استفاده از مدل سازی مبتنی بر شبکه های عصبی عمیق با هدف پیش بینی تغییرات جمعیتی در ایران

Author

گروه جمعیت شناسی، دانشکده علوم اجتماعی، دانشگاه تهران، تهران، ایران

10.22059/jisr.2025.395285.1622

Abstract

کشور ایران در دهه‌های اخیر تحولات جمعیتی منحصر به فردی را تجربه کرده است. هدف اصلی مقاله حاضر، پیش‌بینی میزان افزایش رشد طبیعی جمعیت در ایران طی ده سال آینده (1404-1413) است تا چشم­اندازی جامع از آینده جمعیتی کشور ایران ارائه دهد. برای دستیابی به این هدف، به پیش‌بینی شاخص‌های کلیدی تغییرات جمعیتی شامل میزان خام ولادت، میزان خام مرگ و میر و زمان دو برابر شدن جمعیت پرداخته شده است.
در مقاله حاضر، از روش هوشمند مدل‌سازی شبکه‌های عصبی عمیق استفاده شده است. شبکه‌های عصبی عمیق از جمله مهم‌ترین و تأثیرگذارترین فناوری‌ها در حوزه یادگیری ماشین و هوش مصنوعی هستند. شبیه‌سازی‌ها با استفاده از نرم‌افزار متلب و بر مبنای داده‌های مرکز آمار ایران انجام گردیده است.
نتایج شبیه­سازی نشان می‌دهند که میزان خام ولادت با روند کاهشی از  3/11در سال 1403 به  3/9 در سال 1413 خواهد رسید و در مقابل، میزان خام مرگ‌ومیر با روند افزایشی از  2/5  در سال ۱۴۰3 به 1/6  در سال ۱۴۱3 خواهد رسید. در نتیجه، میزان رشد طبیعی جمعیت با روند کاهشی از 1/6 در هزار در سال ۱۴۰3 به 2/3 در هزار در سال ۱۴۱3 می‌رسد. در نهایت، مدت زمان لازم برای دوبرابر شدن جمعیت با روند افزایشی از   114سال در سال ۱۴۰3 به 218 سال در سال ۱۴۱3 خواهد رسید.
مطالعه حاضر یک مدل شبکه عصبی عمیق  مبتنی بر ساختار برنامه­نویسی  به منظور تببین  و پیش­بینی سیستم پیچیده تغییرات جمعیتی در ایران ارائه نمود.  ساخت این مدل به سیاست­گذاران و برنامه ­ریزان کمک می­کند تا بتوانند با در نظر گرفتن پیش­بینی آینده تغییرات جمعیتی در ایران برنامه ­ها و سیاست­ های خود را با دقت بیشتری برنامه­ ریزی نمایند.

