Identifying Opportunities for Processing in Organic Photovoltaics by Machine Learning

Organic photovoltaics (OPVs) have the potential for high specific power, flexibility, and solution processability. Yet the factors governing OPVs fabrication require extensive optimization due to the interplay between chemistry, processing, morphology. Data analytics-based strategies can yield insight into the interplay between processing conditions and OPV performance metrics like power conversion efficiency (PCE). Poly[(2,6-(4,8-bis(5-(2-ethylhexyl-3-fluoro)thiophen-2-yl)-benzo[1,2-b:4,5-b']dithiophene))-alt-(5,5-(1',3'-di-2-thienyl-5',7'-bis(2-ethylhexyl)benzo[1',2'-c:4',5'-c']dithiophene-4,8-dione)] (PM6) and 2,2'-((2Z,2'Z)-((12,13-bis(2-ethylhexyl)-3,9-diundecyl-12,13-dihydro-[1,2,5]thiadiazolo[3,4-e]thieno[2",3'':4',5']thieno[2',3':4,5]pyrrolo[3,2-g]thieno[2',3':4,5]thieno[3,2-b]indole-2,10-diyl)bis(methanylylidene))bis(5,6-difluoro-3-oxo-2,3-dihydro-1H-indene-2,1-diylidene))dimalononitrile (Y6) OPV's were fabricated as a model system using 1-chloronaphthalene as a solvent additive. The combination of design of experiments and machine learning enables exploration and mapping of the PM6:Y6 parameter space. Furthermore, comparing the gradients in resulting device performance between candidate configurations enables identification of new opportunities for processing in OPV systems.