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
 

Improving Monsoon Precipitation Prediction Using Combined Convolutional and Long Short Term Memory Neural Network

Journal Article · · Water (Basel)
DOI:https://doi.org/10.3390/w11050977· OSTI ID:1613794
 [1];  [2];  [3];  [2];  [2]
  1. Tsinghua Univ., Beijing (China); DOE/OSTI
  2. Univ. of California, Irvine, CA (United States)
  3. Tsinghua Univ., Beijing (China); China Inst. of Water Resources and Hydropower Research, Beijing (China)
+ Show Author Affiliations
Precipitation downscaling is widely employed for enhancing the resolution and accuracy of precipitation products from general circulation models (GCMs). In this study, we propose a novel statistical downscaling method to foster GCMs’ precipitation prediction resolution and accuracy for the monsoon region. We develop a deep neural network composed of a convolution and Long Short Term Memory (LSTM) recurrent module to estimate precipitation based on well-resolved atmospheric dynamical fields. The proposed model is compared against the GCM precipitation product and classical downscaling methods in the Xiangjiang River Basin in South China. Results show considerable improvement compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)-Interim reanalysis precipitation. Also, the model outperforms benchmark downscaling approaches, including (1) quantile mapping, (2) the support vector machine, and (3) the convolutional neural network. To test the robustness of the model and its applicability in practical forecasting, we apply the trained network for precipitation prediction forced by retrospective forecasts from the ECMWF model. Compared to the ECMWF precipitation forecast, our model makes better use of the resolved dynamical field for more accurate precipitation prediction at lead times from 1 day up to 2 weeks. This superiority decreases with the forecast lead time, as the GCM’s skill in predicting atmospheric dynamics is diminished by the chaotic effect. Finally, we build a distributed hydrological model and force it with different sources of precipitation inputs. Hydrological simulation forced with the neural network precipitation estimation shows significant advantage over simulation forced with the original ERA-Interim precipitation (with NSE value increases from 0.06 to 0.64), and the performance is only slightly worse than the observed precipitation forced simulation (NSE = 0.82). This further proves the value of the proposed downscaling method, and suggests its potential for hydrological forecasts.
Research Organization:
Univ. of California, Oakland, CA (United States)
Sponsoring Organization:
China Scholarship Council; National Natural Science Foundation of China; USDOE Office of International Affairs (IA)
Grant/Contract Number:
IA0000018
OSTI ID:
1613794
Journal Information:
Water (Basel), Journal Name: Water (Basel) Journal Issue: 5 Vol. 11; ISSN 2073-4441; ISSN WATEGH
Publisher:
MDPICopyright Statement
Country of Publication:
United States
Language:
English

References (56)

