Machine learning framework for the analysis and prediction of energy loss for non-fullerene organic solar cells

Indoor organic solar cells for low-power IoT devices: recent progress, challenges, and applications

“…Under low light conditions, high photovoltage loss (V loss = E g /q À V OC ) caused by a mismatch between the emission spectra of light sources and the absorption spectra of photoactive layers occurs, which leads to high losses in open circuit voltage. 13,79,80 The simulated V loss for the different illumination sources is shown in Fig. 2b, which indicates that the significant difference between V loss of AM 1.5G and the indoor light source.…”

“…nanomaterials, the power conversion efficiencies (PCEs) of organic solar cells (OSCs) have improved extremely quickly over the past few decades and are presently close to 20%. [1][2][3][4][5][6][7][8][9][10][11][12][13][14] However, these efficiencies are still lower than those of crystalline silicon and other inorganic solar cell technologies under standard illumination. [15][16][17][18][19] However, organic semiconductors offer several advantages that make these materials attractive for purposes other than large-scale power generation.…”

Machine-learning-guided prediction of photovoltaic performance of non-fullerene organic solar cells using novel molecular and structural descriptors

“…33,34,46–49 In recent years, ML has risen to fame in OSCs, and researchers have explored various data-driven ML approaches that focus on material energetics, prediction of photovoltaic parameters, materials design, etc. 40,41,50–56 Han et al developed an ML model using three material descriptors, i.e. , bandgap ( E g ), charge transfer driving force, and singlet–triplet energy gap, to predict the performance parameters.…”

“…33,34,[46][47][48][49] In recent years, ML has risen to fame in OSCs, and researchers have explored various data-driven ML approaches that focus on material energetics, prediction of photovoltaic parameters, materials design, etc. 40,41,[50][51][52][53][54][55][56] Han et al developed an ML model using three material descriptors, i.e., bandgap (E g ), charge transfer driving force, and singlet-triplet energy gap, to predict the performance parameters. 50 To predict Hansen solubility parameters, Mahmood et al investigated various ML models to accelerate the identication of eco-friendly solvents for organic solar cells.…”