The global shift toward sustainable transport electric vehicles (EVs) is at the core of decarbonization efforts. While advanced economies have achieved their rapid adoption through strong policies and incentives, emerging markets face structural and behavioral barriers. This study investigates the paradox in Morocco, whereby a significant automotive capacity contrasts with a minimal domestic BEV market share of 0.6%, despite 143% growth from a small base, using a four-dimensional framework encompassing financial, infrastructural and energy, policy and institutional, and behavioral–social factors. The research integrates a literature review, a survey (n = 522), and secondary data on charging infrastructure and EV sales. Findings reveal a strong value–action gap: 69% of respondents acknowledged EVs’ environmental benefits yet only 1.1% owned one and 42% had considered buying. The high upfront costs of EVs influenced over 70% of participants, and a significant association was confirmed between charging availability and purchase intent (χ² = 34.80, p < 0.05). Urban-centric charging, fragmented governance, and skepticism persist as barriers. The study concludes that industrial strength alone cannot ensure adoption without targeted incentives, equitable infrastructure, and cultural shifts in ownership perception, offering key insights for policymakers in emerging economies pursuing sustainable mobility.

Accurate State-of-Health (SOH) prediction is essential for deploying retired electric vehicle batteries into reliable second-life energy storage systems. However, this task is challenged by sparse and noisy operational data from onboard Battery Management Systems (BMS). This study systematically evaluates a spectrum of deep learning architectures for SOH forecasting under BMS-style data constraints derived from laboratory cycling data: a BiLSTM on aggregated cycle statistics (Model A), preliminary zero-shot transfer to a single unseen cell (Model B), a waveform BiLSTM with full intra-cycle voltage, current, and temperature trajectories (Model C), a baseline TCN (Model D) and a probabilistic TCN-GPR hybrid (Model E). All models are constrained to identical low-fidelity BMS-style variables extracted from the NASA battery aging dataset. Model C achieves the lowest point accuracy error of 0.46% ± 0.18% MAE across five random seeds, demonstrating that high-resolution waveform inputs capture degradation signatures, notably voltage plateau morphology, transient dynamics, and implicit SOC information, that aggregated features irreversibly lose. Model D using the same waveform inputs and evaluation protocol as Model C, achieves a MAE of 2.99% at a single seed, providing direct architectural comparison evidence that the BiLSTM’s position-sensitive temporal summarization outperforms GlobalAveragePooling1D under these conditions. Model E achieves a higher MAE of 2.12% ± 0.33% but uniquely provides calibrated predictive distributions of 99.4% ± 1.2% coverage, NLL = −1.877 ± 0.038, with approximately uniform 95% predictive intervals (mean width 19.83% SOH across 34 test cycles at seed = 42), reflecting the near-constant posterior variance produced by the large optimized GPR length-scale under the frozen two-stage training design. A paired t-test confirms that Model C statistically significantly outperforms Model E on point accuracy (p < 0.01). Isotonic regression recalibration reduces mean calibration error from 0.138 to 0.010, demonstrating that shape-level miscalibration is correctable post hoc. The central implication for second-life battery deployment is a clear accuracy–uncertainty trade-off: Model C is preferred when point estimates suffice, while Model E is essential for risk-aware decisions requiring confidence intervals.