Abstract
Automated Forecasting System have been shown to be highly effective in
providing a wide range of integrated capabilities for time series analysis and
forecasting, econometrics and systems modeling and financial analysis and
reporting. We have presented a platform for the practical development and
design of a Rainfall Prediction System for the Kano City Metropolitan Area.
The system automatically makes future forecasts of rainfall using the rainfall
forecasting model derived from the inputted rainfall time series data. The
system when fully implemented will ensure accurate analysis and forecasting
processes that takes place over time in Kano. The language of implementation
is Visual Basic.
1.0 Background of the Project
It is well known that weather and climatic conditions exert a strong influence
on human activities.
The major goal of various national and international climatic programs is to
minimize the adverse and maximize the positive socioeconomic consequences
of weather and climatic variations (Mason, 1978; Lamb, 1981; World
Meteorological Organization, 1978). The capability to better predict weather
and climate events is likely to be the skill which ultimately achieves these
objectives. Using forecast information to improve societal well-being requires
satisfying three demanding, reasonably sequential prerequisites. These are: 1)
Identification of the most severely impacted economic sectors, 2)
Determination of which of these sectors possess the flexibility to benefit from
the use of climatic forecasts in decision making, and 3) The development of
accordingly focused climate forecast schemes (Lamb, 1981).
Satisfying the third prerequisite requires that socioeconomic evaluations be
performed to ensure that weather and climate forecast deliver economic value.
A number of studies have assessed the value of either actual or potential
forecast capabilities. One major objective of this project is to review past and
existing weather forecasting systems and models and based on their short
comings, design, develop and implement a weather forecasting system with
focus on rainfall prediction, which is the case for this project.
2
1.1 Statement of the Research Problem
Weather forecasting is the application of science and technology to predict the
state of the atmosphere for a future time and a given location (Wesley, 2008).
Human beings have attempted to predict the weather informally for millennia,
and formally since at least the nineteenth century. Weather forecasts are made
by collecting quantitative data about the current state of the atmosphere and
using scientific understanding of atmospheric processes to project how the
atmosphere will evolve (Wesley, 2008).
Once an all-human endeavor based mainly upon changes in barometric
pressure, current weather conditions, and sky condition, forecast models are
now used to determine future conditions. Human input is still required to pick
the best possible forecast model to base the forecast upon, which involves
pattern recognition skills, teleconnections, knowledge of model performance,
and knowledge of model biases. The chaotic nature of the atmosphere, the
massive computational power required to solve the equations that describe the
atmosphere, error involved in measuring the initial conditions, and an
incomplete understanding of atmospheric processes mean that forecasts
become less accurate as the difference in current time and the time for which
the forecast is being made (the range of the forecast) increases.
There are a variety of end uses to weather forecasts. Weather warnings are
important forecasts because they are used to protect life and property.
Forecasts based on rainfall and temperature are important to agriculture, and
therefore to traders within commodity markets. Everyday basis, people use
3
weather forecasts to determine what to wear on a given day. Since outdoor
activities are severely curtailed by heavy rain, snow and the
Wind chill, forecasts can be used to plan activities around these events, and to
plan ahead and survive them. Thus, the need to have in place appropriate,
reliable and accurate forecast model that can help predict or forecast future
weather conditions cannot be undermined. This has necessitated a research in
this direction to design, developed and implement a rainfall forecasting
software. The software will be designed using Visual BASIC programming
language and will make use of historical rainfall data from 1960 to 2010
collected within the Kano City area of Kano State, Nigeria.
1.2 Objectives of the Project
The project will majorly seek to design, develop and implement a rainfall
forecasting system. The forecasting system will provide the following
activities:
i.) Entering, editing and updating rainfall data;
ii.) Trend analysis of rainfall data;
iii.) Above all, the system automatically make future forecasts of rainfall
using the rainfall forecasting model derived from the inputted
rainfall time series data.
iv.) A rainfall computerized forecasting model interface.
1.3 Significance of the Project
A project of this sort to design and develop a software system that can predict
future rainfall for a given area, when designed and fully implemented will be
relevant in the following ways:
4
i.) It will help to minimize the adverse and maximize the positive
socioeconomic consequences of weather and climatic variations;
ii.) Such rainfall forecast information will help to improve societal wellbeing;
iii.) Furthermore, such weather warnings can be used to protect lives and
properties since an individual is already well informed of how the
weather will be beforehand;
iv.) Forecasts based on rainfall and temperature are important to
agriculture, and therefore to traders within commodity markets;
v.) Finally, weather forecasts can be used to determine what to wear on
a given day. Since outdoor weather forecasts can be used to plan
activities around these events, and to plan ahead and survive them.
1.4 Scope of the Project
The project focus mainly on rainfall predictions within Kano City, Nigeria
and fuzzy logic techniques will be used for the analysis.
1.5 Limitations of the Study
In carrying out this research work, we were faced with some limitations.
Designing a forecasting system is quite a complex task especially with the fact
that one is not quite efficient or skillful in the programming language of
implementation and learning the language alongside with academic work,
considering the short time allocated for the research work is not an easy task.
This has limited the research work to the scope specified in the previous
section above