An improved near-real-Time precipitation retrieval for Brazil

Abstract

Observations from geostationary satellites can provide spatially continuous coverage at continental scales with high spatial and temporal resolution. Because of this, they are commonly used to complement ground-based precipitation measurements, whose coverage is often more limited. We present Hydronn, a neural-network-based, near-real-Time precipitation retrieval for Brazil based on visible and infrared (Vis-IR) observations from the Advanced Baseline Imager (ABI) on the Geostationary Operational Environmental Satellite 16 (GOES-16). The retrieval, which employs a convolutional neural network to perform Bayesian precipitation retrievals, was developed with the aims of (1) leveraging the full potential of latest-generation geostationary observations and (2) providing probabilistic precipitation estimates with well-calibrated uncertainties. The retrieval is trained using more than 3 years of collocations with combined radar and radiometer retrievals from the Global Precipitation Measurement (GPM) core observatory over South America. The accuracy of instantaneous precipitation estimates is assessed using a separate year of GPM combined retrievals and compared to retrievals from passive microwave (PMW) sensors and HYDRO, the Vis-IR retrieval that is currently in operational use at the Brazilian Institute for Space Research. Using all available channels of the ABI, Hydronn achieves accuracy close to that of state-of-The-Art PMW precipitation retrievals in both precipitation estimation and detection despite the lower information content of the Vis-IR observations. Hourly, daily, and monthly precipitation accumulations are evaluated against gauge measurements for June and December 2020 and compared to HYDRO, the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) Cloud Classification System (CCS), and the Integrated Multi-satellitE Retrievals for GPM (IMERG). Compared to HYDRO, Hydronn reduces the mean absolute error for hourly accumulations by 21% (22%) compared to HYDRO by 44% (41%) for the mean squared error (MSE) and increases the correlation by 138% (312%) for June (December) 2020. Compared to IMERG, the improvements correspond to 16% (14%), 12% (12%), and 20% (56%), respectively. Furthermore, we show that the probabilistic retrieval is well calibrated against gauge measurements when differences in the distributions of the training data and the gauge measurements are accounted for. Hydronn has the potential to significantly improve near-real-Time precipitation retrievals over Brazil. Furthermore, our results show that precipitation retrievals based on convolutional neural networks (CNNs) that leverage the full range of available observations from latest-generation geostationary satellites can provide instantaneous precipitation estimates with accuracy close to that of state-of-The-Art PMW retrievals. The high temporal resolution of the geostationary observation allows Hydronn to provide more accurate precipitation accumulations than any of the tested conventional precipitation retrievals. Hydronn thus clearly shows the potential of deep-learning-based precipitation retrievals to improve precipitation estimates from currently available satellite imagery.