The keystone to success in oil prospecting or in
mineral exploration is to keep cost on exploration and development in
check. Today there exist many different approaches to predict if oil or
mineral deposit is in the area or not. All these ways are directed on
diminution quantity of wildcat wells that should be drilled for
investigation of the area with oil or mineral deposit. Oil prospectors use
geologic and geophysical methods, subtle changes within the Earth's magnetic
and gravitational fields, stratigraphy,
super-sensitive optical nose, and others to increase the probability of
exploration success. Subsistence so many different ways that were used for
identification of oil or mineral deposits lead us to the conclusion that
among mentioned above ways of oil prospect there is no reliable way to
define deposit. Each of those ways have its strong and weak sides. We have
strong believe that combination of different ways of oil and mineral
prospecting can be quite efficient. However it is quite difficult to
implement this approach because of its complexity and dimension.
We propose way that overcomes dimension and
complexity problem. It is based on associative self-building neural network
that can effectively extract regularities from huge amount of data.
Computer processing power and available memory size are only two factors
that restrict network. That means user can train Artificial Foreteller on a
set of known oil deposit descriptions. Each description of deposit can contain
as many features as an oil prospector has or want to use. Features can be
represented as a set of codes like
Feature A - A1, A2, ... , An.,where
Feature A is a range of values, and A1, A2, ... , An - set
of sub ranges of values.
Feature B - B1, B2, ... , Bm.
Feature Z - Z1, Z2, ... , Zs.
Based on this set of features user can describe
each case of oil deposit as a sequence of codes:
Case 1 - A1,B2,
... , Zm.
Case 2 - A9, Bw, ... , Zr.
Case m - Ak, B6, ... , Zl
If there is history data about oil deposits and
those areas where oil was not found then it is possible to generate train
set of examples. A set of cases can be represented as following:
Train Case 1 - A1, B2, ... , Zm. -
Train Case 2 - A9, Bw, ... , Zr. -
Train Case m - Ak, B6, ... , Zl -
negative, - where "positive" means that the case describes area
where oil deposit was found, and "negative" means that oil
deposit was not found.
A set of cases is used for train and generating of
associative self-building neural network. During train Artificial
Foreteller processes the set and extracts combinations of values of
different features that are typical for positive or negative train cases.
Let's see how Artificial Foreteller processes a train set that is shown
These cases are represented in neural network with
corresponding nodes and connections. It will form four main nodes that
represent two positive, and two negative cases. At the same time it will
generate three new nodes that are common for more than one case. One of
them ( A1&B2&C5&G11&K13 ) belongs to two positive cases, one (A10&B21) - belongs to two negative cases, and one node (D11&E13&G11) belongs both positive and negative cases (Case2,
Case3). As a whole, generated network can be represented like sum of
products and dispersions :
((A1 & B2 & C5 & G11 & K13) & D1 & E23 & F43 & L7 & M8 & N22 & O11 )OR((A1 & B2 & C5 & G11 & K13) & (D11 & E13 & G11) & F33 & L8 & M19 & N21 & O17)OR NOT((A10 & B21) & C15 & (D11 & E13 & G11) & F23 & K18 & L5 & M14 & N11 & O2)OR NOT((A10 & B21) & C14 & D8 & E11 & F3 & G1 & K19 & L6 & M4 & N1 & O4)
Associative self-building neural network is not a
"black box". The formula given above can be analyzed to separate
most important features from minor ones. It can be used as a powerful tool
for data analysis directed on selecting most representative features.
In example shown above the combination of features A1&B2&C5&G11&K13 is common for two cases that describe deposits
where oil was discovered. Combination of features A10&B21 is common for two cases that describe areas where
oil was not found. And combination of features D11&E13&G11 is common for two cases that belong both positive
and negative descriptions. When Artificial Foreteller predicts situation it
assesses activated nodes and if activated node represents combination of
features A1&B2&C5&G11&K13 then its prognosis is positive. If a node that
represents combination of feature's values A10&B21 is activated then Artificial Foreteller predicts
that the area has no oil. In case when a node D11&E13&G11 is activated Artificial Foreteller can give only
assessment of the situation. It can predict that the area can contain or
not oil deposits with % probability.
User, who trains the system, can analyze network
and decide if it necessary to keep features D, E, and G, or remove only sub ranges D11, E13, and G11. After that Artificial
Foreteller can be trained again user can check if its prediction feature
becomes better or not. This way user can select most important and
representative features that describe area with oil or mineral deposits and
remove less important ones.
With help of generated neural network Artificial
Foreteller will predict or recognize area with oil deposits. Artificial
Foreteller can have as many network as many problems it should solved. That
means user can train Artificial Foreteller on separate criterion like
subtle changes within the Earth's magnetic and gravitational fields or
geophysical methods, or other.
Artificial Foreteller Structure
Initially network structure consists of two layers. The lowest layer
is a set of sensors. The second layer consists of receptors connected to
Each feature that describes condition of the area where might be oil
corresponds to a sensor. Sensors are divided into two types - qualitative
and quantitative. Qualitative sensor transfers only signals
"YES"/"NO" to the receptor that is connected with the
sensor. Signal "YES" activates the receptor. Quantitative sensor
is connected with a set of receptors. Range of values that sensor receives
is divided into a set of sub ranges. Current version of preprocessor can
form from 3 up to 50 sub ranges. Accordingly, quantitative sensor can combine
up to 50 receptors. In that case receptor becomes activated only if the
sensor sends a signal that value corresponds to a sub range of values that
was confronted to the receptor. Nodes of associative self-building neural
network are formed by network builder only during training sessions.
During train neural network is formed. In its
structure all derived regularities (or combination of features) are
represented with nodes and their weights. In a mode of oil deposit
prediction, entered into Artificial Foreteller description of the area
where oil might be activates part of the neural network. Activated part of
the neural network sends signals about activation into Artificial
Foreteller of Oil or Mineral Deposit where they are assessed. As a result,
Artificial Foreteller of Oil or Mineral Deposit issues prediction if the
area contains oil or not.
Associative self-building neural network can be
used not only for oil or mineral prediction, but for classification and
data analysis. Analysis of network structure is quite important to derive
most significant features. Associative self-building neural network works over
and accumulates vast amount of information about oil areas.
Artificial Foreteller is a new powerful system that demonstrates
extraordinary ease of use for prediction, and classification situations.
Artificial Foreteller analyses current input values and predicts situation
with oil or mineral deposits. As it well known human being can operate with
not more than 7 criteria at the same time. As distinct from human being
Artificial Foreteller is able to operate as many different criteria and
features as it has been trained.
Artificial Foreteller can
"remember" thousands of oil deposit descriptions in its neural
network and use them for analysis of the current one. It forms prediction
based on derived from train data set of regularities and analogies among
analyzed and known situations.
Artificial Foreteller was written in VC++ and
works under MS Windows98/me/NT/2000/XP. A virtual memory storage was
developed to store neural network and let the system to create network with
size more than size of PC central memory. With help of virtual memory
storage neural network became portable and can be transferred among
parties can contact us at:e-mail