Makine öğrenmesi algoritmalarıyla astronomik gözlem kalitesi tahminine yönelik karar destek sistemi geliştirilmesi ve uygulanması.

The effective and efficient use of the Eastern Anatolia Observatory telescope, which is planned to be made available to researchers upon completion of its installation, is important. Within the scope of this study, it is aimed to develop a decision support system for the projects presented by the researchers to be matched with the observation type, evaluated, and assigned to the most appropriate day, taking into account the local characteristics of the region where the observatory is located. For this purpose, first of all, the performances of four different algorithms were evaluated using naive Bayes, K nearest neighbor, decision tree, and random forest algorithms, resampling methods were applied, and the effect of attributes on the result was examined. Then, inspired by the multi-attribute utility theory method, a decision support model based on the calculation of utility valuescontaining the utility function formula was developed for each project. Benefit values represent success points for projects. The projects were classified according to the type of observation and ordered from the largest to the smallest according to the success score. Afterward, projects were prioritized in line with the predicted types of observations and assigned to the relevant days. With the developed decision support model, it is aimed to automate the evaluation process together with the effective and efficient use of the telescope. [ABSTRACT FROM AUTHOR]