This chapter provides a background to the research problem and the significance ofthe study. It states the research aim, objectives, questions and scope of the study. Thechapter gives an overview of the perspective of rainfall and its impact on agriculture.Focus is on seasonal rainfall forecasting technique currently used in Zambia and howto improve its accuracy. The increasing interest and need by the public for reliableseasonal rainfall forecast provoked further investigation, resulting in this thesis. Aconceptual framework model is used to illustrate a theoretical overview of the intendedresearch and show the order of processes, including how the variables to be consideredmight relate to each other.
1.1 BackgroundWeather describes the atmospheric conditions at a given place over a short duration oftime 1. It is defined in terms of weather parameters like temperature, pressure, wind(speed and direction), clouds and rainfall. Weather forecasting is a scientific estimationof future weather conditions 2. Weather forecasting applies science and technologyto predict the state of the atmosphere for a given time and location 3, 4, 5, 6.1Rainfall is a natural climatic phenomenon resulting from atmospheric, oceanic circulationsystems and complex physical processes that cause an amount of rain to fallat a place during a particular period 7, 8. It is a stochastic process which dependson some precursors from other parameters such as temperature, wind, pressure andother atmospheric parameters 9.
Rainfall is one of the weather parameters whoseaccurate forecasting has significant implications for agriculture and water resourcemanagement 10, 11. Rainfall is the most important climate variable that affectsagriculture in countries that depend on rain fed agriculture 12.A forecast describes what will possibly happen in future. Weather forecasting entailspredicting how the present state of the atmosphere will change. Weather forecastingis a demanding operational responsibilities carried out by meteorological services.It is a complicated procedure that includes numerous specialized fields of expertise13, 11.
Generating weather forecast is complex because in the field of meteorologyall decisions are to be taken in the visage of uncertainty 11. The chaotic nature of theatmosphere and systems responsible for events are a culmination of instabilities 14.Weather forecasts are used in many sectors like agriculture, advisories, and severeweather alerts. Modern weather forecasting of severe weather alerts and advisoriesare done to protect life and property 15.Weather forecasting is a canonical predictive challenge that has depended primarilyon model-based methods. Making inferences and predictions about weather has beenan omnipresent challenge throughout human history. Challenges with accurate meteorologicalmodeling brings to the fore difficulties with reasoning about the complexdynamics of Earth’s atmospheric system 16Rainfall forecasting is part of weather forecasting and is very essential for varioussectors 17.
Of all the weather parameters, rainfall forecasting is the one that is mostcomplicated and challenging operational task done by meteorological services worldover11, 18. Rainfall prediction is challenging, demanding and complex due to thevarious dynamic environmental factors, both spatial and temporal random variations.Rainfall is a highly non-linear parameter 10, 8, 19, 20, 21.2There are four major different weather forecast types, namely;Now-CastingNow-casting weather forecast is a very short-period prediction that maps currentweather conditions and changes to predict weather conditions for a period of 0 to 6hours ahead 22, 23, 20. With now-casting, it is possible to forecast smaller featureswith reasonably more accuracy 23.Short-Range ForecastShort-range weather forecast gives a prediction of the atmospheric condition in eachsuccessive 24 hours for a period of 1 to 3 days. Such forecasting models are set upto produce daily averages in order to use the same time scale as rain gauges observations.Most results of short-range forecast show good agreements between thepredicted rainfall and measurements from rain gauge stations for the given period24.
Medium-Range ForecastMedium-range weather forecasts gives prediction for a period of 4 to 10 days. It givesa forecast of average weather conditions and may prescribe weather on each day withprogressively lesser details and accuracy than for short-range forecasts 25.Long-Range ForecastLong-range forecast, also known as extended range weather forecast ranges from morethan 10days, a month, a seasonal, and a year to even forecast for longer period. LongRange Forecasts (LRF), like seasonal rainfall forecasts are even more challenging toforecast as atmospheric systems may change in time and space 25. Weather forecastsbecome less accurate as the difference in current time and the time for whichthe forecast is being made (as the range of the forecast) increases 4, 26.Amongst all weather parameters, rainfall is the one that mostly affects human lifeand livelihood in developing countries and least developed countries like Zambia wheremajority of the population depends on rain fed agriculture 11, 27, 28, 1, 29.
Rainfallalso affects many sectors including but not limited to water resources management,3energy, tourism, health, disaster risk reduction (DRR) and infrastructure development.These are the core focus areas of the 7 National Development Plan (7NDP)30.People wish to know in advance whether there would be normal rainfall in the comingrainy season.
To achieve this requirement, every National Meteorology and HydrologicalServices (NMHS) needs to forecast well ahead the start of the crop season. Suchrainfall forecasts are used by both farmers and government to plan for the ensuingrainy seasonal 12. Thus, accurate seasonal rainfall forecast is essential for planningof agriculture, water resources management, and many other sectors 31, 32, 12, 33.Accurate long-range forecast provides farmers with sufficient time to plan for cropproduction by adopting appropriate crops and varieties, that will be suitable for theexpected rainfall 34.Seasonal rainfall forecast is the prediction of the expected rainfall performance forthe given rainy season. It is usually generated in August and published in Septemberin the Southern African Development Community (SADC) region, Zambia inclusive.
Empirical statistical forecasting model is developed using Simple Linear RegressionModel (SLRM) to forecast Seasonal rainfall. This model describes a linear relationshipbetween two variables; X as independent which is Sea Surface Temperaturebasins and Y as dependent is rainfall. Statistical models based on regression analysisand eyeball inspection are used. Current seasonal rainfall forecasting methods usedin Zambia have been proved to be less accurate 7, 8.This research proposes to use Artificial Neural Networks (ANNs) in order to improvethe accuracy of seasonal rainfall forecast in Zambia, because statistical models havesome inherent limitations over long range rainfall forecasts 35, 36.41.2 Problem StatementThe current seasonal rainfall forecasting method used in Zambia assumes a directcorrelation between the Sea Surface Temperatures (SST) and station rainfall observations37. Atmospheric systems are not governed by only these two systems, butthis assumption ignores availability of other systems in influencing rainfall 38.
Otherparameters that may have influence on rainfall include Indian Ocean Dipole (IOD),temperature, wind speed, relative humidity and pressure 11. Moreover, changingclimate has introduced further uncertainties in this assumption of a direct linear correlationbetween observed rainfall data and SST 38, 39.A limitation of high spatial variability of station point rainfall observations increasesthe inaccuracy and uncertainty that reduce the skill (accuracy) of the seasonal rainfallforecasts. Zambia’s area is about 752, 613KM2, but only 33 weather stations whichhave enough historical data that is used in generating of the seasonal rainfall forecast.A common weakness of all statistical rainfall forecasting models is that while thecorrelations are assumed to remain constant for the duration of the forecast, theyusually change with time and slowly lose their significance, which makes the rainfallforecast less accurate 40. Long range weather forecasts like seasonal rainfall forecastbecome less accurate as the difference in time between the present moment and thetime for which the forecast is given increases.
Furthermore, some stages in the current seasonal rainfall forecasting process requireexpert knowledge through eye ball inspection which is subjective and not easy to passon through an educational process 41.Therefore, the current seasonal rainfall forecast in Zambia is not of high efficacy.51.3 Aim of the StudyThis research is in response to forecasting seasonal rainfall accuracy inefficiency. Thus,the aim of this research is to improve accuracy of forecasting seasonal rainfall inZambia through the use of Artificial Neural Networks.