India is predominantly an agricultural country, and weather forecasting has always relied on model-based methods. Water is a necessary requirement for human living, and rainfall is one of the primary sources of this resource. Rainfall forecasting is a critical responsibility for agricultural and meteorological departments, yet it is also one of the most difficult. The demand for water has increased as a result of the growing population. As a result, the availability of water has decreased as groundwater levels have been depleted. Chennai, in particular, is significantly reliant on rains to replenish its groundwater resources. As a result, accurate rainfall forecasting is critical. For rainfall prediction, many techniques such as ARIMA, ANN, Regression analysis, Genetic Algorithm, Fuzzy logic, SVM, and others are used. This research shows how to use the k-nearest neighbour data mining technique to estimate Chennai rainfall. The error measure Mean Absolute Percentage Error (MAPE) is used to validate the model, and analysis shows that k-nearest neighbour for k = 3 produced the best results when compared to k = 5.
Author(S) Details
M. Mallika
Sathyabama Institute of Science and Technology, Chennai, India.
M. Nirmala
Sathyabama Institute of Science and Technology, Chennai, India.
View Book:- https://stm.bookpi.org/RAMRCS-V8/article/view/5741
No comments:
Post a Comment