Method for predicting carbon dioxide electroreduction copper alloy catalyst

The invention discloses a method for predicting a carbon dioxide electroreduction copper alloy catalyst, belongs to the field of carbon dioxide electrochemical reduction, and overcomes the problems of low efficiency and poor selectivity by applying density functional theory calculation and machine learning. According to the method, the surface structures of different types of CuM alloys are optimized, and the adsorption energy of key intermediates (CO, HCOO, COOH and H) of a CO2 reduction reaction on each surface is calculated by applying a density functional theory. In order to reduce the spatial dimension of the features, feature parameters of five materials, including a work function (W), an atomic number (AN), an interplanar spacing (d), electronegativity (EN) and local electronegativity (xi), are selected, a gradient boosting regression (GBR) model with good prediction performance is obtained through machine learning training, and a training result is close to the prediction performance of a model contai