<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">koz</journal-id><journal-title-group><journal-title xml:lang="ru">"Вестник Северо-Казахстанского университета имени Манаша Козыбаева"</journal-title><trans-title-group xml:lang="en"><trans-title>Bulletin of Manash Kozybayev North Kazakhstan University</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2958-003X</issn><issn pub-type="epub">2958-0048</issn><publisher><publisher-name>М. Қозыбаев атындағы СҚУ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.54596/2958-0048-2026-3-319-339</article-id><article-id custom-type="elpub" pub-id-type="custom">koz-2806</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ИНФОРМАЦИОННО-КОММУНИКАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>INFORMATION AND COMMUNICATION TECHNOLOGIES</subject></subj-group></article-categories><title-group><article-title>ГИБРИДНЫЙ ПОДХОД МАШИННОГО ОБУЧЕНИЯ ДЛЯ ПРОГНОЗИРОВАНИЯ АМПЛИТУД СЕЙСМИЧЕСКИХ СИГНАЛОВ НА МИНУТНОМ УРОВНЕ В РЕЖИМЕ РЕАЛЬНОГО ВРЕМЕНИ</article-title><trans-title-group xml:lang="en"><trans-title>A HYBRID MACHINE LEARNING APPROACH FOR REAL-TIME FORECASTING OF MINUTE-LEVEL SEISMIC SIGNAL AMPLITUDES</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0006-2690-072X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сапы</surname><given-names>Б.</given-names></name><name name-style="western" xml:lang="en"><surname>Sapy</surname><given-names>B.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Шымкент</p></bio><bio xml:lang="en"><p>master student, Department of Information systems and modeling</p><p>Shymkent</p></bio><email xlink:type="simple">bakytzhansapy02@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-0257-4417</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Умарова</surname><given-names>Ж. Р.</given-names></name><name name-style="western" xml:lang="en"><surname>Umarova</surname><given-names>Zh. R.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Шымкент</p></bio><bio xml:lang="en"><p>corresponding author, PhD, Professor, Department of Information systems and modeling</p><p>Shymkent</p></bio><email xlink:type="simple">zhanat-u@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-6239-4346</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Кемельбекова</surname><given-names>Ж. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Kemelbekova</surname><given-names>Zh. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Шымкент</p></bio><bio xml:lang="en"><p>candidate of technical science, Professor, Department of Computer science</p><p>Shymkent</p></bio><email xlink:type="simple">Kemel_zhan@mail.ru</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-7718-5857</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Калбаева</surname><given-names>А. Т.</given-names></name><name name-style="western" xml:lang="en"><surname>Kalbayeva</surname><given-names>A. T.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Шымкент</p></bio><bio xml:lang="en"><p>candidate of technical science, Associate Professor, Department of Information systems and modeling</p><p>Shymkent</p></bio><email xlink:type="simple">kalbaeva@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-7767-5001</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Jusoh</surname><given-names>Yu.</given-names></name><name name-style="western" xml:lang="en"><surname>Jusoh</surname><given-names>Yu.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Куала-Лумпур</p></bio><bio xml:lang="en"><p>PhD, Associate Professor, Faculty of Computer Science and Information Technology</p><p>Kuala Lumpur</p></bio><email xlink:type="simple">yusmadi@upm.edu.my</email><xref ref-type="aff" rid="aff-3"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Кафедра Информационных систем и моделирования, Южно-Казахстанский университет имени М. Ауэзова</institution><country>Казахстан</country></aff><aff xml:lang="en"><institution>Department of Information Systems and Modeling, M. Auezov South Kazakhstan University</institution><country>Kazakhstan</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Кафедра Информатики, Южно-Казахстанский университет имени М. Ауэзова</institution><country>Казахстан</country></aff><aff