Tutorial 1: AgielNN Data Preparation

AgielNN is basically used to make a prediction of unknown result based on specific input parameters. However, AgielNN requires to be trained first before it ready to conduct any of forecasting. And to make sure that the training is going well, it is also recommended to conduct checking or testing using blind test. So, in general we need 3 kinds of data which are data training, data checking, and data forecasting. 

Data Training & Checking.
Data training and checking must have the same format, which by means of having similar number of column. And those two data are ideally coming from the same data source which is actual data from the field. For example, i want to make a prediction of parameter Z which is estimated to be a function of X, Y, and i have 120 real data from experience as you can see in this SampleANN1.XLS. For simplicity, the data can be divided in to training and checking data by portion of 75:25.  Before inputting to AgielNN, those divided data then must be copied to text editor (Notepad of other similar software) and saved as 2 separated files namely Sample1_train.txt and Sample1_check.txt.

 

Data for Forecasting
Since we want to forecast from 2 variables input, so the data for forecasting must have 2 column only. For example, please refers to this Sample1_Forecast.txt. Must be noted that all input data for forecast must in the range of data input used in the training. For example, if A in the training have minimum value = 0 and maximum = 100, then all A data that will be used for forecasting must lying on 0 to 100. Otherwise, the forecast might goes wrong since the neural network system is only trained for the specific range of data.

!!!REMARKS!!!
AgielNN doesn’t require normalization data since it is automatically do normalization. However, data variation should have linear variation and not exponential or logarithmic or else. For example, if you have variable Z as a function of Log(A), then it is recommended to convert A to C first, where C=Log(A), and use C as input for forecasting the Z.

 

Inputting Data to AgielNN
This is a simple task actually, just go to “Data Source Preparation” window, and click and you will be prompted with this kind of dialog. Fill the name of the data, let say “Data1_Training” and click OK.

A new data source will be created. After that, click the data name. And you will get an empty table on the right panel. To import table from the data that we have prepared previously, simply right click inside the table, and select “Import the File”, or just click the button “Import Table from File” below the table. Browse the Sample1_Train.txt and open. Repeat the procedure for Sample1_Check.txt and Sample1_Forecast.txt named as “Data1_Check” and “Data1_Forecast”. By doing that, now you should have 3 data source, Data1_Check which has 3 columns, Data1_Train 3 columns, and Data1_Forecast 2 columns and this kind of interface.

So, data preparation is finished. This should be a very easy data preparation.. 🙂

This is the end of this tutorial. Should anybody have question, please don’t hesitate to contact my email.
——————————————————————–
Written by Sugiyanto Suwono
Bekasi, March 13, 2013

Tutorial 2: Editing Log Data

Editing Log Data

This tutorial will cover feature of LogView++ to deal with las file, including import, export, doing calculation of log data, making partial log, and combining log data.. This is the basic operation that everybody need to understand before dealing with complicated graphical plotting and cross-sectioning.

Format File
Supported format file in LogView++ version 2012.2 is still LAS 2.0. Other LAS version might resulting unexpected result. LAS 2.0 must have at least the following keywords in the header file:

~Version Information
VERS. 2.0:
WRAP. NO:
~Well Information
~Curve Information
DEPT. :
~Other information
~A

Remarks:
~Version Information, gives the version of the LAS format and wrapping mode. Make sure the format is 2.0. Wrapping true means that the data (in the ~A section) in the log is formatted in multi-line rather than single line.
~Well Information, usually includes the well identification like well name, start depth of log and etc.
~Curve Information, should includes all column data name exists in the file. At least, it should contain DEPT.
~A or ~Asci Data Section, is the final section that filled up with all numerical values of the log data. Number of column must be equal to the number of column defined in the ~Curve Information.

Basic Operation of LAS File
Importing LAS File
This is simple. But, be AWARE, some people made a mistake by choosing wrong menu. Please choose menu “Log Data” and “Import”. DO NOT USE MENU FROM “Project” or “Well” !!!!!!

After clicking that menu, browse a valid LAS file, and open. You will be prompted with this dialog..