Predictions of climate change over Europe using statistical and dynamical downscaling techniques journal April 2000
Precipitation predictors for downscaling: observed and general circulation model relationships journal May 2000
A quantile regression neural network approach to estimating the conditional density of multiperiod returns journal January 2000
Downscaling of global climate models for flood frequency analysis: where are we now? journal January 2002
Spatial resolution sensitivity of catchment geomorphologic properties and the effect on hydrological simulation journal January 2001
Application of a distributed hydrological model and weather radar observations for flood management in the upper Tone River of Japan journal January 2004
Downscaling precipitation to river basin in India for IPCC SRES scenarios using support vector machine journal March 2008
Statistical and dynamical downscaling of the Seine basin climate for hydro-meteorological studies journal January 2007
Role of predictors in downscaling surface temperature to river basin in India for IPCC SRES scenarios using support vector machine journal March 2009
Validation and comparison of a new gauge-based precipitation analysis over mainland China: NEW GAUGE-BASED PRECIPITATION OVER CHINA journal April 2015
Downscaling temperature and precipitation: a comparison of regression-based methods and artificial neural networks journal January 2001
The ERA-Interim reanalysis: configuration and performance of the data assimilation system journal April 2011
A nonparametric kernel regression model for downscaling multisite daily precipitation in the Mahanadi basin: MULTISITE STATISTICAL DOWNSCALING journal March 2013
Intercomparison of the climatological variations of Asian summer monsoon precipitation simulated by 10 GCMs journal August 2002
Projected future changes in synoptic systems influencing southwest Western Australia journal February 2006
Validation of present-day regional climate simulations over Europe: LAM simulations with observed boundary conditions journal August 1997
Long lead monsoon rainfall prediction for meteorological sub-divisions of India using deterministic artificial neural network model journal September 2008
On complex extremes: flood hazards and combined high spring-time precipitation and temperature in Norway journal June 2007
A distributed scheme developed for eco-hydrological modeling in the upper Heihe River journal December 2014
Sensitivity of flood events to global climate change journal April 1997
Novel SVM-based technique to improve rainfall estimation over the Mediterranean region (north of Algeria) using the multispectral MSG SEVIRI imagery journal March 2017
Downscaling of precipitation for climate change scenarios: A support vector machine approach journal November 2006
Establishing a rainfall threshold for flash flood warnings in China’s mountainous areas based on a distributed hydrological model journal October 2016
A comparative assessment of decision trees algorithms for flash flood susceptibility modeling at Haraz watershed, northern Iran journal June 2018
An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines journal February 2019
Effect of precipitation sampling error on simulated hydrological fluxes and states: Anticipating the Global Precipitation Measurement satellites journal January 2004
SVM-PGSL coupled approach for statistical downscaling to predict rainfall from GCM output journal January 2010
Dreary state of precipitation in global models: MODEL AND OBSERVED PRECIPITATION journal December 2010
Projecting changes in future heavy rainfall events for Oahu, Hawaii: A statistical downscaling approach journal January 2011
Improving Precipitation Estimation Using Convolutional Neural Network journal March 2019
Deep learning journal May 2015
The quiet revolution of numerical weather prediction journal September 2015
A hillslope-based hydrological model using catchment area and width functions journal February 2002
Natural evaporation from open water, bare soil and grass journal April 1948
Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition journal June 1965
ImageNet classification with deep convolutional neural networks journal May 2017
Information Analysis of Catchment Hydrologic Patterns across Temporal Scales journal January 2016
Long Short-Term Memory journal November 1997
A Comparison of Statistical and Model-Based Downscaling Techniques for Estimating Local Climate Variations journal April 1998
Large-Scale Circulation Anomalies Conducive to Extreme Precipitation Events and Derivation of Daily Rainfall in Northeastern Mexico and Southeastern Texas journal May 1999
An Evaluation of Statistical and Dynamical Techniques for Downscaling Local Climate journal August 1999
Ensemble Simulations of Asian–Australian Monsoon Variability by 11 AGCMs* journal February 2004
A Statistical Downscaling Model for Southern Australia Winter Rainfall journal March 2009
The Subseasonal to Seasonal (S2S) Prediction Project Database journal January 2017
Is Precipitation a Good Metric for Model Performance? journal February 2019
Development of a China Dataset of Soil Hydraulic Parameters Using Pedotransfer Functions for Land Surface Modeling journal June 2013
From GCMs to river flow: a review of downscaling methods and hydrologic modelling approaches journal June 1999
From GCMs to river flow: a review of downscaling methods and hydrologic modelling approaches journal June 1999
Improving Precipitation Estimation Using Convolutional Neural Network text January 2018
Development of a Geomorphology-Based Hydrological Model for Large Catchments journal January 1998
Novel methods for inferring future changes in extreme rainfall over Northern Europe journal September 2007
Statistical downscaling of climate scenarios over Scandinavia journal January 2005
Flood Prediction Using Machine Learning Models: Literature Review journal October 2018
Convolutional LSTM Networks for Subcellular Localization of Proteins text January 2015
Flood Prediction Using Machine Learning Models: Literature Review text January 2019
Deep Learning text January 2018

Cited By (1)

Hydrological Early Warning System Based on a Deep Learning Runoff Model Coupled with a Meteorological Forecast journal August 2019

Similar Records

Improving Precipitation Estimation Using Convolutional Neural Network
Journal Article · Mon Jan 14 19:00:00 EST 2019 · Water Resources Research · OSTI ID:1613789
Short-Term Precipitation Forecast Based on the PERSIANN System and LSTM Recurrent Neural Networks
Journal Article · Sun Oct 28 20:00:00 EDT 2018 · Journal of Geophysical Research: Atmospheres · OSTI ID:1613787

Related Subjects

54 ENVIRONMENTAL SCIENCES
Water Resources
convolutional neural networks
hydrological simulation
long short term memory networks
precipitation downscaling