xml:lang="en"><institution>Department of Computer Science, M. Auezov South Kazakhstan University</institution><country>Kazakhstan</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>Факультет компьютерных наук и информационных технологий, Университет Путра Малайзия</institution><country>Малайзия</country></aff><aff xml:lang="en"><institution>Faculty of Computer Science and Information Technology, University Putra Malaysia</institution><country>Malaysia</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>30</day><month>09</month><year>2026</year></pub-date><volume>0</volume><issue>3 (71)</issue><fpage>319</fpage><lpage>339</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Сапы Б., Умарова Ж.Р., Кемельбекова Ж.С., Калбаева А.Т., Jusoh Y., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Сапы Б., Умарова Ж.Р., Кемельбекова Ж.С., Калбаева А.Т., Jusoh Y.</copyright-holder><copyright-holder xml:lang="en">Sapy B., Umarova Z.R., Kemelbekova Z.S., Kalbayeva A.T., Jusoh Y.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://vestnik.ku.edu.kz/jour/article/view/2806">https://vestnik.ku.edu.kz/jour/article/view/2806</self-uri><abstract><p>Интерпретация сейсмических волновых данных в режиме реального времени имеет важное значение для мониторинга динамики сигналов и выявления аномальной активности. Однако прогнозирование сейсмических амплитуд остаётся сложной задачей, поскольку сейсмические сигналы характеризуются высокой изменчивостью, шумом и нестационарностью. В данном исследовании представлен автоматизированный, устойчивый к пропускам конвейер прогнозирования амплитуд сейсмических сигналов на минутном уровне в реальном времени на основе волновых данных IRIS FDSN, а также строгое, статистически обоснованное сравнение семи моделей прогнозирования: наивной модели (persistence), ARIMA, Ridge-регрессии, HistGradientBoosting, стандартной GRU, LSTM и регуляризованной GRU, основанной на физических принципах (PI-GRU), которая добавляет в функцию потерь ограничения временной гладкости и штраф за нереалистичный рост амплитуды. Модели были оценены на 81 независимом, неперекрывающемся окне прогнозирования, отобранном из непрерывного 91-дневного периода наблюдений, для четырёх горизонтов (5, 15, 30 и 60 минут); оценка включала парные непараметрические тесты статистической значимости, количественное абляционное исследование и тестирование устойчивости к шуму и пропускам данных, а основные результаты были дополнительно проверены при альтернативной peak-priority агрегации сигнала. Классические модели, в особенности Ridge-регрессия и HistGradientBoosting, показали статистически значимо более низкую ошибку прогнозирования по сравнению со всеми нейросетевыми моделями (тесты Фридмана и Уилкоксона с поправкой Холма, p&lt;0.0001) и продемонстрировали устойчивость к синтетическому шуму и пропускам данных, тогда как предложенная модель PI-GRU, вопреки ожиданиям, показала наихудший результат среди всех моделей и не позволила получить более сглаженные траектории прогноза по сравнению с нерегуляризованной базовой GRU. Мы сообщаем об этом как о честном отрицательном результате, не скрывая его: в текущей конфигурации рассмотренная в этой работе физически обоснованная регуляризация не демонстрирует преимущества в точности или устойчивости по сравнению с классическими методами машинного обучения. Основным вкладом данной работы являются сам автоматизированный конвейер прогнозирования в реальном времени и воспроизводимая, строгая методология оценки, а также конкретные, проверяемые гипотезы относительно того, почему нейросетевые модели показали худший результат и как это можно улучшить в дальнейшей работе.