neural network forecasting of storm surges along the gulf of mexico
Post on 01-Jan-2016
18 Views
Preview:
DESCRIPTION
TRANSCRIPT
Neural Network Forecasting of Neural Network Forecasting of Storm Surges along the Gulf of Storm Surges along the Gulf of
MexicoMexico
Philippe Tissot*, Daniel Cox**, Patrick Michaud*
* Conrad Blucher Institute, Texas A&M University-Corpus Christi
* * Civil Engineering Department, Texas A&M University
Presentation OutlinePresentation Outline
Frontal Passages and the Texas Gulf Coast
Need for better Water Level Forecasting Models
Application of NN Modeling to Water Level
Forecasting
Model Performance
Conclusions
Frontal Systems and the Texas Frontal Systems and the Texas CoastCoast
• Regular frontal passages from late September to mid May every 7 to 10 days
• Wind gusts regularly up to 40-45 mph along the coast
• Effects of the frontal passages last up to 4-5 days
• Changes in temperature and barometric pressure
• The resulting changes in water levels exceed the tidal range
GalvestonGalveston
Study Location: Galveston, TexasStudy Location: Galveston, Texas
Computed Harmonic Tidal Sea Level Computed Harmonic Tidal Sea Level at Pleasure Pier, Galveston (Spring 97)at Pleasure Pier, Galveston (Spring 97)
Comparison of Actual and Computed Sea Comparison of Actual and Computed Sea Level (Spring 97)Level (Spring 97)
Importance of the ProblemImportance of the Problem
• Gulf Coast Ports account for 52.3% of total US tonnage (1995)
• 1240 ship groundings from 1986 to 1991 in Galveston Bay
• Large number of barge groundings along the Texas Intra Coastal Waterways (ICW)
• Worldwide increases in vessel draft
Water Level Forecasting in non Tidally Water Level Forecasting in non Tidally Driven Coastal Water BodiesDriven Coastal Water Bodies
Water level forecasting is important for a
number of coastal users (ports, emergency
management, recreational users, …)
Forecasting models need to account for other
factors then tidal forces and therefore will
necessarily be “near real time” models
TCOON StationsTCOON Stations
Primary Water LevelPrimary Water Level
Water TemperatureWater Temperature
Wind SpeedWind Speed
Wind GustWind Gust
Wind DirectionWind Direction
Typical TCOONstation pageTypical TCOONstation page
Streaming Data ModelingStreaming Data Modeling
Real time data availability is rapidly increasing
Cost of weather sensors and telecommunication
equipment is steadily decreasing while performance
is improving
How to use these new streams of data / can new
modeling techniques be developed
Classic models (large computer codes - finite elements
based) need boundary conditions and forcing functions
which are difficult to provide during storm events
Neural Network modeling can take advantage of high data
density and does not require the explicit input of boundary
conditions and forcing functions
The modeling is focused on forecasting water levels at
specific locations
Streaming Data ModelingStreaming Data Modeling
Neural Network ModelingNeural Network Modeling
• Started in the 60’s
• Key innovation in the late 80’s: Backpropagation learning algorithms
• Number of applications has grown rapidly in the 90’s especially financial applications
• Growing number of publications presenting environmental applications
Neural Network FeaturesNeural Network Features
Non linear modeling capability
Generic modeling capability
Robustness to noisy data
Ability for dynamic learning
Requires availability of high density of data
Neural Network Forecasting of Neural Network Forecasting of Water LevelsWater Levels
Use historical time series of previous water levels, winds, barometric pressure as input
Train neural network to associate changes in inputs and future water level changes
Make water level forecasts using a Static Neural Network Model
Wind Stress Factor in Water Level Wind Stress Factor in Water Level Changes / Forcing FunctionsChanges / Forcing Functions
Neural Network Forecasting of Neural Network Forecasting of Water LevelsWater Levels
Philippe Tissot - 2000
H (t+i)
Output LayerHidden Layer
Wind Stress History
Water Level History
Barometric Pressure History
Wind Stress Forecast
Input Layer
Water Level Forecast
(a1,ixi)
b1
b2
(X1+b1)
b3
(X2+b2)
(X3+b3)
(a2,ixi)
(a3,ixi)
NN Model, 24 Hr prediction
Harmonic Analysis
Comparison between measured water levels (black), tidal chart forecasts (blue), and 24 hour neural network forecasts (red) for Galveston Pleasure Pier during the spring of 1999 (Cox, Tissot, Michaud). The neural network model was trained for a period of 90 days during the spring of 1997 and is applied here to a frontal passage during the spring of 1999. The accuracy of the 24 hour neural network forecast shows the ability to predict the timing and the intensity of frontal passages.
Performance of the ModelPerformance of the Model
Performance index E
2
1
1
2
21
1
2
1
1
N
i i
N
i ii
HN
XHN
E
Hi are the water levels observations and Xi the water level forecasts
Performance Analysis of the Performance Analysis of the ModelModel
• Spring ‘97, ‘98, ‘99 data sets covering 90 days with hourly water levels and weather data
• Train the NN model using one data set e.g. ‘97 for each forecast target, e.g. 12 hours
• Apply the NN model to the other two data sets, e.g. ‘98, ‘99
• Repeat the performance analysis for each training year and forecast target and compute the error index
Model Comparisons for Varying Model Comparisons for Varying Forecasting TimeForecasting Time
0
0.2
0.4
0.6
0.8
1
0 6 12 18 24 30 36 42 48
Forecast time [hours]
For
ecas
t P
erfo
rman
ce
Forecasts not Including Wind Forecasts
Forecasts Including Modified Wind Speed at Forecasted Time
Forecasts Including Exact Wind Speed at Forecasted Time
Tide Charts
ConclusionsConclusions
• Neural network modeling shows excellent promises for local forecasting of water levels during frontal passages (6 to 30 hour forecasts)
• Computationally and financially inexpensive method
• The quality of the wind forecasts will likely be the limiting factor for the accuracy of the water level forecasts
• Expanding the application of the model to other locations along the coast of Texas
Neural Network Neural Network Forecasting of Storm Forecasting of Storm
Surges along the Gulf of Surges along the Gulf of MexicoMexico
Presentation End
Simulated Wind Forecast using Simulated Wind Forecast using Gaussian filterGaussian filter
Observed
Simulated
NWS Predictions and TCOON ObservationsNWS Predictions and TCOON Observations(Actual Forecast)(Actual Forecast)
Galveston Pleasure Pier, 1999 12 Hr Predictions
Training of a Neural NetworkTraining of a Neural Network
Philippe Tissot - 2000
Water Level Changes and TidesWater Level Changes and Tides
There is a large non tidal related component for water level changes on the Texas coast
Other factors influencing water level changes:
Differential atmospheric pressures
Wind Precipitations
Riverine inputs Evaporation
Changes in density Salinity Changes
Forecasted Water Levels vs. Forecasted Water Levels vs. Observed Water LevelsObserved Water Levels
RMS Error: 1ft
Neural Network Forecasts Tidal Forecasts
RMS Error: 3ft
Comparison During Frontal Comparison During Frontal PassagesPassages
RMS Error: 1ft
Neural Network Forecasts Tidal Forecasts
RMS Error: 3ft
top related