Keywords


Azarfar, A., Azar, A.و & Kalantary, S. Z. (2017). Simulation of Population Changes in Iran using Basic Agent-Based Model. Iranian Population Studies3(1), 7-38.
Abbasi-Shavazi, M. J., & Esmaeili, N. (2022). Introduction of Agent-Based Modeling in Explaining Low Fertility. Iranian Population Studies7(1), 257-292. https://doi.org/10.22034/jips.2021.263638.1091
Abbasi-Shavazi, M. J., & Esmaeili, N. (2020). The evolutionary path of demography from the beginning to the emergence of agent-based modeling. Journal of Population Association of Iran, 15(30), 7-40. https://doi.org/10.22034/jpai.2021.521779.1173
Abbasi-Shavazi, M. J., & Esmaeili, N. (2022). Simulation of Women’s Fertility Behavior in Tehran Province Using Agent-Based Modeling Approach. Journal of Population Association of Iran17(33), 77-111. https://doi.org/10.22034/jpai.2023.559267.1241
Amani, M. (2015), Fundamentals of Demography, Samt Publications.
Bloom, N., Liang, J., Roberts, J., & Ying, Z.J. (2013), Dose Working from Home Work? Evidence from a Chinese Experiment, Working Paper, Available at: http://www.nber.org/papers/w18871
Burch, T. K. (2003). Demography in a new key: A theory of population theory, Demographic Research, 9(11): 264-282. https://doi.org/10.4054/DemRes.2003.9.11
Burch, T. K. (2018). Model-Based Demography, Essays on Integrating Data, Technique and Theory, Springer.
Çimen, M., & Kisi, O. (2009). Comparison of two different data-driven techniques in modeling lake level fluctuations in Turkey. Journal of Hydrology, 378 (3-4): 253–262; https://doi.org/10.1016/j.jhydrol.2009.09.029
Danesh, R., & Yekdast, R. (2022). Reducing the growth rate of Iran's population and its effects on the country's power and national security. Defense-Human Capital Management2(3), 1-27.
Esmaeili, M. M. (2025). Population Dynamics in Iran Post-Islamic Revolution an Examination of Policies, Opportunities, Challenges, and Effective Strategies. Social Studies and Research in Iran14(1), 89-112. https://doi.org/10.22059/jisr.2025.391957.1599
Esmaeili, N., & Abbasi-Shavazi, M.J.   (2024). Forecasting number of births and sex ratio at birth in Iran using deep neural network and ARIMA: implications for policy evaluations. Journal of Population Research, 41, 26. https://doi.org/10.1007/s12546-024-09348-9
Esmaeili, N., & Abbasi-Shavazi, M. J. (2024). Impact of family policies and economic situation on low fertility in Tehran, Iran: A multi-agent-based modelling. Demographic Research, 51, 107. https://doi.org/10.4054/DemRes.2024.51.5
Esmaeili, N. (2023). Predicting the trend of changes in the number of births and the sex ratio at birth in Iran: Time series analysis. Journal of Social Problems of Iran14(1), 233-258.  https://ijsp.ut.ac.ir/article_95165.html?lang=en
Esmaeili, N., Sasanipour, M., & Razeghi Nasrabad, H. B. (2025). Forecasting Changes in the Sexual Death Pattern in Iran Using Neural Network Modeling (2022-2031). Journal of Social Problems of Iran15(2), 77-94. https://ijsp.ut.ac.ir/article_102085.html?lang=en
Fathi, E. (2022). Fertility in Iran during 2017–2020, Statistical Centre of Iran. Available at: https://www.amar.org.ir/news/ArticleType/ArticleView/ArticleID/15805
Fathi, E., Javid, N. M., & Nasiripour, M. (2022). Fertility trends in Iran from 2017 to 2021, report prepared in Population, Labor Force and Census, Statistical Center of Iran. Avaliable at: https://www.amar.org.ir/news/ID/18601/
Friedman, J. (2020). Tackle Challenges of Online Classes Due to COVID-19. US News. https://www.scirp.org/reference/referencespapers?referenceid=3341486
Folorunso, O., Akinwale, A.T., Asiribo, O.E., & Adeyemo, T.A. (2010), Population prediction using artificial neural network, African Journal of Mathematics and Computer Science Research, 3 (8):155-162. Available online at http://www.academicjournals.org/AJMCSR.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
Grossman, L., Wilson, T., & Temple, J. (2023). Forecasting small area populations with long short-term memory networks, Socio-Economic Planning Sciences, 88.1-13. https://www.doi.org/10.1016/j.seps.2023.101658
Kazemi-Pour, S. (2010), Development and demographic situation in Iran, with a prospective approach, Second Impression Quarterly, 11 and 12, 1-34.
Kreager, P. (2019), Demographic Change and Long-Run Development, Population Studies, 73(2), 290-291, https://doi.org/10.1080/00324728.2019.1568700
Martinez-Ramon, N., Romay, M.,   Iribarren, D., & Dufour, J. (2024). Life-cycle assessment of hydrogen produced through chemical looping dry reforming of biogas, International Journal of Hydrogen Energy, 78 (12); 373-381.