</p></abstract><trans-abstract xml:lang="en"><p>Real-time interpretation of seismic waveform data is essential for monitoring signal dynamics and detecting abnormal activity. However, forecasting seismic amplitudes remains challenging because seismic signals are highly variable, noisy, and non-stationary. This study presents an automated, gap-aware real-time forecasting pipeline for minute-level seismic signal amplitudes built on IRIS FDSN waveform data, together with a rigorous, statistically grounded comparison of seven forecasting models: Naive persistence, ARIMA, Ridge regression, HistGradientBoosting, a standard Gated Recurrent Unit (GRU), an LSTM, and a physics-inspired regularized GRU (PI-GRU) that adds temporal smoothness and amplitude-growth constraints to the training loss. Models were evaluated on 81 independently sampled, non-overlapping forecasting windows drawn from a continuous 91-day observation period across four horizons (5, 15, 30, and 60 minutes), using paired non-parametric significance testing, a quantitative ablation study, and noise- and missing-data robustness testing, and the main findings were additionally verified under an alternative peak-priority signal aggregation. Classical models, particularly Ridge regression and HistGradientBoosting, achieved significantly lower forecasting error than every neural model tested (Friedman and Holm-corrected Wilcoxon tests, p&lt;0.0001) and were robust to synthetic noise and missing data, while the proposed PI-GRU was, contrary to expectation, the weakest-performing model overall and did not produce smoother forecast trajectories than an unregularized baseline GRU. We report this as an honest negative result: as currently configured, the physics-inspired regularization examined here does not demonstrate an accuracy or stability advantage over classical machine learning baselines for this task. The principal contributions of this work are the automated real-time forecasting pipeline itself and a reusable, rigorous evaluation methodology, together with specific, testable hypotheses - concerning hyperparameter tuning, training budget, and calibration of the physics-inspired constraint - for why the neural models underperformed and how this might be addressed in future work.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>прогнозирование сейсмических сигналов</kwd><kwd>нейронные сети</kwd><kwd>основанные на физических принципах</kwd><kwd>прогнозирование временных рядов</kwd><kwd>гибридные модели прогнозирования</kwd><kwd>машинное обучение</kwd><kwd>мониторинг в реальном времени</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Seismic signal forecasting</kwd><kwd>physics-inspired neural networks</kwd><kwd>time series prediction</kwd><kwd>hybrid forecasting models</kwd><kwd>machine learning</kwd><kwd>real-time monitoring</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Mojtahedi, F., Yousefpour, N., Chow, S. H., &amp; Cassidy, M. (2025). Deep learning for time series forecasting: Review and applications in geotechnics and geosciences. Archives of Computational Methods in Engineering. Advance online publication. https://doi.org/10.1007/s11831-025-10244-5</mixed-citation><mixed-citation xml:lang="en">Mojtahedi, F., Yousefpour, N., Chow, S. H., &amp; Cassidy, M. (2025). Deep learning for time series forecasting: Review and applications in geotechnics and geosciences. Archives of Computational Methods in Engineering. Advance online publication. https://doi.org/10.1007/s11831-025-10244-5</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Wang, L., Jia, B., &amp; Su, G. (2025). Prediction of coal and gas outbursts based on physics-informed neural networks and traditional machine learning models. Scientific Reports, 15, Article 29984. https://doi.org/10.1038/s41598-025-02320-4</mixed-citation><mixed-citation xml:lang="en">Wang, L., Jia, B., &amp; Su, G. (2025). Prediction of coal and gas outbursts based on physics-informed neural networks and traditional machine learning models. Scientific Reports, 15, Article 29984. https://doi.org/10.1038/s41598-025-02320-4</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Jafari, A., Fox, G., Rundle, J. B., Donnellan, A., &amp; Ludwig, L. G. (2024). Time series foundation models and deep learning architectures for earthquake temporal and spatial nowcasting. GeoHazards, 5(4), 1247–1274. https://doi.org/10.3390/geohazards5040059</mixed-citation><mixed-citation xml:lang="en">Jafari, A., Fox, G., Rundle, J. B., Donnellan, A., &amp; Ludwig, L. G. (2024). Time series foundation models and deep learning architectures for earthquake temporal and spatial nowcasting. GeoHazards, 5(4), 1247–1274. https://doi.org/10.3390/geohazards5040059</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Li, Z., Eaton, D. W., &amp; Davidsen, J. (2023). Physics-informed