Designing and understanding light-harvesting devices with machine learning

Häse, Florian; Roch, Loı̈c M.; Friederich, Pascal; Aspuru‐Guzik, Alán

doi:10.1038/s41467-020-17995-8

Cited by 82 publications

(47 citation statements)

References 144 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This choice of properties reects potential design objectives for organic photovoltaics. 54 HOMO-LUMO gap and LUMO energies determine the energy of light absorption and acceptor ability, respectively, while dipole moment can be considered a crude proxy for intermolecular interaction strength. We simulated these properties using the semiempirical GFN2-xTB quantum chemistry method 55 (see details in the Methods Section †).…”

Section: Median Molecules For Photovoltaicsmentioning

confidence: 99%

Beyond generative models: superfast traversal, optimization, novelty, exploration and discovery (STONED) algorithm for molecules using SELFIES

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Median Molecules For Photovoltaicsmentioning

confidence: 99%

Beyond generative models: superfast traversal, optimization, novelty, exploration and discovery (STONED) algorithm for molecules using SELFIES

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…In general, such advanced materials are developed based on inspiration from past research and extensive trial‐and‐error experiments; however, a complete survey of target materials including the never‐explored molecular space is difficult due to the high risks involved and limited resources. Recently, the meteoric rise of machine learning (ML) technology has attracted the attention of the organic electronics community, [ 1–5 ] as it allows rapid virtual screening and is much faster than quantum mechanical (QM) calculations. Moreover, ML algorithms can instantaneously give an answer by considering big data, which is impossible for human brains.…”

Section: Introductionmentioning

confidence: 99%

Experiment‐Oriented Machine Learning of Polymer:Non‐Fullerene Organic Solar Cells

Kranthiraja

Saeki

2021

Adv Funct Materials

View full text Add to dashboard Cite

Despite the capacity of conjugated materials for enhanced power conversion efficiency (PCE) of organic photovoltaics (OPV), a comprehensive survey of unexplored materials is beyond the reach of most researchers’ resources. In such instances, a data‐driven approach using machine learning (ML) is an efficient alternative; however, bridging the gap between experimental observations and data science requires a number of refinements. In this investigation, using a random forest model based on an experimental dataset, a high correlation coefficient of 0.85 is achieved for the ML of polymer and non‐fullerene small molecule acceptor OPVs and performed virtual screening of 200,932 conjugated polymers generated by the combinatorial coupling of donor and acceptor units. Further, to evaluate the effectiveness of the ML model, a series of conjugated polymers (based on benzodithiophene and thiazolothiazole) were designed, synthesized, and characterized with different alkyl chains. Among these, PBDTTzEH:IT‐4F showed a PCE of 10.10%, which is in good correspondence with ML predictions with respect to the choice of alkyl chains. Thus, the current study demonstrates how ML can be utilized for developing OPVs using a relatively small number of experimental data points (566) and screening numerous molecular structures.

show abstract

“…As an application example, we considered the organic photovoltaic dataset form the Harvard Clean Energy (HCE) project [25], and identified 100 sets of three molecules (triplets) such that the first has a high lowest unoccupied molecular orbital (LUMO) energy, the second a high dipole moment, and the third a high energy difference between the highest occupied molecular orbital (HOMO) and LUMO energies (HOMO-LUMO gap), while having low values for the respective other two properties. This choice of properties reflects potential design objectives for organic photovoltaics [48]. HOMO-LUMO gap and LUMO energies determine the energy of light absorption and acceptor ability, respectively, while dipole moment can be considered a crude proxy for intermolecular interaction strength.…”

Section: E Median Molecules For Photovoltaicsmentioning

confidence: 99%

Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules using SELFIES

Nigam

Pollice²,

Krenn³

et al. 2021

Preprint

View full text Add to dashboard Cite

Inverse design allows the design of molecules with desirable properties using property optimization. Deep generative models have recently been applied to tackle inverse design, as they possess the ability to optimize molecular properties directly through structure modification using gradients. While the ability to carry out direct property optimizations is promising, the use of generative deep learning models to solve practical problems requires large amounts of data and is very time-consuming. In this work, we propose STONED – a simple and efficient algorithm to perform interpolation and exploration in the chemical space, comparable to deep generative models. STONED bypasses the need for large amounts of data and training times by using string modifications in the SELFIES molecular representation. We achieve comparable performance on typical benchmarks without any training. We demonstrate applications in high-throughput virtual screening for the design of drugs, photovoltaics, and the construction of chemical paths, allowing for both property and structure-based interpolation in the chemical space. We anticipate our results to be a stepping stone for developing more sophisticated inverse design models and benchmarking tools, ultimately helping generative models achieve wide adoption.

show abstract

Designing and understanding light-harvesting devices with machine learning

Cited by 82 publications

References 144 publications

Beyond generative models: superfast traversal, optimization, novelty, exploration and discovery (STONED) algorithm for molecules using SELFIES

Beyond generative models: superfast traversal, optimization, novelty, exploration and discovery (STONED) algorithm for molecules using SELFIES

Experiment‐Oriented Machine Learning of Polymer:Non‐Fullerene Organic Solar Cells

Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules using SELFIES

Contact Info

Product

Resources

About