master’s thesis by ” Baraa Wisam Abdulghani Abdullah” Department of Statistics and Informatics

Discussion of the master’s thesis in the College of Computer Science and Mathematics -Department of (Statistics and Informatics) entitled: “Missing Values Imputation and Forecasting for Spatio-Temporal Climatic Variables by using Graph Convolutional Networks (GCN) ”

supervised by Dr. Osamah Basheer Shukur

The thesis addressed the problem of missing values, data heterogeneity, and nonlinear patterns in spatio-temporal climate time series, as well as their impact on the accuracy of data imputation and prediction.

The study addressed the use of the Graph Convolutional Network (GCN) for missing value imputation, normal temperature forecasting, and weather condition classification by exploiting the spatial relationships among five meteorological stations and multivariate climate data.

The study aims to to develop a Graph Convolutional Network (GCN)-based model for missing value imputation and improving the accuracy of climate variable forecasting and weather condition classification by exploiting the temporal and spatial relationships among meteorological stations, thereby enabling the model to capture nonlinear patterns and enhance modeling and prediction performance.

The discussion committee consists of

Dr. Muthana Subhi Sulaiman (Chairman)

Dr. Manaf Hazim Ahmed (Member)

Dr. Omar qusai jasim (Member)

Dr. Osamah Basheer Shukur (Member and Su

pervisor)