Bridging artificial intelligence with photovoltaics
Source abstract
Abstract
Turning the significant possibilities presented by artificial intelligence (AI) into practical outcomes for sustainable-energy technology advancement remains challenging, as it requires bridging the independently developed energy and AI domains. This review leverages insights from the photovoltaics (PV) field to highlight the opportunities and challenges presented by AI while simultaneously providing an organized overview to AI researchers on the status of AI application in the PV domain. The current AI application landscape is classified according to the tasks and features required at each stage of PV development. The five major domains identified are material development, process development, fault diagnosis, PV power forecasting and planning, and operation and management. The status and challenges of AI applications are provided, highlighting imbalance in research fields, data dependency, the relationships between components of PV devices, and energy consumption of AI. Further advancements will hinge on our ability to enable AI to operate safely beyond existing datasets so that we can unlock its potential to explore uncharted territories in sustainable technologies and achieve a transformative impact. Lee et al. review how artificial intelligence (AI) connects with photovoltaics (PV). They identify five key domains—materials discovery, process optimization, fault diagnosis, power forecasting, and system management—and highlight challenges such as dependence on human-made data while outlining how AI can move beyond existing datasets to unlock future opportunities.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Photovoltaic System Optimization Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (100+)
Show source-provided references
1. I.—Computing Machinery and Intelligence10.1093/mind/LIX.236.433 ↗
2. Deep learning10.1038/nature14539 ↗
3. Goodfellow · 2016
4. Deep learning in neural networks: An overview10.1016/j.neunet.2014.09.003 ↗
5. Moore’s law: past, present and future10.1109/6.591665 ↗
6. Machine learning: Trends, perspectives, and prospects10.1126/science.aaa8415 ↗
7. ImageNet Classification with Deep Convolutional Neural Networks
8. Best Research-Cell Efficiency Chart NREL. https://www.nrel.gov/pv/(Assessed: September 2024).
9. Historical Analysis of High-Efficiency, Large-Area Solar Cells: Toward Upscaling of Perovskite Solar Cells10.1002/adma.202002202 ↗
10. 2023
11. IPCC, 2023: Climate Change 2023: Synthesis Report
12. International Technology Roadmap for Photovoltaic (ITRPV) - vdma.org - VDMA https://www.vdma.org/international-technology-roadmap-photovoltaic.
13. Accelerated design of promising mixed lead-free double halide organic–inorganic perovskites for photovoltaics using machine learning10.1039/D1NR01117K ↗
14. Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach10.1038/nmat4717 ↗
15. Toward Predicting Efficiency of Organic Solar Cells via Machine Learning and Improved Descriptors10.1002/aenm.201801032 ↗
16. Thermodynamic Stability Landscape of Halide Double Perovskites via High-Throughput Computing and Machine Learning
17. Design-to-Device Approach Affords Panchromatic Co-Sensitized Solar Cells
18. Identifying Pb-free perovskites for solar cells by machine learning10.1038/s41524-019-0177-0 ↗
19. Accelerated Development of Perovskite-Inspired Materials via High-Throughput Synthesis and Machine-Learning Diagnosis10.1016/j.joule.2019.05.014 ↗
20. Self-driving laboratory for accelerated discovery of thin-film materials10.1126/sciadv.aaz8867 ↗
21. Machine learning-guided search for high-efficiency perovskite solar cells with doped electron transport layers10.1039/D1TA08194B ↗
22. Perovskite- and Dye-Sensitized Solar-Cell Device Databases Auto-generated Using ChemDataExtractor10.1038/s41597-022-01355-w ↗
23. Machine-Learning-Assisted Screening of Interface Passivation Materials for Perovskite Solar Cells10.1021/acsenergylett.2c02818 ↗
24. Machine Learning Enables Prediction of Halide Perovskites’ Optical Behavior with >90% Accuracy10.1021/acsenergylett.2c02555 ↗
25. Beyond Ternary OPV: High-Throughput Experimentation and Self-Driving Laboratories Optimize Multicomponent Systems
26. Autonomous Chemical Experiments: Challenges and Perspectives on Establishing a Self-Driving Lab10.1021/acs.accounts.2c00220 ↗
