Annually, earthquakes cause human and material losses. For instance, between 1998 and 2018, 846 thousand deaths and about US$ 661 billion of economic losses were recorded due to earthquakes. Currently, there is no clear precursor to forecast earthquakes. However, numerous investigations have attempted to find precursor proxies based on Land Surface Temperature (LST) anomalies. In this study, a big database collected from GOES/ABI instrument during the full year 2020 has been used to calculate the LST anomalies in the earthquakes zones. A total of 1350 earthquakes of Mw = 4 were studied in 2020. Two methods commonly used in the literature, the interquartile method, and the standard deviation of the time series, have been applied to detect LST anomalies. The confusion matrix, some figures of merit, and the receiver operating characteristic curve have been used to evaluate and enhance the performance of the methods and choose the optimum decision threshold. A positive anomaly is usually found before the earthquakes, followed by an LST decrease after the event.