Introduction modelling a situation by observing its behaviour

Introduction

            This paper discusses the
implementation of artificial intelligence technology (technology with the
capability of solving problems which would normally require human intelligence)
into the selection and manipulation processes of flow and water quality models
in coastal environments. Currently, various numerical models (typically, modelling
a situation by observing its behaviour over time and manipulating the data
mathematically) are used to solve flow and water quality problems. However, the
selection of a model is a very specialised and difficult task, requiring
significant knowledge of the applications and limitations of models, model
features must match with the particular situation. In addition, the manipulation
of certain models requires an experienced user. Therefore, due to a lack of
knowledge of factors such as water depth, water velocity, grid spacing etc., inexperienced
users will have difficulty with these tasks. Artificial Intelligence has the
ability to store knowledge to aid all users with the selection and manipulation
of mathematical models.

 

Need to integrate with Artificial Intelligence

            The manipulation of the models is
necessary to account for changes in initial parameters (as results may be
skewed if these changes aren’t made). Most model users lack the knowledge to
understand, model and evaluate the data and subsequently models can be misused,
underutilized and can even lead to incorrect conclusions. Within model
manipulation, the aim is to achieve a good standard of simulation. Model users
are able to modify one or two parameters of a model to suit a certain situation
but any more and there can be confusion. AI techniques are able to replicate
this and can cope with further manipulations, maximising the effectiveness of
current models. The latest generation of models can integrate AI technology
with computational methods to solve and analyse issues with fluid flows to form
a single system to aid non-experienced users.

 

Integration with Artificial Intelligence

            The
integration of AI technology will provide an effective decision-making tool and
will quicken the water quality planning and control process, by providing faster,
more effective and more organised (better storage, retrieval and manipulation
of data) models. 4 AI algorithms have been explored, KBSs, GAs, ANNs and FISs,
these are explained below:

 

1 – Knowledge
based systems (KBSs)

Interactive,
user friendly computer programs that replicate the decision making and
evaluation processes of experts in solving a specific problem, through
delivering advice, answering questions and justifying conclusions. Most of the
KBSs knowledge is derived from expert knowledge which is stored in a knowledge
base from which inferences are made based upon responses to certain questions. An
example of a KBS in water flow and quality modelling are a decision-support
system for river basin planning and management. Current models only aid in
model selection and not in manipulation, selection alone requires a large
effort to program, with more complex issues the integration of KBSs becomes
very complicated.

2 –
Genetic algorithms (GAs)

These
are ‘evolutionary optimization algorithms’ that utilise models of the
evolutionary process to develop a problem solving system. They use biologically
inspired search techniques like natural selection, reproduction, crossover and
mutation to determine the optimum response. A knowledge base (including prior
knowledge and knowledge of all previous solutions deduced by the system) is
coupled with an artificial survival of the fittest logic system to choose the
best solution. An example of an application is the use of GA to optimize
wastewater treatment in a water quality management model. These algorithms are
highly effective at solving complex, multi-parameter problems.

 

3 – Artificial neural
networks (ANNs)

Algorithms based
on the current understanding of the brain and its nervous systems, the inner
workings of an ANN are outlined in Figure
1. Some issues with ANNs are that they utilise all environmental parameters
rather than the most important parameters in water quality. Additionally,
little is done to extract information from the network’s learning system, so it
is often not specified how conclusions are reached. This technique requires further
development in relation to water quality problems. An example of an application
is where an ANN was used to optimize watershed management for a reasonable
balance between water quality demand and farming industry restrictions.

 

4 – Fuzzy
Inference systems (FISs)

This
algorithm specialises in modelling complex and vague systems when the
constraints and objectives are unclear. Data entering the system is mapped to
values that the fuzzy knowledge base can understand, the logic base then
applies an ‘if – then’ concept basing its decision from its knowledge base, to
determine the outcome. Essentially, in a fuzzy system a computer may not
provide a yes or no question with a yes or no answer and will provide a
justification of the response, similar to what humans do at times. An example
of a FIS is in the design of a algae bloom predictor based on the daily
fluctuations of water quality parameters (e.g. pH, temperature, dissolved
oxygen etc.).

 

Conclusion

            In conclusion, current water quality
models have a variety of constraints and are difficult to use in terms of model
selection and manipulation, especially for inexperienced users. AI technologies
provide the ability to apply expert knowledge to situations without the
presence of an expert model-user. KBSs, GAs, ANNs and FISs are possible AI
technologies that can be used in water quality modelling and to decide whether numerical
models represent actual phenomena. In further development it is projected that
two or more of these systems can be combined to produce an even better water
quality modelling system. Moreover, better user interfaces and more efficient
AI technologies are in the works.

x

Hi!
I'm Mack!

Would you like to get a custom essay? How about receiving a customized one?

Check it out