The invention discloses an online forecasting method for quickly forecasting an organic-inorganic
hybrid perovskite band gap based on
machine learning, which comprises the following steps: establishing a sample set, generating a descriptor, dividing a
training set and a
test set, selecting a modeled optimal feature subset, constructing a quick forecasting model, forecasting the
band gap of a testset sample, developing an online forecasting application program, and rapidly predicting the organic-inorganic
hybrid perovskite band gap value. According to the method, an efficient and rapid forecasting model is established through sample data from a
database, an online forecasting application program for rapidly forecasting the organic-inorganic
hybrid perovskite is developed, the online forecasting application program can be accessed and used through a website and a
mobile phone WeChat two-dimensional code, and the method has the advantages of being simple, convenient, low in cost and
environmentally friendly. By using the application program to forecast the band gap of the organic-inorganic hybrid perovskite on line, experimental researchers can be helped to avoid
blindness of an experimental trial-and-error method, experimental time and cost are saved, and material research and development efficiency is improved.