<?xml version="1.0" encoding="UTF-8"?>
<article article-type="research-article" dtd-version="1.3" xml:lang="ru" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="https://metafora.rcsi.science/xsd_files/journal3.xsd">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">moitvivt</journal-id>
      <journal-title-group>
        <journal-title xml:lang="ru">Моделирование, оптимизация и информационные технологии</journal-title>
        <trans-title-group xml:lang="en">
          <trans-title>Modeling, Optimization and Information Technology</trans-title>
        </trans-title-group>
      </journal-title-group>
      <issn pub-type="epub">2310-6018</issn>
      <publisher>
        <publisher-name>Издательство</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="doi">10.26102/2310-6018/2026.56.5.002</article-id>
      <article-id pub-id-type="custom" custom-type="elpub">2249</article-id>
      <title-group>
        <article-title xml:lang="ru">Реконструкция c, φ и E50 по лабораторным данным: интерпретируемый ансамбль и сравнение моделей</article-title>
        <trans-title-group xml:lang="en">
          <trans-title>Reconstruction c, φ and E50 from laboratory data: interpretable ensemble and model comparison</trans-title>
        </trans-title-group>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0008-2484-591X</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Тишин</surname>
              <given-names>Никита Романович</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Tishin</surname>
              <given-names>Nikita Romanovich</given-names>
            </name>
          </name-alternatives>
          <email>tnick1502@mail.ru</email>
          <xref ref-type="aff">aff-1</xref>
        </contrib>
      </contrib-group>
      <aff-alternatives id="aff-1">
        <aff xml:lang="ru">АО МОСТДОРГЕОТРЕСТ Московский государственный технический университет им. Н.Э. Баумана</aff>
        <aff xml:lang="en">JSC MOSTDORGEOTREST Bauman Moscow State Technical University</aff>
      </aff-alternatives>
      <pub-date pub-type="epub">
        <day>01</day>
        <month>01</month>
        <year>2026</year>
      </pub-date>
      <volume>1</volume>
      <issue>1</issue>
      <elocation-id>10.26102/2310-6018/2026.56.5.002</elocation-id>
      <permissions>
        <copyright-statement>Copyright © Авторы, 2026</copyright-statement>
        <copyright-year>2026</copyright-year>
        <license license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/">
          <license-p>This work is licensed under a Creative Commons Attribution 4.0 International License</license-p>
        </license>
      </permissions>
      <self-uri xlink:href="https://moitvivt.ru/ru/journal/article?id=2249"/>
      <abstract xml:lang="ru">
        <p>Статья посвящена задаче восстановления прочностных и деформационных характеристик грунтов: удельного сцепления сцепления c, угла внутреннего трения трения φ и секущего модуля деформации деформации E50 по физическим и классификационным признакам, доступным в массовых лабораторных протоколах. Актуальность работы обусловлена тем, что в инженерно-геологической практике механические параметры определяются не для всех образцов, хотя именно они необходимы при расчетах оснований и параметризации геотехнических моделей. В работе использован архив лабораторных данных по грунтам, для которого выполнены контроль качества, фильтрация, формирование информативного признакового описания и независимая внешняя проверка. Для решения задачи проведено сравнение моделей машинного обучения для табличных данных, включая CatBoost, FT-Transformer и многозадачную нейросеть, а также рассмотрен интерпретируемый ансамбль моделей. Дополнительно выполнен анализ важности признаков, позволяющий оценить физическую согласованность получаемых прогнозов. Показано, что наилучшее качество достигается при использовании ансамбля с доминирующим вкладом CatBoost (FT-Transformer (0,10) ) + CatBoost (0,90)) с (WAPE) ̅= WAPE = 13,16 %, R2(R^2 ) ̅  = 0,877 и Асс±20% (Acc_(±20%)  ) ̅  =  76,36 %. На тестовой выборке лучшие решения обеспечивают высокое качество восстановления целевых параметров, а внешняя валидация на независимом объекте подтверждает устойчивость подхода. Установлено, что наиболее надежно восстанавливаются параметры параметры c и φ, тогда как прогнозирование  E50 является более сложной задачей из-за повышенной чувствительности этого показателя к условиям испытаний и структурным особенностям грунта. Практическая значимость работы состоит в том, что предложенный подход позволяет обоснованно восстанавливать недостающие механические параметры грунтов по данным стандартных лабораторных определений и может использоваться в цифровых системах инженерно-геологического моделирования, обработке лабораторных данных и подготовке расчетных параметров для инженерной практики.</p>
      </abstract>
      <trans-abstract xml:lang="en">
        <p>The article addresses the problem of reconstructing the strength and deformation characteristics of soils, namely cohesion c, internal friction angle φ, and secant deformation modulus E50, from physical and classification features available in routine laboratory reports. The relevance of the study is due to the fact that, in engineering geological practice, mechanical parameters are not determined for all samples, although these parameters are essential for foundation design calculations and for the parameterization of geotechnical models. The study is based on an archive of laboratory soil data, for which quality control, filtering, informative feature engineering, and independent external validation were performed. To solve the problem, a comparative analysis of machine learning models for tabular data was carried out, including CatBoost, FT-Transformer, and a multitask neural network, and an interpretable model ensemble was also considered. In addition, feature importance analysis was performed to assess the physical consistency of the obtained predictions. It is shown that the best performance is achieved by an ensemble with a dominant contribution from CatBoost, namely&#13;
FT-Transformer (0.10) + CatBoost (0.90), yielding mean WAPE = 13.16 %, mean R2 = 0.877 and mean Асс±20% = 76.36 %. On the test set, the best solutions provide high-quality reconstruction of the target parameters, while external validation on an independent site confirms the robustness of the approach. It was found that the parameters c and φ are reconstructed most reliably, whereas predicting E50 is a more challenging task due to the greater sensitivity of this parameter to testing conditions and the structural features of the soil. The practical significance of the study lies in the fact that the proposed approach enables a justified reconstruction of missing mechanical soil parameters from standard laboratory test data and can be used in digital systems for engineering geological modeling, laboratory data processing, and preparation of design parameters for engineering practice.</p>
      </trans-abstract>
      <kwd-group xml:lang="ru">
        <kwd>инженерная геология</kwd>
        <kwd>механика грунтов</kwd>
        <kwd>восстановление параметров</kwd>
        <kwd>табличные данные</kwd>
        <kwd>CatBoost</kwd>
        <kwd>FT-Transformer</kwd>
        <kwd>многозадачное обучение</kwd>
        <kwd>ансамблирование</kwd>
        <kwd>SHAP</kwd>
      </kwd-group>
      <kwd-group xml:lang="en">
        <kwd>engineering geology</kwd>
        <kwd>soil mechanics</kwd>
        <kwd>parameter reconstruction</kwd>
        <kwd>tabular data</kwd>
        <kwd>CatBoost</kwd>
        <kwd>FT-Transformer</kwd>
        <kwd>multi-task learning</kwd>
        <kwd>ensembling</kwd>
        <kwd>SHAP</kwd>
      </kwd-group>
      <funding-group>
        <funding-statement xml:lang="ru">Исследование выполнено без спонсорской поддержки.</funding-statement>