Mino, K., & Sasaki, H. (2023). Population Aging and Income Inequality in a Semi-Endogenous Growth Model, KIER Working Papers 1096, Kyoto University, Institute of Economic Research. Available: https://repository.kulib.kyoto-u.ac.jp/server/api/core/bitstreams/42d28e82-647f-4131-b110-b6c6d370a0b7/content
Moheby- Meymandi, M., Koosheshi, M. & Souri, A. (2023). Population Growth, Changing Age Structure and its Economic Consequences in Iran: Decomposition and Analysis of the Share of Age Groups. Journal of Population Association of Iran17(34), 309-346. https://doi.org/10.22034/jpai.2023.563001.1253
Mansourm, W., Ramadan, A., & Abdulrazag, M. (2025). Predicting population growth in Libya using deep learning techniques (LSTM), World Journal of Advanced Research and Reviews, 25 (2);291-295. https://doi.org/10.30574/wjarr.2025.25.2.0293
Mustapha, I., Sabo, U. M. & Jungudo, M. (2024). Forecasting Nigeria's Population Growth Using Deep Learning Technique, Open Journal of Physical Science, 5(1):45-57. https://doi.org/10.52417/ojps.v5i1.783
Modis, T. (2002). Predictions: 10 years later. CreateSpace Independent Publishing Platform.
Mahmoudian, H., & Esmaeili, N. (2023). Predicting the labor force participation rate in Iran using neural network based Simulations. Journal of Economic & Developmental Sociology12(1), 1-24. https://doi.org/10.22034/jeds.2023.51837.1658
Nigri, A., Levantesi, S., & Aburto, J. M. (2022). Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth. Demographic Research, 47(8), 199–232. https://doi.org/10.4054/DemRes.2022.47.8
National Organization for Civil Registration. (2025). Number of births and deaths in 2024, available at; https://commons.wikimedia.org/wiki/File:National_Organization_for_Civil_Registration-3.jpg
National Organization for Civil Registration, Population Statistics and Information Office (2010). A study of the birth and death registration trends from 2004 to 2009 with emphasis on timely registration of vital events, Population Journal; 71-72: 131-144.
National Organization for Civil Registration. (2021). Yearbook of population statistics 2006-2021. Tehran: Organization Publications Registration of Iran.
Nwozor, B. U., & Onoseraye, A. H. (2025). An Optimized Machine Learning Model for Population Growth Prediction Using Artificial Neural Network and Genetic (Neuro-Genetic) Algorithm, Fuore Journal, 9(1):364-379. http://fupre.edu.ng/journal
Pressat, R. (1992). Demographie Statistique, translated by Mohammad Seyed Mirzaei, Astan Quds Razavi Publications.
Rafaftery, A.E., & Sevcikova, H. (2023). Probabilistic population forecasting: Short to very long-term, International Journal of Forecasting, 39 (1), 73-97. https://doi.org/10.1016/j.ijforecast.2021.09.001
Razeghi -Nasrabad, H. B., Askari-Nodoushan, A., & Tanhaa, F. (2025). Structural Solutions to Remove Barriers to Childbearing; Analysis of the Perspectives of Employed Women in the Social Security Organization. Social Studies and Research in Iran, 14(3), 451-470. https://doi.org/10.22059/jisr.2025.394507.1617
Sarai, H. (2011). Demography, Foundations and Backgrounds. Tehran: SAMT.
Singh, K., Sajjad, M., & Won Ahn, C.  (2015). Simulating Population Dynamics with an Agent Based and Microsimulation Based Framework, International Conference on Applied Social Science Research: 335-339. https://doi.org/10.2991/icassr-15.2016.90
Sadeghi, R., & Hosseini- Milani, H. S. (2025). Unequal Development and Inter-City Migration in Iran. The Journal of Community Development (Rural-Urban), 17(1), 183-202. https://doi.org/10.22059/jrd.2025.376068.668858
Statistical Center of Iran (2025), time series data on the number of births and deaths in the whole country from 1965 to 2025, available at: https://amar.org.ir/statistical-information/catid/3503
Sadeghi, R., Esmaeili, N., & Abbasi-Shavazi, M. J. (2021). Education, Development and Internal Migration in Iran. Journal of Population Association of Iran16(31), 193-215. https://doi.org/10.22034/jpai.2021.128570.1152
Torabi, F., & Esmaeili, N. (2021). Application of neural-wavelet network in predicting the incidence of marriage and divorce in Iran. China Population and Development Studies, 4(5), 439–457. https://doi.org/10.1007/s42379-020-00072-4
Torkashvand - Moradabadi, M., & Irannejad, K. (2024). Demographic Dynamics and Population Projections in Iran: Analyzing Population Size and Age Structure up to 2040 Horizon. Journal of Social Continuity and Change, 3(1), 7-33. https://doi.org/10.22034/jscc.2024.21185.1103
Zanjani, H. (1993). A study of mortality in Iran from civil registration data, Population Quarterly, 3-4: 69-78.