ABSTRACTS

General Structure

Background and Objective

Downscaling CGCM climate change output scenario using the Artificial Neural Network model

Kang Boosik1 / Yang Jeong-Seok2 1Department of Civil & Environmental Engineering, Dankook University / 2School of Civil & Environmental Engineering, Kookmin University

Correspondence : Kang Boosik, Ph.D./ProfessorDepartment of Civil & Environmental Engineering, Dankook University#126 Jukjeon, Suji, Yongin, Korea 448-701e-mail : bskang@dankook.ac.kr

This study carried out the prediction of basin-wide climate change using GCM(Global Climate Model) climate change outlook scenario. To regionalize the original GCM scenario, the Artificial Neural Network (ANN) model was used. The 22 GCM output variables including precipitation flux, air pressure at sea level, near-surface daily-mean air temperature, surface upward latent heat flux etc, were used for potential predictor variables. The precipitation and temperature variables were used for predictands. The original GCM data is the CGCM3.1/T63 20C3M scenario (reference scenario) provided by CCCma (Canadian Centre for Climate Modeling and Analysis).

The ANN learning process was performed from January 1997 to December 2000. The suggested ANN has a 3-layer perceptron (multi-layer perceptron; MLP) and back-propagation learning algorithm. The ANN predictors selected through the sensitivity analysis were utilized for final ANN model of Soyang and Chungju dam basin. Daily temperature and precipitation trend from 2001 to 2100 were suggested. The basin-wide prediction data of climate change scenario can be served as input data of long-term runoff model and give estimate of future available water resources.

 

Keywords: Artificial Neural Network, Global Climate Model, multi-layer perceptron

In order to reproduce regional climate information from the large-scale GCM outputs, the Model Output Statistics (MOS) post-processing based on multiple regression correlations between the predictand and available predictors is one of the useful methodologies. A number of other nonlinear techniques can be used to post-process NWP outputs, including generalized additive models (Vislocky and Fritsch, 1995), self-learning algorithms (e.g. Abdel-Aal and Elhadidy, 1995), and models based on artificial neural networks (ANN). ANN models have been proving to be useful in the field of hydrology (e.g. Silverman and Dracup, 2000). ANN models are capable of approximating extremely complex functions, while easier to apply than more traditional nonlinear statistical methods. This study carried out the prediction of basin-wide climate change using GCM(Global Climate Model) climate change outlook scenario. To regionalize the original GCM scenario, the Artificial Neural Network (ANN) model was used.

One of the most popular network architectures is perhaps the multilayer perceptron, consisting of an input layer, one or more hidden layers, and an output layer. The input layer simply introduces the values of the input variables, while the hidden and output layer neurons are each connected to all of the units in the preceding layer. A diagram of a three-layer neural network is shown in Figure 1. The input layer consists of nI

units, each of which receives one of the input variables. The so-called hidden layer is composed by nH units.

Finally, the output layer consists of nK units, each of which computes a desired output (for the present study,

only one output is needed). The neural networks developed for this study have a feed-forward structure: signals flow forward from input neuron through any hidden units, eventually reaching the output neurons. The mathematical equation of a three-layer NN can be written as:

Study Area

Watershed : Soyang Dam

Location : Kangwon Province, Korea

# of sub-basin : 2 (#1011, #1012)

Area : 2,783.26 ㎢ (#1001 : 931.22 ㎢ , #1002 : 1852.04 ㎢ )

# of Automatic Weather Station (AWS) : 8 stations

Data used for ANN training : daily temperature & precipitation

for 1997 – 2000 (4 years)

Schematic of a 3-layer neural network

Conclusion

Results

Basin-wide daily temperature and precipitation projection from 2001 to 2100 were suggested for Soyang dam basin based on SRES B1 scenario downscaled from CCCma’s CGCM3.1/T63 output. When comparing 2081-2100 with 2001-2020, the winter and summer temperatures will be expected to increase 1.06℃ and 0.39 , respectively, which shows warming will be more significant ℃during winter season. The winter and summer precipitation will be expected to increase 6.2mm and 21.2mm, respectively. To be more reliable results, the typhoon effects needs to be considered in the future.

