Novel environment-friendly insulating gas molecule screening method based on deep learning

The invention discloses a novel environment-friendly insulating gas molecule screening method based on deep learning. The novel environment-friendly insulating gas molecule screening method comprises the following steps: establishing a basic library of known gas molecule electrical environment-friendly properties; representing the gas molecules in the basic library by molecular descriptors to generate a molecular data matrix, and dividing the matrix into a training library and a test library; a deep learning model is built, the training library is used for training the deep learning model, and the test library tests the prediction precision of the trained deep learning model until the optimal deep learning model is obtained; generating new small molecular structures in batches from the gas molecules in the basic library through a functional group replacement method, and forming a gas molecule target library; adopting the optimal deep learning model to screen gas molecules in the gas molecule target library, a