systematic review, spanning Google Scholar, IEEE Xplore, and Scopus, to screen 274 papers down to 66 relevant studies, and introduces a technical language processing (TLP) framework that combines AI agents, optimized prompts, and multimodal large language models for DBP- and battery-prediction tasks. Key contributions include the first comprehensive taxonomy of 16 NLP tasks along the life cycle, a synthesis of state-of-the-art results across 11 tasks, and a proposed framework to address standardization, transparency, and data interoperability challenges. The work offers practical guidance for researchers and policymakers, highlighting data sharing, benchmarking gaps, and the EU digital battery passport as a driver for AI-assisted, transparent battery lifecycle predictions with potential multimodal data enhancements in the future.

Abstract

We present a comprehensive systematic survey of the application of natural language processing (NLP) along the entire battery life cycle, instead of one stage or method, and introduce a novel technical language processing (TLP) framework for the EU's proposed digital battery passport (DBP) and other general battery predictions. We follow the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method and employ three reputable databases or search engines, including Google Scholar, Institute of Electrical and Electronics Engineers Xplore (IEEE Xplore), and Scopus. Consequently, we assessed 274 scientific papers before the critical review of the final 66 relevant papers. We publicly provide artifacts of the review for validation and reproducibility. The findings show that new NLP tasks are emerging in the battery domain, which facilitate materials discovery and other stages of the life cycle. Notwithstanding, challenges remain, such as the lack of standard benchmarks. Our proposed TLP framework, which incorporates agentic AI and optimized prompts, will be apt for tackling some of the challenges.

Figures (3)

• Figure 1: Battery life cycle (Images are ChatGPT-generated).
• Figure 2: prisma flow diagram for the systematic review.
• Figure 3: tlp framework for dbp and battery-related predictions.