A new method for predicting precipitation δ¹⁸O distribution based on deep learning and spatio-temporal clustering

References

• A.-R. Shurbaji ARC. 1997. Study of evaporation and recharge in desert soil using environmental tracers, New Mexico, USA. Environmental Geology, 29: 147-151. DOI: 10.1007/s002540050112
   Google Scholar
• Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamaria J, Fadhel MA, Al-Amidie M, Farhan L. 2021. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data, 8: 53. DOI: 10.1186/s40537-021-00444-8.
   Google Scholar
• Araguás-Araguás L, Froehlich K, Rozanski K. 1998. Stable isotope composition of precipitation over southeast Asia. Journal of Geophysical Research: Atmospheres, 103: 28721-28742. DOI: 10.1029/98jd02582.
   Google Scholar
• Barnes CJ, Allison GB. 1983. The distribution of deuterium and 18O in dry soils. Journal of Hydrology, 60: 141-156. DOI: 10.1016/0022-1694(83)90018-5
   Google Scholar
• Barzegar R, Aalami MT, Adamowski J. 2020. Short-term water quality variable prediction using a hybrid CNN–LSTM deep learning model. Stochastic Environmental Research and Risk Assessment, 34: 415-433. DOI: 10.1007/s00477-020-01776-2.
   Google Scholar
• Belayneh A, Adamowski J, Khalil B, Ozga-Zielinski B. 2014. Long-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet neural network and wavelet support vector regression models. Journal of Hydrology, 508: 418-429. DOI: 10.1016/j.jhydrol.2013.10.052.
   Google Scholar
• Bowen GJ, Revenaugh J. 2003. Interpolating the isotopic composition of modern meteoric precipitation. Water Resources Research, 39. DOI: 10.1029/2003wr002086.
   Google Scholar
• Bowen GJ, Wilkinson B. 2002. Spatial distribution of δ18O in meteoric precipitation. Geology, 30. DOI: 10.1130/0091-7613(2002)030<0315:Sdooim>2.0.Co;2.
   Google Scholar
• Chun IY, Noh S, Love DJ, Talavage TM, Beckley S, Kisner SJ. 2016. Mean Squared Error (MSE)-Based Excitation Pattern Design for Parallel Transmit and Receive SENSE MRI Image Reconstruction. IEEE Transactions on Computational Imaging: 1-1. DOI: 10.1109/tci.2016.2610141.
   Google Scholar
• Cui J, Lang J, Chen T, Mao S, Cheng S, Wang Z, Cheng N. 2019. A framework for investigating the air quality variation characteristics based on the monitoring data: Case study for Beijing during 2013-2016. J Environ Sci (China), 81: 225-237. DOI: 10.1016/j.jes.2019.01.009.
   Google Scholar
• Erdélyi D, Kern Z, Nyitrai T, Hatvani IG. 2023. Predicting the spatial distribution of stable isotopes in precipitation using a machine learning approach: a comparative assessment of random forest variants. GEM - International Journal on Geomathematics, 14. DOI: 10.1007/s13137-023-00224-x.
   Google Scholar
• Gower JC. 1967. A Comparison of Some Methods of Cluster Analysis. Biometrics, 23. DOI: 10.2307/2528417.
   Google Scholar
• Hernández-Pérez E, Levresse G, Carrera-Hernández J, García-Martínez R. 2020. Short term evaporation estimation in a natural semiarid environment: New perspective of the Craig – Gordon isotopic model. Journal of Hydrology, 587. DOI: 10.1016/j.jhydrol.2020.124926.
   Google Scholar
• Hochreiter S. 2011. The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 06: 107-116. DOI: 10.1142/s0218488598000094.
   Google Scholar
• Kattenborn T, Leitloff J, Schiefer F, Hinz S. 2021. Review on Convolutional Neural Networks (CNN) in vegetation remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 173: 24-49. DOI: 10.1016/j.isprsjprs.2020.12.010.
   Google Scholar
• Klaus J, Chun KP, Stumpp C. 2015. Temporal trends in δ18O composition of precipitation in Germany: insights from time series modelling and trend analysis. Hydrol Process, 29: 2668-2680. DOI: 10.1002/hyp.10395.
   Google Scholar
• Kratzert F, Klotz D, Brenner C, Schulz K, Herrnegger M. 2018. Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrology and Earth System Sciences, 22: 6005-6022. DOI: 10.5194/hess-22-6005-2018.
   Google Scholar
• Latifoglu L. 2022. A novel combined model for prediction of daily precipitation data using instantaneous frequency feature and bidirectional long short time memory networks. Environ Sci Pollut Res Int, 29: 42899-42912. DOI: 10.1007/s11356-022-18874-z.
   Google Scholar
• LeCun Y, Bengio Y, Hinton G. 2015. Deep learning. Nature, 521: 436-444. DOI: 10.1038/nature14539.
   Google Scholar
• Lee J-E, Fung I, DePaolo DJ, Henning CC. 2007. Analysis of the global distribution of water isotopes using the NCAR atmospheric general circulation model. Journal of Geophysical Research, 112. DOI: 10.1029/2006jd007657.
   Google Scholar
• Li J, Li F, Liu Q, Suzuki Y. 2014. Nitrate pollution and its transfer in surface water and groundwater in irrigated areas: a case study of the Piedmont of South Taihang Mountains, China. Environ Sci Process Impacts, 16: 2764-2773. DOI: 10.1039/c4em00200h.
   Google Scholar
• Liu H, Tian H-q, Pan D-f, Li Y-f. 2013. Forecasting models for wind speed using wavelet, wavelet packet, time series and Artificial Neural Networks. Applied Energy, 107: 191-208. DOI: 10.1016/j.apenergy.2013.02.002.
