Machine Learning‐Assisted Optimization of Iodide Electrolytes for Efficient Indoor Dye‐Sensitized Solar Cells with Engineered Photoanodes
Abstract
Although dye-sensitized solar cells (DSSCs) have lower power conversion efficiencies than other emerging photovoltaic technologies under standard test conditions, they perform remarkably well under low light or artificial lighting. This makes them particularly well suited to indoor photovoltaics (IPVs) and powering Internet of Things (IoT) devices. The most efficient indoor DSSCs rely on copper-based redox shuttles to achieve high photovoltages; however, their long-term stability is still uncertain. In contrast, iodide-based electrolytes are robust under harsh and outdoor conditions, but under indoor illumination, they often deliver limited photovoltage. Here, we propose a strategy that combines an innovative photoanode architecture, designed to suppress charge recombination, with a design of experiments (DoE) approach that is integrated with machine learning (ML). This strategy is intended to optimize iodine-based electrolytes for high-performance IPVs. Support vector machines and Bayesian optimization were employed to accelerate development, achieving efficiencies surpassing 23% at 1000 Lx. As photovoltage is crucial for IoT applications, it was specifically targeted during ML optimization, achieving up to 683 mV at 500 Lx using an iodide/triiodide redox couple. Bayesian optimization also enabled the exploration of electrolyte formulation, achieving 713 mV at 1000 Lx. These results are among the highest reported for iodide/triiodide-based DSSCs under indoor lighting.
Related
- Selective Hydrogen Evolution Reaction in HMF-Containing Mild-Alkaline Electrolytes on Structurally Engineered MoS2@GNP Cathode Materials
- Kinetic Monte Carlo-Ising Machine Optimization for Atomistic Inverse Design of Solid Electrolytes.
- Laser-Engineered Ti/RuO2–Sb2O4–TiO2 Anodes Enabling Energy-Efficient Electrochemical Degradation of Thiamethoxam in Flow Reactors
- Synergistic Lewis Acid Photocatalysis Over Cluster‐Defect‐Engineered UiO‐66 for Efficient Liquid Biomass Upgrading
- Ruδ+-Engineered La2Ti2-xRuxO7 Perovskite with Dynamic Lattice Oxygen Vacancies for Efficient and Stable Photothermal Dry Reforming of Methane.
BibTeX
@article{mwalukuku2026machine,
title = {{Machine Learning‐Assisted Optimization of Iodide Electrolytes for Efficient Indoor Dye‐Sensitized Solar Cells with Engineered Photoanodes}},
author = {Valid Mwalukuku and Antonio Blanco and Cyril Aumaître and Yann Kervella and Said Hamad and Renaud Demadrille and Juan Anta},
journal = {Small Science},
year = {2026},
month = jun,
doi = {10.1002/smsc.70324},
url = {https://hal.science/hal-05775115v1},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine Learning‐Assisted Optimization of Iodide Electrolytes for Efficient Indoor Dye‐Sensitized Solar Cells with Engineered Photoanodes
AU - Valid Mwalukuku
AU - Antonio Blanco
AU - Cyril Aumaître
AU - Yann Kervella
AU - Said Hamad
AU - Renaud Demadrille
AU - Juan Anta
PY - 2026
DA - 2026/06/13
JO - Small Science
DO - 10.1002/smsc.70324
UR - https://hal.science/hal-05775115v1
AB - Although dye-sensitized solar cells (DSSCs) have lower power conversion efficiencies than other emerging photovoltaic technologies under standard test conditions, they perform remarkably well under low light or artificial lighting. This makes them particularly well suited to indoor photovoltaics (IPVs) and powering Internet of Things (IoT) devices. The most efficient indoor DSSCs rely on copper-based redox shuttles to achieve high photovoltages; however, their long-term stability is still uncertain. In contrast, iodide-based electrolytes are robust under harsh and outdoor conditions, but under indoor illumination, they often deliver limited photovoltage. Here, we propose a strategy that combines an innovative photoanode architecture, designed to suppress charge recombination, with a design of experiments (DoE) approach that is integrated with machine learning (ML). This strategy is intended to optimize iodine-based electrolytes for high-performance IPVs. Support vector machines and Bayesian optimization were employed to accelerate development, achieving efficiencies surpassing 23% at 1000 Lx. As photovoltage is crucial for IoT applications, it was specifically targeted during ML optimization, achieving up to 683 mV at 500 Lx using an iodide/triiodide redox couple. Bayesian optimization also enabled the exploration of electrolyte formulation, achieving 713 mV at 1000 Lx. These results are among the highest reported for iodide/triiodide-based DSSCs under indoor lighting.
SN - 2688-4046
ER -