        <funding-statement xml:lang="en">The study was performed without external funding.</funding-statement>
      </funding-group>
    </article-meta>
  </front>
  <back>
    <ref-list>
      <title>References</title>
      <ref id="cit1">
        <label>1</label>
        <mixed-citation xml:lang="ru">Schanz T., Vermeer P.A., Bonnier P.G. The Hardening Soil Model: Formulation and Verification. In: Beyond 2000 in Computational Geotechnics: 10 years of PLAXIS International: Proceedings of the International Symposium beyond 2000 in Computational Geotechnics, 18–20 March 1999, Amsterdam, The Netherlands. Rotterdam: A. A. Balkema; 1999. P. 281–296.</mixed-citation>
      </ref>
      <ref id="cit2">
        <label>2</label>
        <mixed-citation xml:lang="ru">Zhao T., Shen F., Xu L. Review and comparison of machine learning methods in developing optimal models for predicting geotechnical properties with consideration of feature selection. Soils and Foundations. 2024;64(6). https://doi.org/10.1016/j.sandf.2024.101523</mixed-citation>
      </ref>
      <ref id="cit3">
        <label>3</label>
        <mixed-citation xml:lang="ru">Yuan B., Choo Ch.S., Yeo L.Y., et al. Physics-informed machine learning in geotechnical engineering: a direction paper. Geomechanics and Geoengineering. 2025;20(5):1128–1159. https://doi.org/10.1080/17486025.2025.2502029</mixed-citation>
      </ref>
      <ref id="cit4">
        <label>4</label>
        <mixed-citation xml:lang="ru">Alzighaibi W.A., Daghistani F. Machine Learning in Geotechnical Engineering: A State-of-the-Art Review of Research Progress and Barriers to Real-World Implementation. In: 2025 IEEE International Conference on Emerging Trends in Engineering and Computing (ETECOM), 29–30 October 2025, Riffa, Bahrain. IEEE; 2025. https://doi.org/10.1109/ETECOM66111.2025.11319124</mixed-citation>
      </ref>
      <ref id="cit5">
        <label>5</label>
        <mixed-citation xml:lang="ru">Bozorgzadeh N., Feng Y. Evaluation structures for machine learning models in geotechnical engineering. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards. 2024;18(1):52–59. https://doi.org/10.1080/17499518.2024.2313485</mixed-citation>
      </ref>
      <ref id="cit6">
        <label>6</label>
        <mixed-citation xml:lang="ru">Lei D., Zhang Y., Lu Zh., et al. A machine learning framework for predicting shear strength properties of rock materials. Scientific Reports. 2025;15(1). https://doi.org/10.1038/s41598-025-91436-8</mixed-citation>
      </ref>
      <ref id="cit7">
        <label>7</label>
        <mixed-citation xml:lang="ru">Ahmad M., Zubi M.A., Almujibah H., et al. Improved prediction of soil shear strength using machine learning algorithms: interpretability analysis using SHapley Additive exPlanations. Frontiers in Earth Science. 2025;13. https://doi.org/10.3389/feart.2025.1542291</mixed-citation>
      </ref>
      <ref id="cit8">
        <label>8</label>
        <mixed-citation xml:lang="ru">Yuke W., Shuang F., Yanhui Zh., Bei Zh., et al. A data-driven model for predicting shear strength indexes of normally consolidated soils. Chinese Journal of Geotechnical Engineering. 2023;45(S2):183–188. https://doi.org/10.11779/CJGE2023S20025</mixed-citation>
      </ref>
      <ref id="cit9">
        <label>9</label>
        <mixed-citation xml:lang="ru">Lundberg S., Lee S.-I. A Unified Approach to Interpreting Model Predictions. arXiv. URL: https://doi.org/10.48550/arXiv.1705.07874 [Accessed 10th March 2026].</mixed-citation>
      </ref>
      <ref id="cit10">
        <label>10</label>
        <mixed-citation xml:lang="ru">Jas K., Dodagoudar G.R. Explainable machine learning model for liquefaction potential assessment of soils using XGBoost-SHAP. Soil Dynamics and Earthquake Engineering. 2023;165. https://doi.org/10.1016/j.soildyn.2022.107662</mixed-citation>
      </ref>
      <ref id="cit11">
        <label>11</label>
