Modeling of the Earth’s rotation variations using a novel approach inspired by the brain emotional learning

DT is a quantity that converts universal time (UT; defined by the Earth’s rotation) to terrestrial time (TT; independent of Earth’s rotation). The DT values during the time show the Earth’s rotation variations. Solar activities and the gravitational force of major solar system components are known as astronomical-based factors that can provide these variations. Recently, several models have been proposed to interpolate and forecast the DT values. Structurally, all mentioned methods have just used past DT values for modeling. In this paper, we propose a novel approach for modeling DT based on the brain’s emotional learning with respect to astronomical-origin-based factors effective on the Earth’s rotation as the emotional input signals. This model, which employs memory units in the amygdala and orbitofrontal parts, can be named Memory-Based Brain Emotional Learning (MBBEL). MBBEL was run using the data from 1900 to 2000 and 2000 to 2019 as training and testing stages, respectively. After the modeling process, the mean absolute error (MSE) and maximum absolute error (MaxAE) of the train and test stages were 0.011, 0.051, 0.10, and 0.295, respectively. Comparing the MBBEL results against those of eight prior models revealed that MBBEL results considerably improved compared to those of the previous models.