Journal Article

FZJ-2025-05268

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Demystifying data-driven approaches for battery electric transportation: Challenges and future directions

Liaw, B. (Corresponding author)FZJ* ; Li, W. ; Raijmakers, L.FZJ* ; Yan, L. ; Ali Ali, H. A. ; Windmüller, A.FZJ* ; Tsai, C.-L.FZJ* ; Sauer, D. U.RWTH* ; Eichel, R.-A.FZJ*RWTH*

2025
Elsevier Amsterdam [u.a.]

This record in other databases:    

Please use a persistent id in citations: doi:10.1016/j.etran.2025.100501

Abstract: Data-driven techniques leveraging artificial intelligence (AI) and machine learning (ML) are growing as favorable approaches to overcome challenges in predicting complicated behaviors of battery systems. Yet the data-driven approaches continue to face stiff challenges, including the difficulties in acquiring exhausting resources for data acquisition, managing escalating data quality issues to build robust data-driven capability, and sharing multimodal data from a variety of sources using wide ranges of test and operating conditions, and the lack of a reliable framework to verify and validate data consistency so the accuracy of the heuristic data reductions could be assessed. These challenges undermine the reach of a cost-effective and robust approach to predict battery performance and life with high fidelity for battery management. Here, we look into the root of these challenges and provide exemplified guidance to shed light on future directions, aiming for addressing these issues effectively.

---

Contributing Institute(s):

1. Grundlagen der Elektrochemie (IET-1)

Research Program(s):

1. 1223 - Batteries in Application (POF4-122) (POF4-122)

Appears in the scientific report 2025

---

Database coverage:
Clarivate Analytics Master Journal List ; Current Contents - Engineering, Computing and Technology ; Essential Science Indicators ; Nationallizenz ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---