        <mixed-citation xml:lang="ru">Prokhorenkova L., Gusev G., Vorobev A., et al. CatBoost: unbiased boosting with categorical features. arXiv. URL: https://doi.org/10.48550/arXiv.1706.09516 [Accessed 10th March 2026].</mixed-citation>
      </ref>
      <ref id="cit12">
        <label>12</label>
        <mixed-citation xml:lang="ru">Gorishniy Y., Rubachev I., Khrulkov V., Babenko A. Revisiting Deep Learning Models for Tabular Data. arXiv. URL: https://doi.org/10.48550/arXiv.2106.11959 [Accessed 10th March 2026].</mixed-citation>
      </ref>
      <ref id="cit13">
        <label>13</label>
        <mixed-citation xml:lang="ru">Somepalli G., Goldblum M., Schwarzschild A., Bruss C.B., Goldstein T. SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training. arXiv. URL: https://doi.org/10.48550/arXiv.2106.01342 [Accessed 10th March 2026].</mixed-citation>
      </ref>
      <ref id="cit14">
        <label>14</label>
        <mixed-citation xml:lang="ru">Hollmann N., Müller S., Eggensperger K., Hutter F. TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second. arXiv. URL: https://doi.org/10.48550/arXiv.2207.01848 [Accessed 11th March 2026].</mixed-citation>
      </ref>
      <ref id="cit15">
        <label>15</label>
        <mixed-citation xml:lang="ru">Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13–17 August 2016, San Francisco, CA, USA. New York: ACM; 2016. P. 785–794. https://doi.org/10.1145/2939672.2939785</mixed-citation>
      </ref>
      <ref id="cit16">
        <label>16</label>
        <mixed-citation xml:lang="ru">Ke G., Meng Q., Finley Th., et al. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 04–09 December 2017, Long Beach, CA, USA. 2017. P. 3146–3154.</mixed-citation>
      </ref>
      <ref id="cit17">
        <label>17</label>
        <mixed-citation xml:lang="ru">Friedman J.H. Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics. 2001;29(5):1189–1232. https://doi.org/10.1214/aos/1013203451</mixed-citation>
      </ref>
      <ref id="cit18">
        <label>18</label>
        <mixed-citation xml:lang="ru">Breiman L. Stacked Regressions. Machine Learning. 1996;24:49–64. https://doi.org/10.1007/BF00117832</mixed-citation>
      </ref>
      <ref id="cit19">
        <label>19</label>
        <mixed-citation xml:lang="ru">Caruana R. Multitask Learning. Machine Learning. 1997;28:41–75. https://doi.org/10.1023/A:1007379606734</mixed-citation>
      </ref>
      <ref id="cit20">
        <label>20</label>
        <mixed-citation xml:lang="ru">Salih A.M., Raisi-Estabragh Z., Galazzo I.B., et al. A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME. Advanced Intelligent Systems. 2024. https://doi.org/10.1002/aisy.202400304</mixed-citation>
      </ref>
      <ref id="cit21">
        <label>21</label>
        <mixed-citation xml:lang="ru">Ankah M.L.Y., Adjei-Yeboah Sh., Ziggah Y.Y., Asare E.N. Advanced hybrid machine learning models with explainable AI for predicting residual friction angle in clay soils. Scientific Reports. 2025;15. https://doi.org/10.1038/s41598-025-05962-6</mixed-citation>
      </ref>
      <ref id="cit22">
        <label>22</label>
        <mixed-citation xml:lang="ru">Wu P., Chen J., Huang J., et al. Interpretable machine learning approach for predicting lunar soil shear strength parameters based on data imputation techniques. Advances in Space Research. 2025;76(2):1091–1115. https://doi.org/10.1016/j.asr.2025.04.071</mixed-citation>
      </ref>
      <ref id="cit23">
        <label>23</label>
        <mixed-citation xml:lang="ru">Molnar Ch. Interpretable Machine Learning. Lulu.com; 2020. 320 p.</mixed-citation>
      </ref>
      <ref id="cit24">
        <label>24</label>
        <mixed-citation xml:lang="ru">Arik S.Ö., Pfister T. TabNet: Attentive Interpretable Tabular Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2021;35(8):6679–6687. https://doi.org/10.1609/aaai.v35i8.16826</mixed-citation>
      </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>