Quantitative precipitation prediction based on radar echo extrapolation has broad prospects.It’s important to get accurate nowcasting.To this end,we propose GLnet,an efficient neural networksbased on Unet and SwinTransformer architecture equipped with two different attention modules CBAM and Nonlocal. The model has an asymmetric twoway feature extractor. In this way,the GLnet model extracts local and global features of radar echo images through convolution and windows selfattention mechanisms respectively.We create two datasets, NL20 and NL50, in Netherlands Precipitation Dataset by filtering the original precipitation dataset and choosing only the images with at least 20% and 50% of pixels containing any amount of rain respectively. We evaluate our approaches in NL20 and NL50. The experimental results show that compared with the classical model Unet，the mean square error is reduced by 144% and 106% respectively.