deep learning for forecasting seismic activity. Scientific Reports, 13, Article 13133. https://doi.org/10.1038/s41598-023-40403-2</mixed-citation><mixed-citation xml:lang="en">Li, Z., Eaton, D. W., &amp; Davidsen, J. (2023). Physics-informed deep learning for forecasting seismic activity. Scientific Reports, 13, Article 13133. https://doi.org/10.1038/s41598-023-40403-2</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Bischof, R., &amp; Kraus, M. A. (2025). Multi-objective loss balancing for physics-informed deep learning. Computer Methods in Applied Mechanics and Engineering. Advance online publication. https://doi.org/10.1016/j.cma.2025.117914</mixed-citation><mixed-citation xml:lang="en">Bischof, R., &amp; Kraus, M. A. (2025). Multi-objective loss balancing for physics-informed deep learning. Computer Methods in Applied Mechanics and Engineering. Advance online publication. https://doi.org/10.1016/j.cma.2025.117914</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Hu, H., Qi, L., &amp; Chao, X. (2024). Physics-informed neural networks for computational solid mechanics: Applications and frameworks. Thin-Walled Structures. Advance online publication. https://doi.org/10.1016/j.tws.2024.112495</mixed-citation><mixed-citation xml:lang="en">Hu, H., Qi, L., &amp; Chao, X. (2024). Physics-informed neural networks for computational solid mechanics: Applications and frameworks. Thin-Walled Structures. Advance online publication. https://doi.org/10.1016/j.tws.2024.112495</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Wang, S., Teng, Y., &amp; Perdikaris, P. (2020). Understanding and mitigating gradient pathologies in physics-informed neural networks. Journal of Computational Physics, 419, Article 109913. https://doi.org/10.48550/arXiv.2001.04536</mixed-citation><mixed-citation xml:lang="en">Wang, S., Teng, Y., &amp; Perdikaris, P. (2020). Understanding and mitigating gradient pathologies in physics-informed neural networks. Journal of Computational Physics, 419, Article 109913. https://doi.org/10.48550/arXiv.2001.04536</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Nasiri, M., Kortelainen, J., &amp; Särkkä, S. (2026). Dual-level models for physics-informed multi-step time series forecasting. arXiv. https://doi.org/10.48550/arXiv.2601.07640</mixed-citation><mixed-citation xml:lang="en">Nasiri, M., Kortelainen, J., &amp; Särkkä, S. (2026). Dual-level models for physics-informed multi-step time series forecasting. arXiv. https://doi.org/10.48550/arXiv.2601.07640</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Park, K. V., Kim, J., &amp; Seo, J. (2025). PINT: Physics-informed neural time series models with applications to long-term inference on WeatherBench 2m-temperature data. arXiv. https://doi.org/10.48550/arXiv.2502.04018</mixed-citation><mixed-citation xml:lang="en">Park, K. V., Kim, J., &amp; Seo, J. (2025). PINT: Physics-informed neural time series models with applications to long-term inference on WeatherBench 2m-temperature data. arXiv. https://doi.org/10.48550/arXiv.2502.04018</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Biswas, S., &amp; Yadav, K. K. (2025). A physics-informed U-Net-LSTM network for nonlinear structural response under seismic excitation. arXiv. https://doi.org/10.48550/arXiv.2511.21276</mixed-citation><mixed-citation xml:lang="en">Biswas, S., &amp; Yadav, K. K. (2025). A physics-informed U-Net-LSTM network for nonlinear structural response under seismic excitation. arXiv. https://doi.org/10.48550/arXiv.2511.21276</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Martinez, Y., Rojas, L., Peña, A., Valenzuela, M., &amp; Garcia, J. (2025). Physics-informed neural networks for the structural analysis and monitoring of railway bridges: A systematic review. Mathematics, 13(10), Article 1571. https://doi.org/10.3390/math13101571</mixed-citation><mixed-citation xml:lang="en">Martinez, Y., Rojas, L., Peña, A., Valenzuela, M., &amp; Garcia, J. (2025). Physics-informed neural networks for the structural analysis and monitoring of railway bridges: A systematic review. Mathematics, 13(10), Article 1571. https://doi.org/10.3390/math13101571</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Huang, Y., Han, X., &amp; Zhao, L. (2021). Recurrent neural networks for complicated seismic dynamic response prediction of a slope system. Engineering Geology, 289, Article 106198. https://doi.org/10.1016/j.enggeo.2021.106198</mixed-citation><mixed-citation xml:lang="en">Huang, Y., Han, X., &amp; Zhao, L. (2021). Recurrent neural networks for complicated seismic dynamic response prediction of a slope system. Engineering Geology, 289, Article 106198. https://doi.org/10.1016/j.enggeo.2021.106198</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Huang, Y.