Precipitation is a vital process in water cycle. Accurate estimation of the precipitation rate underpins the success of hydrological simulations, flood predictions, and water resource management. Satellite infrared (IR) data, with high temporal resolution and wide coverages, have been commonly used in precipitation inversion. However, existing IR-based precipitation retrieval algorithms suffer from various problems such as overestimation in dry regions, poor performance in extreme rainfall events, and reliance on an empirical cloud-top brightness-rain rate relationship. To resolve these problems, we construct a deep learning model using a spherical convolutional neural network to properly represent the Earth’s spherical surface. With data inputted directly from IR band 3, 4, and 6 of the operational Geostationary Operational Environmental Satellite (GOES), our new model of Precipitation Estimation based on IR data with Spherical Convolutional Neural Network (PEISCNN) was first trained and tested with a three-month-long dataset, and then validated in a two-year period. Compared to the commonly used IR-based precipitation product PERSIANN CCS (the Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Network, Cloud Classification System), PEISCNN showed significant improvement in the metrics of POD, CSI, RMSE and CC, especially in the dry region and for extreme rainfall events. Decomposed with the 4CED method, the overestimation of PEISCNN was averaged 47.66% lower than the CCS at the hourly scale. The PEISCNN model may provide a promising way to produce an improved IR-based precipitation product to benefit a wide range of hydrological applications.

In this study artificial neural networks (ANNs) have been applied to predict faecal coliform concentration levels at compliance points along bathing water zones situated in the south west of Scotland, UK. Hydrological parameters, such as river discharges, sunshine, rainfall and tidal conditions, were used as the input data for these networks. Data collected at seven locations during the period 1990–2000 were used to train and verify the neural networks. A novel technique called the gamma test was used for data analysis to aid in the construction of ANN models. In general, the river discharges and tidal range were found to be the most important variables affecting the level of bacteria concentration at the compliance points. For compliance points close to the meteorological station, the amount of rainfall was found to be relatively significant in the model results. Relatively good correlation coefficients were obtained for the learning and verifying process for all of the ANNs and these networks confirmed that the samples failed to comply with the standard values specified in the European Union Bathing Water Directive in 57·4% of the cases.