Introduction

The prediction tool for the estimation of mean overtopping discharges at various types of coastal structures is developed by Deltares. Details of the methodology followed for the development of the prediction tool are described in Van Gent et al. (2007). The output of this program tool includes the Neural Network prediction of the mean overtopping discharge at a coastal structure and several other parameters indicating the uncertainty of the prediction.

The NN_Overtopping model takes data from Delft-FEWS, processes it, and returns it. This used to be achieved with an adapter written in MATLAB and using PI time series xml files. The adapter has been ported to Java while keeping the same functionality.

Background NN_Overtopping model

The adapter takes data from Delft-FEWS and creates a file called: NN_OVERTOPPING.INP as input to the NN_Overtopping model. The following parameters are used as input to the adapter:

Parameter descriptionParameter nameUnit

Angle of Wave attack

b

degr

Water depth in front of structure

h


Significant Wave Height at the toe of structure

Hm0

toe(m)

Wave period

Tm-1,0

toe(s)

Water depth at the toe of structure

ht

m

Width of toe

Bt

m

Roughness coefficient

gf


Angle of down slope

cotad


Angle of upper slope

catau


Crest Freeboard in relation to SWL

Rc

m

Berm Width

B

m

Water depth at the berm of the structure

hb

m

Berm slope

tanaB


Armour Freeboard in relation to SWL

Ac

m

Armour Width

Gc

m

The NN_Overtopping model then produces output in a file called: NN_OVERTOPPING.lis which is then loaded into Delft-FEWS. These data use the q parameter with units of m3/s/m, along with values for q at 2.5, 5, 25, 50, 75, 95, and 97.5 %.

Configuration

The adapter needs to be supplied with the input and output time series files via the inputTimeSeriesFile and outputTimeSeriesFile elements so it can read and write data. The work directory needs to be specified, which must contain the NN_Overtopping model executable so it can run. As an additional argument the location of the Runinfo.xml file will need to be specified. The Runinfo.xml file will have to be created by the general adapter. 

When the model is run if an input value has any of:

  • h less than 0
  • ht less than 0
  • Rc / Hm0 greater than 5
  • Gc / Hm0 greater than 10
  • B / Hm0 greater than 15

then the value is determined to be negative and marked as 0. This logic was present in the previous adapter and can be turned off by setting the property convertNegativeValues to off in the Runinfo.xml file:

Properties
<properties>
    <string key="convertNegativeValues" value="off"/>
</properties>

Below you will find an example configuration for calling the NnOvertoppingPreAdapter:

            <executeActivity>
                <description>Run NN Overtopping Pre Adapter</description>
                <command>
                    <className>nl.deltares.nn.overtopping.NnOvertoppingPreAdapter</className>
                    <binDir>%ROOT_DIR%/Modules/EuroTop/bin</binDir>
                </command>
                <arguments>
                    <argument>%ROOT_DIR%/Modules/EuroTop/FoC/Input/RunInfo.xml</argument>
                </arguments>
                <timeOut>600000</timeOut>
            </executeActivity>

Below you will find an example configuration for calling the NnOvertoppingPostAdapter:

            <executeActivity>
                <description>Run NN Overtopping Post Adapter</description>
                <command>
                    <className>nl.deltares.nn.overtopping.NnOvertoppingPostAdapter</className>
                    <binDir>%ROOT_DIR%/Modules/EuroTop/bin</binDir>
                </command>
                <arguments>
                    <argument>%ROOT_DIR%/Modules/EuroTop/FoC/Input/RunInfo.xml</argument>
                </arguments>
                <timeOut>600000</timeOut>
            </executeActivity>







  • No labels

Disclaimer