Life Cycle Management from Global to Local | 2026
Authors: Echazarreta J.M.; Peña C.
DOI: 10.1007/978-3-032-17987-6_9
Journal: Life Cycle Management from Global to Local
Year: 2026
Publisher: Springer Science+Business Media
Document Type: Book chapter
Open Access: All Open Access; Gold Open Access
Cited by: 0
This paper explores the adoption of new technologies to improve consistent and reliable verification of environmental performance indicators of products and services. Life Cycle Assessment (LCA) Critical Review (CR) for Environmental Product Declaration (EPD) verification aimed at providing reliable information on environmental performance of products and services. There is a need to improve accuracy, facilitating comparability of results between EPDs, as well as ensure impartiality and transparency of the process. Using Artificial Intelligence (AI) and Machine Learning (ML) for auditing EPD verification processes can establish an effective framework for EPD Program Operators (POs) to validate the work of verifiers, improve the quality of EPDs, and promote continuous improvement and timesaving in the new era of massive EPD publication. AI and ML tools offer the ability to leverage vast datasets and address complex, multidimensional issues in LCA projects. These technologies can validate Life Cycle Inventory (LCI) data by identifying, isolating, and rectifying errors, inconsistencies, and outliers, as demonstrated in numerous case studies. Algorithms can also support the auditing of the CR process, correcting mistakes and preventing distortions by minimizing the risk of human error. The ML framework, aligned with ISO 14071 and ISO 17029 standards, enhances direct and efficient oversight of verifiers, maintaining the impartiality of the process and further reducing the potential for human mistakes. This integration not only improves accuracy but also streamlines the verification process, offering a more reliable and objective assessment of environmental performance. Furthermore, the paper emphasizes the necessity for POs to integrate these new tools to keep pace with emerging trends and future challenges, making EPDs remain effective and relevant. © The Editor(s) (if applicable) and The Author(s) 2026.
Artificial intelligence; Benchmarking; Environmental technology; Errors; Information systems; ISO Standards; Learning systems; Life cycle; Life cycle assessment; Artificial intelligence learning; Block-chain; Continuous improvements; Critical review; Environmental performance; Environmental performance indicators; Environmental product declarations; Machine-learning; Product and services; Verification process; Environmental management