Precipitation Estimation Based on Infrared Data with a Spherical Convolutional Neural Network

Abstract

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. 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.