Temperature Forecasting System Using Fuzzy Mathematical Model: Case Study Mumbai City

Temperature Forecasting System Using Fuzzy Mathematical Model: Case Study Mumbai City

Abdel Karim M. Baareh
Copyright: © 2018 |Pages: 10
DOI: 10.4018/IJAEC.2018070105
(Individual Articles)
No Current Special Offers


Temperature study and model development related to estimation is an essential and important task not only for a human life but also for animal life, agriculture, tourism, water reservation and evaporation, and many other fields. Regression is considered a dominant prediction model which is heavily used in forecasting in spite of the difficulties related to the number of available measurements, the order of the model and the nonlinearity of the data. In this article, the purpose is to use a nonlinear model structure to forecast the temperature at the airport of Mumbai city in India using the fuzzy logic technique. The datasets were collected for twelve months period starting from 1st of January 2009 to 31st of December at a weather underground in India. The datasets were divided into two parts, 288 days (80%) of the data for training and the remaining 72 days (20%) for testing. The results obtained and the error calculated using the fuzzy logic model were satisfactory.
Article Preview

Many researchers from different fields worked on temperature forecasting using different techniques, Al-Matarneh et.al, applied two different models for temperature forecasting, Feed Forward Neural Networks with back propagation algorithm and Fuzzy Logic model. Different evaluation criteria were used, the Variance Accounted For (VAF), and Mean Absolute Error (MAE). The results obtained were good and showed that the proposed models can act with more accuracy.

Radhika and Shashi, used the Support Vector Machines (SVMs) to predict the maximum weather temperature at a particular location based on the daily time series observations.

Hayati et.al, used the Artificial Neural Network with Multilayer perceptron (MLP) to predict the temperature for ten years dataset (1996 to 2006). The dataset was divided into two sets one for training and other for testing. The performance of the MLP network was very good with minimum errors.

Patel and Christian, developed a temperature forecasting model for Inland Cities in India. The dataset of one year of daily temperature observations was considered. Relative humidity and mean sea level pressure were measured as inputs variables. The obtained results showed a great decrease in the Root mean square error.

Complete Article List

Search this Journal:
Volume 14: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 13: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing