Review outlines fabrication methodologies and machine learning applications for enhancing perovskite solar cell performance.
Metal halides are prominent candidates for next-generation photovoltaics, especially due to the tuneable bandgap, strong absorption, plus defect tolerance. Power consumption efficiency has advanced beyond 25% of single-junction Perovskite solar cell, and the certified efficiency reached 28% for Perovskite/silicon tandem devices, showing the competitiveness of Perovskite film with silicon technology. Despite rapid progress, large-scale deployment is limited by challenges in film uniformity, long-term stability, and sustainable processing. This review outlines advances in scalable thin-film deposition, including blade layering, slot-die coating, vapour-assisted growth, and spray-based approaches, emphasising their influence on crystallisation, morphology, and device performance. Aerosol-assisted and ultrasonic spray coating demonstrate particular promise for large areas over 40 cm2, and the efficiency up to 15.5% makes it a high-quality film with industrial relevance. Complementarily, ML has arisen as a powerful tool for accelerating new materials innovation, enabling predictive modelling of composition, defect energetics, and carrier transport with reduced cost and time. ML-driven technology reduces the experimental space, time, and cost by up to 99% while optimising the fabrication parameters such as composition of materials, coating temperature, annealing time, scalable deposition, improve yield. The integration of scalable fabrication with AI-driven optimisation offers a practical pathway towards effective solar cells for industrial application.
No takes yet. Share an insight, caveat, or question.
Lande et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: