Assessing the Circular Economy Transition in the EU

Predictive Insights From an Artificial Neural Network Model

Bibliographic Data

ID12307190
AuthorsPaolo Pariso (0000-0003-1066-4102, Engineering Department University of Campania “Luigi Vanvitelli” Aversa Caserta Italy, corresponding author), Alfonso Marino (0000-0003-1722-0539, Engineering Department University of Campania “Luigi Vanvitelli” Aversa Caserta Italy)
Year2025
Volume34
IssueS1
Pages538-556
Publication date2025-09-01
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueSustainable Development (JOURNAL)
Journal identifiersISSN: 0968-0802 • E-ISSN: 1099-1719
PublisherWiley (PUBLISHER • GB)
DOI10.1002/sd.70163
OpenAlexW4413900114
LanguageEN
Citations received2
References cited61

The transition to a circular economy (CE) is a critical component of the European Union's (EU) sustainability agenda, aiming to reduce resource dependency, enhance waste management efficiency, and foster innovation‐driven circular business models. This study employs an artificial neural network (ANN) model to assess the CE performance of the 27 EU member states from 2014 to 2023 and forecast their trajectories for 2030. By integrating four key dimensions—Waste Management, Secondary Raw Materials, Competitiveness and Innovation, and Global Sustainability and Resilience—the study comprehensively evaluates circularity trends, identifies regional disparities, and highlights the structural barriers impeding progress. The ANN model demonstrates strong predictive accuracy ( R 2 ranging from 0.76 to 0.92), supporting reliable future projections. The analysis reveals a heterogeneous transition, with leading nations demonstrating sustained improvements in waste management, secondary material integration, and innovation capacity while lower‐performing countries continue to face institutional and structural barriers. While waste recycling rates have increased, the reintegration of secondary raw materials into production cycles remains limited, highlighting disparities between waste recovery efforts and industrial material reuse. The study also identifies the role of governance and policy coherence as fundamental in shaping CE trajectories. The findings suggest that while some EU Member States are on track to meet the 2030 CE targets, others require targeted policy interventions, including enhanced financial incentives, regulatory alignment, and capacity‐building measures. The study underscores the need for a multidimensional governance approach to ensure a balanced and inclusive CE transition across Europe

Artificial neural network · Biology · Economics · Transition (genetics · Computer Science · Energy, Environment, Economic Growth · Sustainable Supply Chain Management · Artificial Intelligence · Biochemistry

Tools

Open DOIOpen Access