AI-Centered Circular Economy Systems & Solutions (ACCESS)

A Hybrid Deep Learning and Quantum-Optimization Framework for Predictive Modelling of Biogas-Based Energy Harvesting: A Farm-Scale Anaerobic Co-Digestion CHP Case Study

2026-09-29T11:14:10+02:00

Accurate forecasting of the electrical energy harvested from biogas-fuelled combined heat and power (CHP) plants is central to the economic and operational viability of anaerobic digestion (AD) as a dispatchable renewable energy pathway, yet the process is governed by strongly non-linear, multi-parameter microbial kinetics that are difficult for purely classical predictive models to capture and expensive to tune. This paper develops and evaluates a hybrid quantum-classical machine-learning framework, coupling a custom convolutional-recurrent deep neural network (“DeepEnergyNet”: 1-D convolution, long short-term memory and additive temporal attention, implemented and back-propagated from first principles) with two quantum optimisation components: a Quantum Approximate Optimization Algorithm (QAOA), simulated exactly on a 12-qubit state-vector, that solves a maximum-relevance-minimum-redundancy Quadratic Unconstrained Binary Optimization (QUBO) for process-variable feature selection; and Quantum-behaved Particle Swarm Optimization (QPSO) that tunes the network's hyperparameters. The framework is demonstrated on a literature-calibrated, physically consistent operational case study of a 3000 m³ farm-scale anaerobic co-digestion CHP plant (N = 6000 hourly records), built from published modified-Gompertz kinetics and IWA Anaerobic Digestion Model No. 1 (ADM1)-informed inhibition relationships, with injected sensor noise, missing data and outliers to emulate a real SCADA export. QAOA selected a physically interpretable 7-of-12 feature subset (best-observed-shot approximation ratio 0.9996 relative to the exact brute-force optimum), and QPSO converged the network's five hyperparameters within ten swarm iterations. On a chronologically held-out test partition, the resulting hybrid model (DL+QAOA+QPSO) achieved RMSE = 59.81 kWh, MAE = 41.55 kWh, MAPE = 12.82% and R² = 0.754, improving on an untuned deep-learning baseline (RMSE = 61.56 kWh) and on each quantum component applied in isolation, while converging in fewer training epochs (33 vs. 47). The hybrid framework narrowed the gap to a Random Forest benchmark (RMSE = 57.64 kWh) while offering, in addition, an interpretable and computationally economical route to feature and hyperparameter selection. All back-propagation gradients were verified against finite-difference estimates (maximum relative error 3.4×10⁻⁸) prior to use. These findings indicate that quantum-classical coupling is a practically viable and physically interpretable strategy for renewable-energy time-series forecasting, and outline a pathway toward NISQ-hardware validation of the QAOA component.

Artificial Intelligence at the Core of Circular Futures: Introducing ACCESS

2026-09-13T22:10:45+02:00

The accelerating convergence of artificial intelligence (AI) and the circular economy marks a decisive shift in how societies design, manage, and regenerate economic systems under planetary constraints. AI-Centered Circular Economy Systems & Solutions (ACCESS) is launched to serve as a dedicated, international, open-access platform for rigorous and impactful research at this critical intersection. This inaugural editorial outlines the intellectual vision, thematic scope, and scholarly mission of ACCESS. It situates the journal within contemporary debates on sustainability, digital transformation, and systems thinking, while highlighting foundational research streams that inform AI-enabled circular strategies—ranging from consumer behavior and community-driven business models to supply chain resilience, stakeholder governance, agricultural intelligence, and digitalized waste management. ACCESS also aspires to function as a scientific bridge between East Asia and the European Union, fostering cross-regional collaboration and joint innovation. By emphasizing ethical publishing, interdisciplinary integration, and real-world relevance, ACCESS aims to accelerate the transition toward intelligent, data-driven, and regenerative economic systems.

A Coupled System Dynamics and Strategic Management Framework for Global Wind Energy Diffusion: Technology Learning, Grid Integration, and Adaptive Policy Control

2026-09-29T09:29:27+02:00

Global wind power deployment has grown by more than fifty-fold since 2000, yet strategic decision-makers still lack an integrated, quantitative framework that jointly represents technology learning, grid-integration constraints, and the feedback effects of policy intervention. This paper develops a coupled system dynamics (SD) and strategic-management model of the global wind-energy system, comprising eight interacting stocks: installed capacity, cumulative investment, research and development (R&D) knowledge, grid-integration capacity, social/political acceptance, skilled workforce, cumulative avoided CO2 emissions, and a policy-controller state. Technology cost is represented by a two-factor learning curve combining learning-by-doing and learning-by-searching; adoption follows a logistic-plus-imitation diffusion structure; and grid congestion is represented as an explicit balancing feedback loop. A strategic-management layer is implemented as a proportional-integral (PI) feedback controller that adjusts a feed-in premium in response to the gap between installed capacity and an aspirational deployment trajectory. The model is calibrated by non-linear least squares against 2001-2024 global capacity statistics (mean absolute percentage error of 8.6%) and used to compare a passive Business-as-Usual strategy against Adaptive and Aggressive strategic-management archetypes to 2050, alongside a constrained strategic-optimisation exercise and a systematic sensitivity/uncertainty analysis. Results show that closed-loop strategic management can raise 2050 installed capacity by approximately 37% relative to Business-as-Usual while simultaneously lowering the levelised cost of energy by about 22%, and that active feedback control substantially reduces the sensitivity of projected capacity to structural behavioural uncertainty, concentrating outcome risk instead in the technical deployment ceiling and the capital-mobilisation adjustment time. A formal optimisation of the policy levers further shows that a research-and-development-intensive strategy can achieve comparable deployment at a fraction of the cumulative public subsidy required by an unoptimised feed-in-tariff-led strategy.