Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Short-Term Precipitation Forecast Based on the PERSIANN System and LSTM Recurrent Neural Networks

Journal Article · · Journal of Geophysical Research: Atmospheres
DOI:https://doi.org/10.1029/2018jd028375· OSTI ID:1613787
 [1];  [2];  [3];  [4];  [5];  [5]
  1. Univ. of California, Irvine, CA (United States); DOE/OSTI
  2. Univ. of California, Irvine, CA (United States); Univ. of Oklahoma, Norman, OK (United States)
  3. Univ. of California, Irvine, CA (United States); National Taiwan Ocean Univ., Keelung (Taiwan)
  4. Univ. of California, Irvine, CA (United States)
  5. China Inst. of Water Resources and Hydropower Research, Beijing (China)
+ Show Author Affiliations
Short-term Quantitative Precipitation Forecasting is important for flood forecasting, early flood warning, and natural hazard management. This study proposes a precipitation forecast model by extrapolating Cloud-Top Brightness Temperature (CTBT) using advanced Deep Neural Networks, and applying the forecasted CTBT into an effective rainfall retrieval algorithm to obtain the Short-term Quantitative Precipitation Forecasting (0–6 hr). To achieve such tasks, we propose a Long Short-Term Memory (LSTM) and the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN), respectively. The precipitation forecasts obtained from our proposed framework, (i.e., LSTM combined with PERSIANN) are compared with a Recurrent Neural Network (RNN), Persistency method, and Farneback optical flow each combined with PERSIANN algorithm and the numerical model results from the first version of Rapid Refresh (RAPv1.0) over three regions in the United States, including the states of Oregon, Oklahoma, and Florida. We report our experiments indicate better statistics, such as correlation coefficient and root-mean-square error, for the CTBT forecasts from the proposed LSTM compared to the RNN, Persistency, and the Farneback method. The precipitation forecasts from the proposed LSTM and PERSIANN framework has demonstrated better statistics compared to the RAPv1.0 numerical forecasts and PERSIANN estimations from RNN, Persistency, and Farneback projections in terms of Probability of Detection, False Alarm Ratio, Critical Success Index, correlation coefficient, and root-mean-square error, especially in predicting the convective rainfalls. The proposed method shows superior capabilities in short-term forecasting over compared methods, and has the potential to be implemented globally as an alternative short-term forecast product.
Research Organization:
Univ. of California, Oakland, CA (United States)
Sponsoring Organization:
California Energy Commission; National Climatic Data Center (NCDC); National Environmental Satellite, Data, and Information Service (NESDIS); National Oceanic and Atmospheric Administration (NOAA); National Science Foundation (NSF); US Army Research Office (ARO); USDOE Office of International Affairs (IA)
Grant/Contract Number:
IA0000018
OSTI ID:
1613787
Alternate ID(s):
OSTI ID: 1482741
Journal Information:
Journal of Geophysical Research: Atmospheres, Journal Name: Journal of Geophysical Research: Atmospheres Journal Issue: 22 Vol. 123; ISSN 2169-897X
Publisher:
American Geophysical UnionCopyright Statement
Country of Publication:
United States
Language:
English

References (60)