Give a name, and decide whether this imported log would be a part of specific well or just create new well for it. This null number is actually magic number that is defined to accommodate the NULL number in log file. Default value is -999.25 (I don’t know why somebody choose that strange number.. 🙂 )
Just click OK and done!!.

Exporting LAS File
It can be done simply by going to menu “Log Data” and select “Export”. You must be prompted by a dialog. Select the proper well and the log, and export. Done.. Nothing complicated.

Renaming, Duplicating, and Deleting the Log
Right click in the main data tree as shown below, select Setting for renaming, Duplicate for duplicating, and surely Delete for deleting.
You must noted that deleting a log data or anything would be allowed in case of the data is not being used by any of window or editor.

Showing Imported Las File
To show the imported LAS File, simply go to tab Log Editor, then select well name and las name to be shown. Correct operation should give this kind of screenshot.

This log editor shows the tree of data available in the log, table of all data, and also statistic data of each column that should be useful for determining the limit of value in the next plotting procedure.

Editing Imported Las File
Rename & Delete Column
It can be simply done by right click the tree of log data and select menu rename or delete…

Create Partial Log
Creating a part of log sometimes is very important especially if we want to calculate a certain interval that have a very different property compared to whole log interval. To do that, right click tree data, and select “Create Partial Log”. You will get to this kind of dialog.
Those dialog is example if we want to make a partial log of the existing log data, only for the first 100 rows, and only for column SP, GR, and DEPT. By clicking “Create”, you will have new partial log data in the same well as the original log from. To show the partial log, just do select the new well log in the log editor window.

Advance Calculator
I call it advance because of this is probably the most difficult operation and the most useful feature in this editing the Las file chapter. Right click on tree, and select menu “Advance Calculator”. And you will see this kind of dialog.

This dialog contain 3 parts which are formula history, variables, and formula to be calculated. The formula history shows any formula that you ever calculate previously. To re-calculate again the previous calculation, just double click the history and you will get your formula in the form.

Variables shows all data column available in the selected las file and its aliases. For example, in above picture, rows no-1 shows X0 and DEPT1. That means the column name is DEPT1 and the alias is X0. !!!PLEASE BE CAREFUL!!!. You are only allowed to use the alias in the formula, not the real name.

In the formula section, it has operator, variable name, and formula itself. Operator is operator.. 🙂 like +, – , log, and etc. Variable name is the expected result column name. and the formula is of course the equation to be calculated. We can write formula single line or multi-line format. And it could be a very complicated formula if you wish. Please take a look at this example formula.

single line formula:
if(X0>1000 & X1!=-999.25, X1/100, -999.25)
——————————————
it should clearly explained.. 🙂

multi-line formula:
A:=X0;
B:=X1;
C:=A+B;
C
——————————————
first and second line, we make new sub variable called A & B.
third line, C is derived from A & B
last line, C is return as final result.
We can also write as follows…
——————————————
A:=X0;
B:=X1;
A+B
——————————————
those 2 example will give same result & same meaning actually.. 🙂 If you you want to know more about the supported operator, please click “More” for further documentation. After formula is ready, click “Execute”, and you will have new column data in the table. Enjoy it..

Combining Two Log Data
Combining two log data is also one of the difficult task to do since sometime a little bit confusing. More over, I have no enough time to test this feature. So, probably you will encounter an unexpected bug while doing this.

For example, we have 2 partial data like this:
Las File – 1:

Las File – 2:

We want to combined those two files to become one file for simplicity.

To do that, go to menu bar “Log Data” and select “Combine LAS Files”. By doing that, you will be prompted by this kind of dialog. Browse LAS File – 1 and 2 from the dialog. By default, in case of data intersection occur, it will used data from LAS File-1. But actually you can change it to LAS File – 2 as well.

Once two LAS Files ready, click “Add Column” and select the appropriate column pairs for those two LAS Files. Figure below shows how to add 4 column in the targeted merged file. In the first 2 pictures, it shows pairs that both Las File – 1 and 2 are having the column. In the second row, the GR column is not available in the Las File-2. So we can choose NULL for that. The ILD is also not available in the Las File – 1. So we can also choose the NULL for that.

