Climate change has a historical impact at universal and local levels over the past era. Climate change is one of the greatest challenge issues in the globe for meteorological research. Air temperature estimation, in particular, has been measured as a significant feature in weather impression studies on industrial sectors, environmental, ecological, and agricultural. Accurately predicting air temperature guides to measure lifestyle, perform a key character for the government, industries, and public in development activities. In this paper, we investigate the use of various data mining approaches such as Support Vector Machine (SVM), Decision tree (DT), and Naïve Bayes for air temperature prediction within Sulaymaniyah City in Kurdistan, IRAQ. The metrological data is collected from the local Weather Forecast Department in the city within the range 2013 to 2018 inclusive. A dataset for the metrological data was developed and used to train the data mining algorithms. The proposed data mining algorithms were tested on the dataset to predict the air temperature and the performance of these algorithms were compared using standard performance metrics. Support vector machine has accomplished promising performance among using algorithms.
Air Temperature Prediction, Support Vector Machine (SVM), Decision Tree (DT), Naïve Bayes (NB), Climate Change, Weather Forecast
Author ORCID ID
Co-Authors ORCID ID
Mohammed Salih, Yusra Mohammed; Murad, Sherko; and Tahir, Brzu
"Air Temperature Prediction Using Different Datamining Approaches In Sulaymaniyah City In Iraq,"
Passer Journal: Vol. 3
, Article 1.
Available at: https://passer.garmian.edu.krd/journal/vol3/iss2/1