   Google Scholar
• Liu L, Hu Z, Zhou C, Xu G. 2018. Research on the clustering algorithm of the bicycle stations based on OPTICS. Concurrency and Computation: Practice and Experience, 31. DOI: 10.1002/cpe.4876.
   Google Scholar
• Liu X, Rao Z, Zhang X, Huang W, Chen J, Chen F. 2015. Variations in the oxygen isotopic composition of precipitation in the Tianshan Mountains region and their significance for the Westerly circulation. Journal of Geographical Sciences, 25: 801-816. DOI: 10.1007/s11442-015-1203-x.
   Google Scholar
• Liu Z, Bowen GJ, Welker JM. 2010. Atmospheric circulation is reflected in precipitation isotope gradients over the conterminous United States. Journal of Geophysical Research, 115. DOI: 10.1029/2010jd014175.
   Google Scholar
• Mohammadi B, Mehdizadeh S. 2020. Modeling daily reference evapotranspiration via a novel approach based on support vector regression coupled with whale optimization algorithm. Agricultural Water Management, 237. DOI: 10.1016/j.agwat.2020.106145.
   Google Scholar
• Nelson DB, Basler D, Kahmen A. 2021. Precipitation isotope time series predictions from machine learning applied in Europe. Proc Natl Acad Sci U S A, 118. DOI: 10.1073/pnas.2024107118.
   Google Scholar
• Panahi M, Sadhasivam N, Pourghasemi HR, Rezaie F, Lee S. 2020. Spatial prediction of groundwater potential mapping based on convolutional neural network (CNN) and support vector regression (SVR). Journal of Hydrology, 588. DOI: 10.1016/j.jhydrol.2020.125033.
   Google Scholar
• Shahid F, Zameer A, Muneeb M. 2020. Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM. Chaos Solitons Fractals, 140: 110212. DOI: 10.1016/j.chaos.2020.110212.
   Google Scholar
• Shengjie W, Shijun L, Mingjun Z, Catherine H, Jagoda C, Zhongfang L, Deye Q. 2022. Spatial and Seasonal Isotope Variability in Precipitation across China: Monthly Isoscapes Based on Regionalized Fuzzy Clustering. Journal of Climate, 35: 3411–3425. DOI: 10.1175/JCLI-D-21-0451.s1.
   Google Scholar
• Shi Y, Wang S, Zhang M, Argiriou AA, Guo R, Song Y, Zhu X. 2020. Isoscape of δ18O in Precipitation of the Qinghai-Tibet Plateau: Assessment and Improvement. Water, 12. DOI: 10.3390/w12123392.
   Google Scholar
• Stumpp C, Klaus J, Stichler W. 2014. Analysis of long-term stable isotopic composition in German precipitation. Journal of Hydrology, 517: 351-361. DOI: 10.1016/j.jhydrol.2014.05.034.
   Google Scholar
• Takashi Onoda MS, Seiji Yamada. 2010. Careful Seeding Based on Independent Component Analysis for k-Means Clustering. In: 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.
   Google Scholar
• Terzer S, Wassenaar LI, Araguás-Araguás LJ, Aggarwal PK. 2013. Global isoscapes for δ&lt;sup&gt;18&lt;/sup&gt;O and δ&lt;sup&gt;2&lt;/sup&gt;H in precipitation: improved prediction using regionalized climatic regression models. Hydrology and Earth System Sciences, 17: 4713-4728. DOI: 10.5194/hess-17-4713-2013.
   Google Scholar
• Tian L, Yao T, Sun W, Stievenard M, Jouzel J. 2001. Relationship between δD and δ18O in precipitation on north and south of the Tibetan Plateau and moisture recycling. Science in China Series D: Earth Sciences, 44: 789-796. DOI: 10.1007/bf02907091.
   Google Scholar
• White P, Carty M. 2010. Reducing bias through process inventory dataset normalization. The International Journal of Life Cycle Assessment, 15: 994-1013. DOI: 10.1007/s11367-010-0215-0.
   Google Scholar
• Wu Y, Lin L, Wang J, Wu S. 2020. [Application of semantic segmentation based on convolutional neural network in medical images]. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 37: 533-540. DOI: 10.7507/1001-5515.201906067.
   Google Scholar
• Xiang Z, Yan J, Demir I. 2020. A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning. Water Resources Research, 56. DOI: 10.1029/2019wr025326.
   Google Scholar
• Xie Y, Jia X, Shekhar S, Bao H, Zhou X. 2021. Significant DBSCAN+: Statistically Robust Density-based Clustering. ACM Transactions on Intelligent Systems and Technology, 12: 1-26. DOI: 10.1145/3474842.
   Google Scholar
• Yan R, Liao J, Yang J, Sun W, Nong M, Li F. 2021. Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering. Expert Systems with Applications, 169. DOI: 10.1016/j.eswa.2020.114513.
   Google Scholar
• Yoshimura K, Kanamitsu M, Noone D, Oki T. 2008. Historical isotope simulation using Reanalysis atmospheric data. Journal of Geophysical Research: Atmospheres, 113. DOI: 10.1029/2008jd010074.
   Google Scholar
• Zhang P, Li X, Chen J. 2022. Prediction Method for Mine Earthquake in Time Sequence Based on Clustering Analysis. Applied Sciences, 12. DOI: 10.3390/app122111101.
   Google Scholar
• Zhu Q, Burzykowski T. 2013. A Markov-chain-based regression model with random effects for the analysis of18O-labelled mass spectra. Journal of Statistical Computation and Simulation, 83: 145-157. DOI: 10.1080/00949655.2011.620610.
   Google Scholar