Abstract:An adequate understanding of molecular structure− property relationships is important for developing new molecules with desired properties. Although deep learning optical spectroscopy (DLOS) has been successfully applied to predict the optical and photophysical properties of organic chromophores, how specific functional groups and solvents affect the optical properties is not clearly understood. Here, we employed an explainable DLOS method by applying the integrated gradients method to DLOS. The integrated gra… Show more
Optimizing light utilization is crucial in organic photovoltaics. Understanding the intricate connection between the optical properties and the chemical structure of organic materials is pivotal yet challenging in this regard. In this work, we survey over 2800 published reports with a database of ∽300 organic non‐fullerene acceptors (NFAs), and establish a mathematical model suitable for prediction and analyzing the optical properties of organic photovoltaic materials. We employ the model to predict the optical properties of representative NFAs within experimental error, including four newly synthesized organic materials to validate the model. In addition, we demonstrate the reliability and applicability of the model through data transformation and find that the addition of double bonds and asymmetry in the chemical structure does not necessarily reduce the optical bandgap of organic materials. Based on the model, we propose that the strong non‐covalent interaction is more significant than the weak non‐covalent interaction and asymmetry on the reduction of the bandgap, which provides new insights into the design and development of organic photovoltaic materials with tunable optical properties.This article is protected by copyright. All rights reserved.
Optimizing light utilization is crucial in organic photovoltaics. Understanding the intricate connection between the optical properties and the chemical structure of organic materials is pivotal yet challenging in this regard. In this work, we survey over 2800 published reports with a database of ∽300 organic non‐fullerene acceptors (NFAs), and establish a mathematical model suitable for prediction and analyzing the optical properties of organic photovoltaic materials. We employ the model to predict the optical properties of representative NFAs within experimental error, including four newly synthesized organic materials to validate the model. In addition, we demonstrate the reliability and applicability of the model through data transformation and find that the addition of double bonds and asymmetry in the chemical structure does not necessarily reduce the optical bandgap of organic materials. Based on the model, we propose that the strong non‐covalent interaction is more significant than the weak non‐covalent interaction and asymmetry on the reduction of the bandgap, which provides new insights into the design and development of organic photovoltaic materials with tunable optical properties.This article is protected by copyright. All rights reserved.
Explainable artificial intelligence (XAI) has gained significant attention in various domains, including natural and medical image analysis. However, its application in spectroscopy remains relatively unexplored. This systematic review aims to fill this gap by providing a comprehensive overview of the current landscape of XAI in spectroscopy and identifying potential benefits and challenges associated with its implementation. Following the PRISMA guideline 2020, we conducted a systematic search across major journal databases, resulting in 259 initial search results. After removing duplicates and applying inclusion and exclusion criteria, 21 scientific studies were included in this review. Notably, most of the studies focused on using XAI methods for spectral data analysis, emphasizing identifying significant spectral bands rather than specific intensity peaks. Among the most utilized AI techniques were SHapley Additive exPlanations (SHAP), masking methods inspired by Local Interpretable Model-agnostic Explanations (LIME), and Class Activation Mapping (CAM). These methods were favored due to their model-agnostic nature and ease of use, enabling interpretable explanations without modifying the original models. Future research should propose new methods and explore the adaptation of other XAI employed in other domains to better suit the unique characteristics of spectroscopic data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.