The photovoltaic performance of perovskite solar cell is determined by multiple interrelated factors,such as perovskite compositions,electronic properties of each transport layer and fabrication parameters,which makes it rather challenging for optimization of device performances and discovery of underlying mechanisms.Here,we propose and realize a novel machine learning approach based on forward-reverse framework to establish the relationship between key parameters and photovoltaic performance in high-profile MASnxPb1-xI3 perovskite materials.The proposed method establishes the asymmetrically bowing relationship between band gap and Sn composition,which is precisely verified by our experiments.Based on the analysis of structural evolution and SHAP library,the rapid-change region and low-bandgap plateau region for small and large Sn composition are explained,respectively.By establishing the models for photovoltaic parameters of working photovoltaic devices,the deviation of short-circuit current and open-circuit voltage with band gap in defective-zone and low-bandgap-plateau regions from Shockley-Queisser theory is captured by our models,and the former is due to the deep-level traps formed by crystallographic distortion and the latter is due to the enhanced susceptibility by increased Sn4+content.The more difficulty for hole extraction than electron is also concluded in the models and the prediction curve of power conversion efficiency is in a good agreement with Shockley-Queisser limit.With the help of search and optimization algorithms,an optimized Sn:Pb composition ratio near 0.6 is finally obtained for high-performance perovskite solar cells,then verified by our experiments.Our constructive method could also be applicable to other material optimization and efficient device development.

Xia Cai;Fengcai Liu;Anran Yu;Jiajun Qin;Mohammad Hatamvand;Irfan Ahmed;Jiayan Luo;Yiming Zhang;Hao Zhang;Yiqiang Zhan

School of Information Science and Technology,Fudan University,Shanghai 200433,China;College of Information,Mechanical and Electrical Engineering,Shanghai Normal University,Shanghai 200234,China;Center of Micro-Nano System,Fudan University,Shanghai 200433,China;Department of Physics,Chemistry and Biology,Link?ping University,Link?ping SE-58183,Sweden;Key Laboratory of Micro and Nano Photonic Structures and Department of Optical Science and Engineering,Fudan University,Shanghai 200433,China;Yiwu Research Institute of Fudan University,Chengbei Road,Yiwu City,Zhejiang 322000,China

光：科学与应用（英文版）

[1]Xia Cai;Fengcai Liu;Anran Yu;Jiajun Qin;Mohammad Hatamvand;Irfan Ahmed;Jiayan Luo;Yiming Zhang;Hao Zhang;Yiqiang Zhan-.Data-driven design of high-performance MASnxPb1-xI3 perovskite materials by machine learning and experimental realization)[J].光：科学与应用（英文版）,2022(09):2115-2126

MASnxPb1,xI3,Sn4+content

Data,driven,design,high,perovskite,materials,by,machine,learning,experimental,realization,photovoltaic,solar,determined,multiple,interrelated,factors,such,compositions,electronic,properties,each,transport,layer,fabrication,parameters,which,makes,rather,challenging,optimization,performances,discovery,underlying,mechanisms,Here,realize,novel,approach,forward,reverse,framework,relationship,between,key,profile,proposed,method,establishes,asymmetrically,bowing,precisely,verified,our,experiments,Based,analysis,structural,evolution,SHAP,library,rapid,change,low,bandgap,plateau,small,large,are,explained,respectively,By,establishing,models,working,devices,deviation,short,circuit,current,open,voltage,defective,zone,regions,from,Shockley,Queisser,theory,captured,former,due,deep,level,traps,formed,crystallographic,distortion,latter,enhanced,susceptibility,increased,more,difficulty,hole,extraction,than,also,concluded,prediction,curve,power,conversion,efficiency,good,agreement,limit,With,help,search,algorithms,optimized,ratio,near,finally,obtained,cells,then,Our,constructive,could,applicable,other,efficient,development

0.548921