A review on solid–liquid triboelectric nanogenerators for energy harvesting with machine learning and deep learning-based design optimization

Solid-liquid triboelectric nanogenerators (SL-TENGs) provide a sustainable and clean solution to energy harvesting. This technology works on the phenomenon of electrostatic induction and contact electrification to harvest marine energy. TENG materials have high energy density and are suited for multidisciplinary applications. Translating laboratory-scale SL-TENGs into commercially viable technologies is currently impeded by 3 primary challenges: charge screening originating from the electrical double layer, poor long-term material stability, and the inherent impedance disparity between high-voltage generation and low-impedance storage. To address these bottlenecks, this review offers an analytical evaluation of recent technological progress in the field, moving beyond standard descriptive summaries. We investigate the combined effects of chemical surface modification and mechanical flexibility in maximizing both interfacial charge transfer and overall durability. Furthermore, we discuss the paradigm-shifting applications of machine learning and deep learning within this domain, emphasizing the utility of Physics-Informed Neural Networks in elucidating nonlinear interfacial phenomena and Generative Adversarial Networks in driving the targeted discovery of high-performance materials. By synthesizing fundamental interfacial mechanisms with cutting-edge computational frameworks, we deliver a definitive roadmap for realizing stable, high-output SL-TENGs. This review paves the way for transformative next-generation applications, advancing the viability of self-powered biomedical implants, expansive cathodic protection networks, and large-scale Blue Energy solutions.