Summary of Academic Journal

Summary:

The paper introduces Isocompy, a Python library designed for isotopic composition modeling in environmental studies. Isocompy utilizes machine learning algorithms and allows users to define variables to estimate isotopic compositions. The library provides a range of functionalities, including dataset preprocessing, outlier detection, statistical analysis, feature selection, model validation, calibration, and postprocessing. Isocompy is capable of handling non-continuous inputs in time and space. It incorporates automated decision-making procedures throughout the algorithm, while still allowing manual intervention at each step. The generated output reports, figures, and maps aid in understanding stable water isotope studies. The paper demonstrates the functionality of Isocompy using an application example involving meteorological features and isotopic composition of precipitation in Northern Chile, with comparisons to previous studies. Ultimately, Isocompy serves as an open-source foundation for reproducible research in isotopic studies within environmental domains.