After all columns are ready, last but the most important thing is that we must specify the Key Column. This is the column that both Las File-1 and 2 have it and will be used for reference of merging. Ideally, this Key Column should be the DEPT since we want to merge mainly for the depth.

After we finish the merging setup. Click execute and you will prompted to save the resulted file. And you can imported to the LogView++ to compare the result with the data source. Doing the correct procedure should give this kind of result.

This is the end of this tutorial. Should anybody have question, please don’t hesitate to contact my email.
——————————————————————–

Written by Sugiyanto Suwono
Bekasi, March 12, 2013

Tutorial 1: Introduction to LogView++

Introduction to LogView++
(see also LogView++ Presentation)

 

Graphical User Interface:

LogView++ is basically a kind of petrophysical software that commonly used to manipulate LAS data that is resulted from oil & gas well logging. In the first version (2010.12), it was developed mostly to helps engineer, geologist, or petrophysicist to do a single well log plotting. However, in the latest version (2012.2), LogView++ has been extended by some feature such as plotting completion, zonation / layering, and also cross-sectioning. In this tutorial, version used for explanation is 2012.2.

Generally, the graphical interface of LogView++ is divided into 3 areas. The first area is the main menu bar (ribbon bar) that contain many of icons that give you direct link to many features in LogView++. Following pictures are all tool bar available in the ribbon bar.

This LogView++ file management is based on project file. Above “Project” ribbon bar lets you open, save, and close the project. And this ribbon also allows you to see the diagnostic log in order to understand some hidden message delivered by LogView++.

Above “Well” menu enables you to make new well, as well as import and export well header from file.

Above “Log Data” menu bar deals everything related to log (LAS File) data.

Zonation menu is dealing with everything about zone or layers or well top.

Completion ribbon bar gives an access to completion editing, including completion database management.

Log template menu of course deal with log template.

And the last bar, helps give you access to main documentation of LogView++ and about dialog.

File Type Supported:
There are some file formats that are currently supported by LogView++ as follows.
– Project File (*.pro++)
– LAS File (*.las)
– Well header (text file *.*)
– Completion Package (text file *.*)
– Log template (*.template)
– Zone list (text file *.*)

 

LogView++ Main Features:
Following list is the main feature that currently supported by LogView++…

  • Manipulating Log Data
    Manipulating log data includes modifying the content of the LAS File by renaming column, deleting column, calculating new column based on existing column, creating partial log, combining 2 LAS files, and etc. Detail procedures of this feature would be explained in the next tutorial. The following screenshot shows the main log editor.
  • Manipulating Zone / Layer / Well Top
    Manipulating zone including export & import zone data, setting zone color and style. It is very important for you to make cross-section. Detailed tutorial of zone editing will be discussed further.
  • Manipulating Well Completion Data
    Completion editor is very important editor before creating well sketch in the log plot. This completion editor is very customizable. You can create your own completion database, and also support multi-completion package for one well. Detailed procedures of editing completion package and database will be discussed in this tutorial.
  • Manipulating Log Plot Template
    Template editing basically is creating rules for next step of log plotting and cross-sectioning. LogView++ 2012 supports unlimited track, unlimited curve in a track, unlimited area in a track, and also completion track. This LogView++ version not yet supporting integer track like rock type and lithology description, which is one of the future development track of LogView++. Detailed procedures of this template editing will be discuss in the next tutorial.
  • Creating Log Plot
    Log plotting is certainly the most important feature in LogView++. After a las file and a template is ready, you can easily create log plot by selecting the las and template in the Log Plot panel. Detail tutorial of log plotting is described in the next tutorial.
  • Creating Cross-Section
    Cross-sectioning is also one of the most important feature in LogView++. It is available only in LogView++ 2012 and newer version. Besides creating common cross section, some important feature like global template, custom depth, and flattening. Detailed cross-sectioning procedures will be discussed in this page.

This is the end of this tutorial. Should anybody have question, please don’t hesitate to contact my email.
——————————————————————–

Written by Sugiyanto Suwono
Bekasi, March 12, 2013