27. Accelerating the discovery of materials for clean energy in the era of smart automation10.1038/s41578-018-0005-z ↗
28. Inverse molecular design using machine learning: Generative models for matter engineering10.1126/science.aat2663 ↗
29. How Machine Learning Predicts and Explains the Performance of Perovskite Solar Cells10.1002/solr.202101100 ↗
30. Autonomous optimization of an organic solar cell in a 4-dimensional parameter space10.1039/D3EE02027D ↗
31. Bayesian Optimization of photonic curing process for flexible perovskite photovoltaic devices10.1016/j.solmat.2022.112055 ↗
32. Data mining photovoltaic cell manufacturing data
33. Data-Driven Tunnel Oxide Passivated Contact Solar Cell Performance Analysis Using Machine Learning
34. Deep Learning approach to inline quality rating and mapping of multicrystalline Si-wafers
35. Determination of cutting parameters for silicon wafer with a Diamond Wire Saw using an artificial neural network10.1016/j.solener.2017.04.022 ↗
36. Discovering Process Dynamics for Scalable Perovskite Solar Cell Manufacturing with Explainable AI10.1002/adma.202307160 ↗
37. Learning Quality Rating of As-Cut mc-Si Wafers via Convolutional Regression Networks10.1109/JPHOTOV.2019.2906036 ↗
38. Machine Learning Enhanced High-Throughput Fabrication and Optimization of Quasi-2D Ruddlesden–Popper Perovskite Solar Cells
39. Machine Learning for Understanding Compatibility of Organic–Inorganic Hybrid Perovskites with Post-Treatment Amines10.1021/acsenergylett.8b02451 ↗
40. Machine learning with knowledge constraints for process optimization of open-air perovskite solar cell manufacturing10.1016/j.joule.2022.03.003 ↗
41. Machine-Learning-Accelerated Perovskite Crystallization10.1016/j.matt.2020.02.012 ↗
42. Optimization of Solar Cell Production Lines Using Neural Networks and Genetic Algorithms10.1021/acsaem.0c01207 ↗
43. Passivating contact-based tunnel junction Si solar cells using machine learning for tandem cell applications10.1016/j.egyai.2023.100299 ↗
44. Using machine learning for prediction of spray coated perovskite solar cells efficiency: From experimental to theoretical models10.1016/j.matdes.2023.112161 ↗
45. Process Insights into Perovskite Thin-Film Photovoltaics from Machine Learning with In Situ Luminescence Data10.1002/solr.202201114 ↗
46. Zhang, J., Chen, X., Wei, H., and Zhang, K. (2023). A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation. https://doi.org/10.48550/arXiv.2302.07455.10.1016/j.apenergy.2023.122184 ↗
47. A photovoltaic surface defect detection method for building based on deep learning
48. AI-assisted Cell-Level Fault Detection and Localization in Solar PV Electroluminescence Images
49. Anomaly detection and automatic labeling for solar cell quality inspection based on Generative Adversarial Network10.3390/s21134361 ↗
50. Automatic classification of defective photovoltaic module cells in electroluminescence images10.1016/j.solener.2019.02.067 ↗
51. CNN based automatic detection of photovoltaic cell defects in electroluminescence images10.1016/j.energy.2019.116319 ↗
52. Deep learning based automatic defect identification of photovoltaic module using electroluminescence images10.1016/j.solener.2020.03.049 ↗
53. Defects Inspection in Polycrystalline Solar Cells Electroluminescence Images Using Deep Learning10.1109/ACCESS.2020.2976843 ↗
54. Solar cell surface defect inspection based on multispectral convolutional neural network10.1007/s10845-018-1458-z ↗
55. A benchmark dataset for defect detection and classification in electroluminescence images of PV modules using semantic segmentation
56. Segmentation of photovoltaic module cells in uncalibrated electroluminescence images10.1007/s00138-021-01191-9 ↗
57. A deep learning-based forecasting model for renewable energy scenarios to guide sustainable energy policy: A case study of Korea10.1016/j.rser.2020.109725 ↗
58. Accurate photovoltaic power forecasting models using deep LSTM-RNN10.1007/s00521-017-3225-z ↗
59. An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting10.1109/ACCESS.2021.3062776 ↗
60. An Hour-Ahead PV Power Forecasting Method Based on an RNN-LSTM Model for Three Different PV Plants10.3390/en15062243 ↗
61. Application of extreme learning machine for short term output power forecasting of three grid-connected PV systems10.1016/j.jclepro.2017.08.081 ↗
62. Benefits of physical and machine learning hybridization for photovoltaic power forecasting10.1016/j.rser.2022.112772 ↗