Developing reservoir monthly inflow forecasts using artificial intelligence and climate phenomenon information: RESERVOIR INFLOW FORECASTS journal April 2017
Short-term flood inundation prediction using hydrologic-hydraulic models forced with downscaled rainfall from global NWP: SHORT-TERM FLOOD INUNDATION PREDICTION journal October 2013
Evaluation of a new satellite-based precipitation data set for climate studies in the Xiang River basin, southern China: EVALUATION OF PERSIANN-CDR FOR CLIMATE STUDIES journal May 2017
Performance of 4D-Var NWP-based nowcasting of precipitation at the Met Office for summer 2012: 4D-Var NWP-based Nowcasting of Precipitation
  • Ballard, Susan P.; Li, Zhihong; Simonin, David
  • Quarterly Journal of the Royal Meteorological Society, Vol. 142, Issue 694 https://doi.org/10.1002/qj.2665
journal November 2015
Two-Frame Motion Estimation Based on Polynomial Expansion book January 2003
Self-organized formation of topologically correct feature maps journal January 1982
Rainfall forecasting in space and time using a neural network journal August 1992
Generalization of backpropagation with application to a recurrent gas market model journal January 1988
Convolutional neural networks book January 2020
Quantitative Precipitation Nowcasting: A Lagrangian Pixel-Based Approach journal November 2012
A quantitative comparison of precipitation forecasts between the storm-scale numerical weather prediction model and auto-nowcast system in Jiangsu, China journal November 2016
Nowcasting of deep convective clouds and heavy precipitation: Comparison study between NWP model simulation and extrapolation journal February 2017
An enhanced artificial neural network with a shuffled complex evolutionary global optimization with principal component analysis journal December 2017
Evaluation of satellite-based precipitation estimation over Iran journal October 2013
Short-term quantitative precipitation forecasting using an object-based approach journal March 2013
Rainfall frequency analysis for ungauged regions using remotely sensed precipitation information journal August 2018
Framewise phoneme classification with bidirectional LSTM and other neural network architectures journal July 2005
Nimrod: A system for generating automated very short range forecasts journal March 1998
Self-organizing linear output map (SOLO): An artificial neural network suitable for hydrologic modeling and analysis: SOLO, AN ANN MODEL SUITABLE FOR HYDROLOGIC MODELING journal December 2002
Evaluation of satellite-retrieved extreme precipitation rates across the central United States journal January 2011
Comparison of PERSIANN and V7 TRMM Multi-satellite Precipitation Analysis (TMPA) products with rain gauge data over Iran journal September 2013
The estimation of global monthly mean rainfall using infrared satellite data: The GOES precipitation index (GPI) journal October 1994
Recurrent neural networks and robust time series prediction journal March 1994
Scene labeling with LSTM recurrent neural networks conference June 2015
Speech recognition with deep recurrent neural networks conference May 2013
Recurrent nets that time and count
  • Gers, F. A.; Schmidhuber, J.
  • Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium https://doi.org/10.1109/IJCNN.2000.861302
conference January 2000
LSTM: A Search Space Odyssey journal October 2017
The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions journal April 1998
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification conference October 2015
Learning to Forget: Continual Prediction with LSTM journal October 2000
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks journal June 1989
Long Short-Term Memory journal November 1997
Localized Precipitation Forecasts from a Numerical Weather Prediction Model Using Artificial Neural Networks journal December 1998
Precipitation Forecasting Using a Neural Network journal June 1999
Short-Range Ensemble Forecasts of Precipitation during the Southwest Monsoon journal October 2002
Consensus Clustering of U.S. Temperature and Precipitation Data journal June 1997
Interannual Variability of the U.S. Summer Precipitation Regime with Emphasis on the Southwestern Monsoon journal October 1998
Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks journal September 1997
A Microwave Infrared Threshold Technique to Improve the GOES Precipitation Index journal May 1999
A Tutorial on Lateral Boundary Conditions as a Basic and Potentially Serious Limitation to Regional Numerical Weather Prediction journal November 1997
Diurnal Variations in Precipitation and Thunderstorm Frequency over the Conterminous United States journal May 1975
A Comprehensive Radiation Scheme for Numerical Weather Prediction Models with Potential Applications in Climate Simulations journal February 1992
Experiments in Short-Term Precipitation Forecasting Using Artificial Neural Networks journal February 1998
Distributed Quantitative Precipitation Forecasting Using Information from Radar and Numerical Weather Prediction Models journal December 2003
PERSIANN-MSA: A Precipitation Estimation Method from Satellite-Based Multispectral Analysis journal December 2009
National Mosaic and Multi-Sensor QPE (NMQ) System: Description, Results, and Future Plans journal October 2011
Improving QPE and Very Short Term QPF: An Initiative for a Community-Wide Integrated Approach journal December 2007
Use of NWP for Nowcasting Convective Precipitation: Recent Progress and Challenges journal March 2014
An Automated Technique to Quality Control Radar Reflectivity Data journal March 2007
A North American Hourly Assimilation and Model Forecast Cycle: The Rapid Refresh journal April 2016
National Mosaic and Multi-sensor QPE (NMQ) System – Description, Results and Future Plans journal June 2011
Finding Structure in Time journal March 1990
Convolutional Neural Networks text January 2019
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
  • Cho, Kyunghyun; van Merrienboer, Bart; Gulcehre, Caglar
  • Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) https://doi.org/10.3115/v1/D14-1179
conference January 2014
LSTM: A Search Space Odyssey text January 2015
Evaluation of satellite rainfall estimates over Ethiopian river basins journal January 2011
Evaluation of numerical weather prediction model precipitation forecasts for short-term streamflow forecasting purpose journal January 2013
Post-processing rainfall forecasts from numerical weather prediction models for short-term streamflow forecasting journal January 2013
Development and verification of a real-time stochastic precipitation nowcasting system for urban hydrology in Belgium journal January 2016
Evaluating the streamflow simulation capability of PERSIANN-CDR daily rainfall products in two river basins on the Tibetan Plateau journal January 2017

Cited By (3)

Lake Level Prediction using Feed Forward and Recurrent Neural Networks journal April 2019
Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks journal May 2019
Conditional Generative Adversarial Networks (cGANs) for Near Real-Time Precipitation Estimation from Multispectral GOES-16 Satellite Imageries—PERSIANN-cGAN journal September 2019

Similar Records

PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks
Journal Article · Tue Nov 26 19:00:00 EST 2019 · Journal of Hydrometeorology · OSTI ID:1575959

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
54 ENVIRONMENTAL SCIENCES
LSTM
PERSIANN system
RNN
Rapid Refresh
deep learning
meteorology & atmospheric sciences
precipitation forecast