33rd IAHR Congress, Water Engineering for a Sustainable Environment, Vancouver, British Columbia, Canada, August 9-14, 2009

k

ihihi xwShSS

SS

ihi yee

eeSf

hihi

hihi

)(

k

hkhkh ywSkkhhkh ySSf )(

Where:

·xi(t) is the input to unit i of the input layer and zk(t) is the output obtained at unit

k of the output layer

·i = 1, 2, …, nI where nI is the number of inputs

·h = 1, 2, …, nH where nH is the number of hidden units

·k = 1, 2, …, nK where nK is the number of outputs

·whhi are the parameters, or weights, controlling the strength of the connection

between the input unit i and the hidden unit h

·q i and q h are the thresholds

· wokh are the parameters controlling the strength of the connection between the

hidden unit h and the output unit k

·f is the activation or transfer function:

GCM scenario

Model : CGCM 3.1/T63 provided by CCCma

Grid Resolution : - Lateral : lon 2.81° × lat 2.81° (128 ×64 Gaussian grids) - Vertical : 63 layers

Available scenarios : SRES A1B, B1, A2

Reference scenario : CGCM3.1/T63 20C3M Scenario

Projection used in this study : CGCM3.1/T63 SRES B1 Scenario

Model output : - Monthly : 2001-2100 (2D, 3D) - Daily : 2001-2100 (2D) 2046-2065 (3D) 2081-2100 (3D)

CGCM3.1/T63 Variables

psl_a2 air pressure at sea level (Pa)

GCM prec precipitation flux ( ㎏ m-2 s-1)tasmax near-surface daily-maximum air temperature (K)

tasmin near-surface daily-minimum air temperature (K)

tas near-surface daily-mean air temperature (K)

hfls surface upward latent heat flux (W m-2)

hfss surface upward sensible heat flux (W m-2)

rlds surface downwelling longwave flux in air (W m-2)

rlus surface upwelling longwave flux in air (Wm-2 )

rsds surface downwelling shortwave flux in air (W m-2)

rsus surface upwelling shortwave flux in air (W m-2)

uas near-surface eastward wind (m s-1)

vas near-surface northward wind (m s-1)

rlut toa outgoing longwave flux (W m-2)

ps surface air pressure (Pa)

huss near-surface specific humidity (dimensionless fraction)

evsp surface water evaporation flux ( ㎏ m-2 s-1)prsn snowfall flux ( ㎏ m-2 s-1)snd surface snow thickness (m)

snw surface snow amount where land ( ㎏ m-2)snr snow density ( ㎏ m-3)

psl_a6 air pressure at sea level, 12 or 6 hourly (Pa)

ANN Training with Reference Scenario

100-yr Projection under B1 Scenario

1011 sub-basin

1012 sub-basin

Sub-basin MERR CORR1011 0.52 0.651012 0.57 0.74

1011 sub-basin

1012 sub-basin

DJF

(Win

ter)

JJA

(Su

mm

er)

Tem

per

atu

reP

reci

pit

atio

n

DJF

(Win

ter)

JJA

(Su

mm

er)

Sub-basin MERR CORR1011 -1.36 0.901012 -0.78 0.88

Tem

per

atu

reP

reci

pit

atio

n

Abdel-Aal, R.E. and Elhadidy, M.A. (1995). Modeling and forecasting the maximum temperature using abductive machine learning. Weather and Forecasting 10, pp. 310-325

Silverman, D. and Dracup, J. (2000). Artificial Neural Networks and Long Range Precipitation Prediction in California, Journal of Applied Meteorology, 31:1, pp.57-66

Vislocky, R. L. and J. M. Fritsch (1995). Improved model output statistics forecasts through model consensus. Bull. Amer. Meteor. Soc., 76, pp.1157–1164.

1011 1012 Mean

DJF JJA DJF JJA DJF JJA

2001 – 2020 1.46 19.71 0.39 20.16 0.925 19.9

2041 – 2060 1.83 20.12 1.25 20.58 1.54 20.4

2081 - 2100 2.21 20.10 1.76 20.55 1.985 20.3

1011 1012 Mean

DJF JJA DJF JJA DJF JJA

2001 – 2020 9.32 276.08 16.09 234.75 12.71 255.4

2041 – 2060 13.22 293.05 20.41 251.12 16.82 272.1

2081 - 2100 15.07 295.90 22.79 257.29 18.93 276.6

References

TOPIC C: Water Engineering for the Protection and Enhancement of Natural Watershed and Aquifer Environments Technical Session 2, Track C-5: Climate Influences on Water Flow in Watersheds (August 10, Regency & Plaza Foyers, Balmoral)