63. Convergence of Photovoltaic Power Forecasting and Deep Learning: State-of-Art Review10.1109/ACCESS.2021.3117004 ↗
64. Deep Learning Enhanced Solar Energy Forecasting with AI-Driven IoT10.1155/2021/9249387 ↗
65. Deep photovoltaic nowcasting10.1016/j.solener.2018.10.024 ↗
66. Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements10.3390/en14133992 ↗
67. Forecasting Photovoltaic Power Generation with a Stacking Ensemble Model10.3390/su141711083 ↗
68. High resolution global spatiotemporal assessment of rooftop solar photovoltaics potential for renewable electricity generation10.1038/s41467-021-25720-2 ↗
69. Improved solar photovoltaic energy generation forecast using deep learning-based ensemble stacking approach10.1016/j.energy.2021.122812 ↗
70. Kernel learning for intra-hour solar forecasting with infrared sky images and cloud dynamic feature extraction
71. Large-scale rooftop solar photovoltaic technical potential estimation using Random Forests10.1016/j.apenergy.2018.02.118 ↗
72. PV power intra-day predictions using PDE models of polynomial networks based on operational calculus10.1049/iet-rpg.2019.1208 ↗
73. Random forest machine learning algorithm based seasonal multi-step ahead short-term solar photovoltaic power output forecasting
74. Review on the Application of Photovoltaic Forecasting Using Machine Learning for Very Short- to Long-Term Forecasting10.3390/su15042942 ↗
75. Solar Photovoltaic Power Forecasting: A Review10.3390/su142417005 ↗
76. Stacking Model for Photovoltaic-Power-Generation Prediction10.3390/su14095669 ↗
77. A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization10.1016/j.rser.2020.109792 ↗
78. A Machine Learning-Based Communication-Free PV Controller for Voltage Regulation10.3390/su132112208 ↗
79. A stacking ensemble classifier-based machine learning model for classifying pollution sources on photovoltaic panels
80. A novel image enhancement algorithm to determine the dust level on photovoltaic (PV) panels10.1016/j.renene.2022.10.073 ↗
81. Deep-Learning-Based Probabilistic Estimation of Solar PV Soiling Loss10.1109/TSTE.2021.3098677 ↗
82. Detection of cleaning interventions on photovoltaic modules with machine learning10.1016/j.apenergy.2020.114642 ↗
83. Detection of Faults in Solar Panels Using Deep Learning
84. Identification of surface defects on solar PV panels and wind turbine blades using attention based deep learning model10.1016/j.engappai.2023.107836 ↗
85. Intelligent cleanup scheme for soiled photovoltaic modules10.1016/j.energy.2022.126293 ↗
86. Monitoring Solar Panels using Machine Learning Techniques
87. Application of Artificial Intelligence in PV Fault Detection10.3390/su142113815 ↗
88. Design scenarios for integrated renewable energy systems10.1109/60.475847 ↗
89. Spier, R.J., Barton, J.R., and Liffring, M.E. Developments in Expert Systems for Advanced Power Control. In 22nd Intersociety Energy Conversion Engineering Conference (American Institute of Aeronautics and Astronautics). https://doi.org/10.2514/6.1987-9228.10.2514/6.1987-9228 ↗
90. Glass, B. Prototype for the Automation of Electrical Power Systems. In 22nd Intersociety Energy Conversion Engineering Conference (American Institute of Aeronautics and Astronautics). https://doi.org/10.2514/6.1987-9107.10.2514/6.1987-9107 ↗
91. Software survey: VOSviewer, a computer program for bibliometric mapping10.1007/s11192-009-0146-3 ↗
92. AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations10.1016/j.commatsci.2012.02.002 ↗
93. Commentary: The Materials Project: A materials genome approach to accelerating materials innovation10.1063/1.4812323 ↗
94. Crystallography Open Database – an open-access collection of crystal structures10.1107/S0021889809016690 ↗
95. The inorganic crystal structure data base10.1021/ci00038a003 ↗
96. The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies10.1038/npjcompumats.2015.10 ↗
97. A Critical Review of Machine Learning of Energy Materials10.1002/aenm.201903242 ↗
98. Machine Learning-Driven Insights for Phase-Stable FAxCs1–xPb(IyBr1–y)3 Perovskites in Tandem Solar Cells10.1021/jacsau.5c00033 ↗
99. A bilayer conducting polymer structure for planar perovskite solar cells with over 1,400 hours operational stability at elevated temperatures10.1038/s41560-021-00953-z ↗
100. Anion optimization for bifunctional surface passivation in perovskite solar cells10.1038/s41563-023-01705-y ↗