-M., Chen, K.-Y., Lin, W.-W., &amp; Chen, D.-Y. (2025). An attention-based framework with multistation information for earthquake early warnings. IEEE Transactions on Geoscience and Remote Sensing. Advance online publication. https://doi.org/10.48550/arXiv.2412.18099</mixed-citation><mixed-citation xml:lang="en">Huang, Y.-M., Chen, K.-Y., Lin, W.-W., &amp; Chen, D.-Y. (2025). An attention-based framework with multistation information for earthquake early warnings. IEEE Transactions on Geoscience and Remote Sensing. Advance online publication. https://doi.org/10.48550/arXiv.2412.18099</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Bilal, M. A., Ji, Y., Wang, Y., Akhter, M. P., &amp; Yaqub, M. (2022). An early warning system for earthquake prediction from seismic data using batch normalized graph convolutional neural network with attention mechanism (BNGCNNATT). Sensors, 22(17), Article 6482. https://doi.org/10.3390/s22176482</mixed-citation><mixed-citation xml:lang="en">Bilal, M. A., Ji, Y., Wang, Y., Akhter, M. P., &amp; Yaqub, M. (2022). An early warning system for earthquake prediction from seismic data using batch normalized graph convolutional neural network with attention mechanism (BNGCNNATT). Sensors, 22(17), Article 6482. https://doi.org/10.3390/s22176482</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Lyu, D., Nakata, R., Ren, P., Mahoney, M. W., Pitarka, A., Nakata, N., &amp; Erichson, N. B. (2025). Rapid wavefield forecasting for earthquake early warning via deep sequence to sequence learning. Nature Communications. Advance online publication. https://doi.org/10.1038/s41467-025-65435-2</mixed-citation><mixed-citation xml:lang="en">Lyu, D., Nakata, R., Ren, P., Mahoney, M. W., Pitarka, A., Nakata, N., &amp; Erichson, N. B. (2025). Rapid wavefield forecasting for earthquake early warning via deep sequence to sequence learning. Nature Communications. Advance online publication. https://doi.org/10.1038/s41467-025-65435-2</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., &amp; Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1724-1734). https://doi.org/10.3115/v1/D14-1179</mixed-citation><mixed-citation xml:lang="en">Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., &amp; Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1724-1734). https://doi.org/10.3115/v1/D14-1179</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Hochreiter, S., &amp; Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735</mixed-citation><mixed-citation xml:lang="en">Hochreiter, S., &amp; Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Hoerl, A. E., &amp; Kennard, R. W. (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1), 55-67. https://doi.org/10.1080/00401706.1970.10488634</mixed-citation><mixed-citation xml:lang="en">Hoerl, A. E., &amp; Kennard, R. W. (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1), 55-67. https://doi.org/10.1080/00401706.1970.10488634</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189-1232. https://doi.org/10.1214/aos/1013203451</mixed-citation><mixed-citation xml:lang="en">Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189-1232. https://doi.org/10.1214/aos/1013203451</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Box, G. E. P., Jenkins, G. M., Reinsel, G. C., &amp; Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). John Wiley &amp; Sons.</mixed-citation><mixed-citation xml:lang="en">Box, G. E. P., Jenkins, G. M., Reinsel, G. C., &amp; Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). John Wiley &amp; Sons.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
