Stable Isotope Signatures in Tehran's Precipitation - Insights from Artiﬁcial Neural Networks, Stepwise Regression, Wavelet Coherence, and Ensemble Machine Learning Approaches

Aug 5, 2026

Upload by Finn

This study investigates how precipitation influences Middle Eastern conditions, focusing on Tehran through stable isotope techniques and multiple statistical and machine learning models. Precipitation isotope data from the GNIP Tehran station were analyzed for two intervals (1961–1987 and 2000–2004) using standardized sampling and laboratory procedures. Artificial neural networks, stepwise regression, and ensemble machine learning were applied, with XGBoost achieving the best performance for both 18O and 2H. Wavelet coherence further revealed dominant links mainly between isotopes and temperature over 16–32 months, clarifying that temperature is the primary control while precipitation plays a smaller role.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Introduction

Study context: water shortage and precipitation assessment in Tehran

Stable isotope techniques and GNIP data sources

Methods and Modeling Approaches

Data collection and isotope measurements (18O, 2H, 3H)

Simulation models: ANN, stepwise regression, ensemble learning (XGBoost)

Uncertainty evaluation with bootstrap

Wavelet coherence analysis

Results and Interpretation

Model performance comparison (accuracy and error metrics)

Coherence timing and controlling factors (temperature vs precipitation)

Conclusions

water Article Stable Isotope Signatures in Tehran's Precipitation: Insights from Artiﬁcial Neural Networks, Stepwise Regression, Wavelet Coherence, and Ensemble Machine Learning Approaches Mojtaba Heydarizad 1, Luis Gimeno 2,*, Masoud Minaei 3,4 and Marjan Shahsavan Gharehghouni 3 Citation: Heydarizad, M.; Gimeno, L.; Minaei, M.; Gharehghouni, M.S. Stable Isotope Signatures in Tehran's Precipitation: Insights from Artiﬁcial Neural Networks, Stepwise Regression, Wavelet Coherence, and Ensemble Machine Learning Approaches. Water 2023, 15, 2357 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)w15132357 Academic Editors: Paula M. Carreira and Jos² Manuel Marques Received: 7 May 2023 Revised: 18 June 2023 Accepted: 23 June 2023 Published: 26 June 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 State Key Laboratory of Marine Geology, Tongji University, Shanghai 200092, China; [mojtabaheydarizad@yahoo.com](mojtabaheydarizad@yahoo.com) 2 Centro de Investigaciân Mariña, Environmental Physics Laboratory (EPhysLab), Campus As Lagoas s/n, Universidade de Vigo, 32004 Ourense, Spain 3 Department of Geography, Ferdowsi University of Mashhad, Mashhad 9177794883, Iran; [m.minaei@um.ac.ir](m.minaei@um.ac.ir) (M.M.); [m.shahsavand98@gmail.com](m.shahsavand98@gmail.com) (M.S.G.) 4 Geographic Information Science/System and Remote Sensing Laboratory (GISSRS: Lab), Ferdowsi University of Mashhad, Mashhad 9177794883, Iran * Correspondence: [l.gimeno@uvigo.es](l.gimeno@uvigo.es) Abstract: This study investigates the impact of precipitation on Middle Eastern countries like Iran using precise methods such as stable isotope techniques. Stable isotope data for precipitation in Tehran were obtained from the Global Network of Isotopes in Precipitation (GNIP) station and sampled for two periods: 1961–1987 and 2000–2004 . Precipitation samples were collected, stored, and shipped to a laboratory for stable isotope analyses using the GNIP procedure. Several models, including artiﬁcial neural networks (ANNs), stepwise regression, and ensemble machine learning approaches, were applied to simulate stable isotope signatures in precipitation. Among the studied machine learning models, XGboost showed the most accurate simulation with higher R2 (0 .84 and 0.86) and lower RMSE (1.97 and 12.54), NSE (0.83 and 0.85), AIC (517.44 and 965.57), and BIC values (531 .42 and 979 .55) for 18O and 2H compared to other models, respectively. The uncertainty in the simulations of the XGboost model was assessed using the bootstrap technique, indicating that this model accurately predicted stable isotope values. Various wavelet coherence analyses were applied to study the associations between stable isotope signatures and their controlling parameters. The BWC analysis results show coherence relationships, mainly ranging from 16 to 32 months for both 􀀎 18O–temperature and 􀀎2H–temperature pairs with the highest average wavelet coherence (AWC) . Temperature is the dominant predictor inﬂuencing stable isotope signatures of precipitation, while precipitation has lower impacts. This study provides valuable insights into the relationship between stable isotopes and climatological parameters of precipitation in Tehran. Keywords: artiﬁcial neural networks; precipitation; local parameters; regional parameters; stable isotopes; stepwise model; ensemble machine learning algorithm; wavelet coherence analysis; Tehran 1. Introduction Tehran, the capital of Iran, is the most populated and largest metropolitan area in the country. Over the last few decades, the water shortage crisis has signiﬁcantly affected the liv

FAQs

What data source and time periods were used to study Tehran precipitation isotopes?

Stable isotope data were taken from the GNIP “Tehran” station and analyzed for two periods: 1961–1987 and 2000–2004.

Which modeling approach produced the most accurate simulation of isotope signatures?

XGBoost performed best, showing the highest R² values and lower RMSE, with strong results for both 18O and 2H compared with other models.

What does wavelet coherence indicate about the main controls on isotope signatures?

Wavelet coherence shows significant coherence relationships for isotope–temperature pairs, mainly in the 16–32 month band, indicating temperature is the dominant predictor while precipitation has smaller impacts.

Aug 5, 2026

Upload by Finn