Water obtained from surface or subsurface sources is crucial for life. But direct use of raw waterrnhas serious health risks. Different water treatment processes can be used to make the raw waterrnsafe for domestic purposes. Coagulation and Flocculation is one of the treatment stages used tornremove colloidal particles through the use of chemicals (coagulants) that enable the formation ofrnlarger flocs that can be easily removed by sedimentation and filtration. Determination of thernoptimum coagulant dosage is important to meet the required water quality. For instance, a highrncoagulant dosage may lead to high residual chemical in the treated water, high sludge volume, andrnincreased load on the filter units. All these can result in poor water treatment performances, highrnoperational costs, and process complications. Jar test has been used widely to determine thernoptimal coagulant dosage for a given water quality. However, this practice has some drawbacksrnsuch as it is time-consuming, the probability of making errors is high and it is impractical forrnhighly variable raw water turbidity. Consequently, the need to develop new tools and techniquesrnto determine optimum coagulant dosage becomes important. However, quantifying thernrelationship between the process inputs and output in the water treatment unit process is veryrndifficult with the existing process model. Thus, Artificial Neural Network was used to develop thernmodels in this research as it is a robust technique that allows the development of a multi-variablernand complex non-linear relationship. ANN Multi-Linear Perceptron type with one hidden layerrnwas used to simulate the jar test for the optimum coagulant dosage forecasting. Two models wererndeveloped and their performances were evaluated based on Root mean squared error (RMSE) andrncoefficient of determination (Rrn2rn). The first model which enables prediction of turbidity for a givenrncoagulant dosage and other factors was the process model. The second model which allowsrndetermination of optimum coagulant dosage to attain the desired turbidity level is the InversernProcess Model. The RMSE and Rrn2 rnvalues were found to be 0.0748 NTU and 0.6121, respectivelyrnfor the Process model. For the Inverse Process model the RMSE and Rrn2rn values were found to bern0.225mg/l and, 0.9823, respectively. These indicate that a good performance of the ANN-basedrnmodel to simulate the jar test could be obtained. The models can be used to optimize therncoagulation process within the available raw water turbidity range of Legedadi Water TreatmentrnPlant.