Experimental designThe design of th

Experimental designThe design of the process is presented in Fig. 4. In this study, the input data for the DNN are IR imagery collected by GOES, the same raw information used by PERSIANN-CCS. The dataset is at a spatial resolution of 0.08° × 0.08° and an hourly temporal resolution. IR imagery provides cloud-top brightness temperature and has been used for multiple near-real-time precipitation estimation products (Hong et al. 2004; Hsu et al. 1997; Huffman et al. 2007; Joyce et al. 2004). In PERSIANN-CCS, nine features of IR imagery in a cloud patch (Table 1) are used to predict precipitation rates at the (target) pixels within the cloud patch. Instead of using cloud image features designed by researchers, we allow the neural network to extract a useful representation for precipitation estimation itself. As shown in Fig. 4, the input to DNN is a matrix 15 × 15 containing the IR image in a 15 × 15 pixel window centered in pixel t8,8, at which PERSIANN-CCS indicates a positive precipitation rate rp. To produce a training data pool, the window is moved across the image sequentially, shifting location one grid box at a time in each hourly IR image of the study region.