Deep learning insights into spatial patterns of stable isotopes in Iran's precipitation: a novel approach to climatological mapping.

Abstract

Stable isotope techniques are precise methods for studying various aspects of hydrology, such as precipitation characteristics. However, understanding the variations in the stable isotope content in precipitation is challenging in Iran due to numerous climatic and geographic factors. To address this, forty-two precipitation sampling stations were selected across Iran to assess the fractional importance of these climatic and geographic parameters influencing stable isotopes. Additionally, deep learning models were employed to simulate the stable isotope content, with missing data initially addressed using the predictive mean matching (PMM) method. Subsequently, the recursive feature elimination (RFE) technique was applied to identify influential parameters impacting Iran's precipitation stable isotope content. Following this, long short-term memory (LSTM) and deep neural network (DNN) models were utilized to predict stable isotope values in precipitation. Interpolated maps of these values across Iran were developed using inverse distance weighting (IDW), while an interpolated reconstruction error (RE) map was generated to quantify deviations between observed and predicted values at study stations, offering insights into model precision. Validation using evaluation metrics demonstrated that the model based on DNN exhibited higher accuracy. Furthermore, RE maps confirmed acceptable accuracy in simulating the stable isotope content, albeit with minor weaknesses observed in simulation maps. The methodology outlined in this study holds promise for application in regions worldwide characterized by diverse climatic conditions.