College of Computer Science and Mathematics

Discussion of the master’s thesis in the College of Computer Science and Mathematics -Department of Statistics and Informatics Department entitled:

Climatic Time Series Forecasting by Using Echo State Network and State Space Model Based on ARIMA Model

In continuation of the scientific research movement and with the follow-up and presence of the Dean of the College of Computer Science and Mathematics Respected Professor Dr. Duha Bashir Abdullah

Master’s thesis by  Suha Saleem Mahjoob Khalaf

supervised by Assis.Prof.Dr. Osamah Basheer Shukur

This thesis includes: Forecasting climate time series using State Space (SS) method based on ARIMA model which is called ARIMA-SS hybrid model to address the problem of uncertainty caused by non-linearity of temperature data. Echo State Network (ESN) based on ARIMA model which is called ARIMA-ESN hybrid method was used to address the problems of non-linearity and uncertainty.

The study addressed:  To predict the minimum temperature for the cities of Mosul and Baghdad for the period (11/1/2011-10/31/2022) using hybrid models. Since the minimum temperature data for Mosul and Baghdad are heterogeneous, the Time Stratified (TS) method was used with the data to align the data in two seasons (hot season and cold season) to obtain more homogeneous data to predict minimum temperatures.

The study aims : To improve the accuracy of minimum temperature prediction by using methods that are more suitable for time series data that suffer from the problem of non-linearity that necessarily leads to the problem of uncertainty in the modeling process.

The discussion committee consists of

Prof.Dr. Zakariya Yahya Nuri  (Chairman)

Assis.Prof.Dr.  Muthanna Subhi Suleiman  (Member)

Assis.Prof.Dr. Ahmad Najm Sheet (Member)

Assis.Prof.Dr. Osamah Basheer Shukur (Member and Supervisor)