Abstract: A solar dark green glass and a vehicle are provided. The solar dark green glass includes a glass basic component and a glass tinted component. The solar dark green glass includes a glass basic component and a mass tinted component. The glass tinted component includes, as percentages by weight, 0.8%-2.0% total iron expressed as Fe2O3, 0.01%-0.6% TiO2, 0.001%-2.0% CeO2, 5 ppm-150 ppm Cr2O3, 15 ppm-60 ppm Zro2, 2 ppm-1000 ppm CuO, 5 ppm-50 ppm SrO, 80 ppm-200 ppm BaO, and 5 ppm-120 ppm Co2O3. A content of total iron expressed as Fe2O3 and a content of TiO2 total 1.0%-2.0%, and the content of TiO2 and a content of CeO2 total 0.2%-2.1%. The solar dark green glass manufactured has a thickness of 1.6 mm-2.1 mm, and solar direct transmittance less than or equal to 65%, infrared transmittance less than or equal to 45%, and ultraviolet transmittance less than or equal to 35%.

Abstract: This disclosure relates to a method and apparatus for training a prediction model. The method includes: obtaining a training sample set; determining a current training sample from the training sample set based on the training sample weights; inputting current target energy characteristics corresponding to the current training sample into a pre-trained prediction model for basic training to obtain a basic prediction model after completing the basic training; updating the training sample weights corresponding to the training samples based on the basic prediction model; and returning to perform the operation of determining the current training sample from the training sample set based on the updated training sample weights until completing model training to obtain a target prediction model.

Abstract: This disclosure relates to a method and an apparatus for classification model training.