PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks
Open Access
- 27 November 2019
- journal article
- research article
- Published by American Meteorological Society in Journal of Hydrometeorology
- Vol. 20 (12), 2273-2289
- https://doi.org/10.1175/jhm-d-19-0110.1
Abstract
Accurate and timely precipitation estimates are critical for monitoring and forecasting natural disasters such as floods. Despite having high-resolution satellite information, precipitation estimation from remotely sensed data still suffers from methodological limitations. State-of-the-art deep learning algorithms, renowned for their skill in learning accurate patterns within large and complex datasets, appear well suited to the task of precipitation estimation, given the ample amount of high-resolution satellite data. In this study, the effectiveness of applying convolutional neural networks (CNNs) together with the infrared (IR) and water vapor (WV) channels from geostationary satellites for estimating precipitation rate is explored. The proposed model performances are evaluated during summer 2012 and 2013 over central CONUS at the spatial resolution of 0.08° and at an hourly time scale. Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)–Cloud Classification System (CCS), which is an operational satellite-based product, and PERSIANN–Stacked Denoising Autoencoder (PERSIANN-SDAE) are employed as baseline models. Results demonstrate that the proposed model (PERSIANN-CNN) provides more accurate rainfall estimates compared to the baseline models at various temporal and spatial scales. Specifically, PERSIANN-CNN outperforms PERSIANN-CCS (and PERSIANN-SDAE) by 54% (and 23%) in the critical success index (CSI), demonstrating the detection skills of the model. Furthermore, the root-mean-square error (RMSE) of the rainfall estimates with respect to the National Centers for Environmental Prediction (NCEP) Stage IV gauge–radar data, for PERSIANN-CNN was lower than that of PERSIANN-CCS (PERSIANN-SDAE) by 37% (14%), showing the estimation accuracy of the proposed model.Keywords
Funding Information
- U.S. Department of Energy (# DE-IA0000018)
- The California Energy Commission (CEC Award # 300-15-005)
- National Science Foundation (Award CCF-1331915)
- National Oceanic and Atmospheric Administration (Prime award NA09NES4400006 and NCSU CICS and subaward 2009-1380-01)
- U.S. Army Research Office (award W911NF-11-1-0422)
- Agro-Industry Research and Development Special Fund of China (2016YFE0102400)
This publication has 51 references indexed in Scilit:
- Evaluation of the High-Resolution CMORPH Satellite Rainfall Product Using Dense Rain Gauge Observations and Radar-Based EstimatesJournal of Hydrometeorology, 2012
- Orographic effects on precipitating cloudsReviews of Geophysics, 2012
- Status of satellite precipitation retrievalsHydrology and Earth System Sciences, 2011
- PERSIANN-MSA: A Precipitation Estimation Method from Satellite-Based Multispectral AnalysisJournal of Hydrometeorology, 2009
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Intercomparison of Rain Gauge, Radar, and Satellite-Based Precipitation Estimates with Emphasis on Hydrologic ForecastingJournal of Hydrometeorology, 2005
- A Lagrangian Analysis of the Atmospheric Branch of the Global Water Cycle. Part I: Method Description, Validation, and Demonstration for the August 2002 Flooding in Central EuropeJournal of Hydrometeorology, 2004
- Retrieval of Precipitation Profiles from Multiresolution, Multifrequency Active and Passive Microwave ObservationsJournal of Applied Meteorology and Climatology, 2004
- Global Precipitation at One-Degree Daily Resolution from Multisatellite ObservationsJournal of Hydrometeorology, 2001
- The Relationship between Large-Scale Convective Rainfall and Cold Cloud over the Western Hemisphere during 1982-84Monthly Weather Review, 1987