<?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">nature</journal-id><journal-title-group><journal-title xml:lang="ru">Природопользование</journal-title><trans-title-group xml:lang="en"><trans-title>Nature Management</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2079-3928</issn><publisher><publisher-name>Институт природопользования НАН Беларуси</publisher-name></publisher></journal-meta><article-meta><article-id custom-type="elpub" pub-id-type="custom">nature-142</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>ГЕОГРАФИЯ. ГЕОЭКОЛОГИЯ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>GEOGRAPHY. GEOECOLOGY</subject></subj-group></article-categories><title-group><article-title>Коррекция ошибок мезомасштабного численного прогноза погоды методами машинного обучения</article-title><trans-title-group xml:lang="en"><trans-title>Error correction of mesoscale numerical weather forecast by machine learning methods</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Лысенко</surname><given-names>С. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Lysenko</surname><given-names>S. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Лысенко Сергей Александрович – доктор физико-математических наук, профессор, директор</p><p>ул. Ф. Скорины, 10, 220076, г. Минск</p></bio><bio xml:lang="en"><p>Sergey A. Lysenko – D. Sc. (Physical and Mathematical), Professor, Director</p><p>10, F. Skoriny Str., 220076, Minsk</p></bio><email xlink:type="simple">lysenko.nature@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Юдыцкая</surname><given-names>К. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Yudytskaya</surname><given-names>K. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Юдыцкая Ксения Сергеевна – младший научный сотрудник</p><p>ул. Ф. Скорины, 10, 220076, г. Минск</p></bio><bio xml:lang="en"><p>Kseniya S. Yudytskaya – Junior Researcher</p><p>10, F. Skoriny Str., 220076, Minsk</p></bio><email xlink:type="simple">kseniya.yudytskaya@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Институт природопользования НАН Беларуси</institution></aff><aff xml:lang="en"><institution>Institute of Nature Management of the National Academy of Sciences of Belarus</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>22</day><month>03</month><year>2026</year></pub-date><volume>0</volume><issue>2</issue><fpage>5</fpage><lpage>18</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Лысенко С.А., Юдыцкая К.С., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Лысенко С.А., Юдыцкая К.С.</copyright-holder><copyright-holder xml:lang="en">Lysenko S.A., Yudytskaya K.S.</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://www.nature-journal.by/jour/article/view/142">https://www.nature-journal.by/jour/article/view/142</self-uri><abstract><p>Проанализированы метрики успешности краткосрочных численных прогнозов погоды для территории Беларуси на основе мезомасштабной гидродинамической модели атмосферы WRF (Weather Research and Forecasting) с регионально адаптированным блоком моделирования подстилающей поверхности. Оценена эффективность коррекции систематических ошибок численных прогнозов приземных метеопараметров с применением метода экспоненциально взвешенного скользящего среднего и фильтра Калмана.</p><p>Предложен метод повышения оправдываемости мезомасштабных численных прогнозов, в котором поправки к прогностическим полям метеопараметров вычисляются с использованием моделей машинного обучения, а предикторами выступают прогнозы нескольких глобальных и региональных гидродинамических моделей атмосферы. Проведен сравнительный анализ эффективности коррекции численных прогнозов с применением моделей машинного обучения (XGBoost и ElasticNet) и рекуррентной графовой нейронной сети с механизмом внимания (TGCN-A).</p><p>Показано, что за счет более точного описания в модели WRF подстилающей поверхности и предварительной обработки ее выходной продукции методом экспоненциально взвешенного скользящего среднего оправдываемость численных прогнозов температуры на сроки до 48 ч повышается на 1,0–4,4 %, а среднеквадратическая погрешность скорости ветра уменьшается на 0,1–0,2 м/c. Последующая коррекция прогнозов модели WRF с применением методов машинного обучения и нейронной сети дополнительно повышает оправдываемость численного прогноза температуры в среднем на 3,2 %, а также уменьшает среднеквадратические погрешности прогнозов приземного давления и скорости ветра на 0,20–0,74 гПа и 0,32–0,53 м/c соответственно.</p></abstract><trans-abstract xml:lang="en"><p>The metrics of success of short-term numerical weather forecasts for the territory of Belarus based on the mesoscale hydrodynamic model of the atmosphere WRF (Weather Research and Forecasting) with regionally adapted block of underlying surface modelling are analyzed. The efficiency of systematic error correction of numerical forecasts of surface meteorological parameters using the method of exponentially weighted moving average and Kalman filter is evaluated.</p><p>A method of increasing the validity of mesoscale numerical forecasts has been proposed, in which corrections to the prognostic fields of meteorological parameters are calculated using machine learning models, and predictors are forecasts of several global and regional hydrodynamic models of the atmosphere. A comparative analysis of the efficiency of correction of numerical forecasts using machine learning models (XGBoost and ElasticNet) and recurrent graph neural network with attention mechanism (TGCN-A) was carried out.</p><p>It is shown that due to a more accurate description of the underlying surface in the WRF model and preliminary processing of its output by the exponentially weighted moving average method, the validity of numerical temperature fore- casts for periods up to 48 h increases by 1.0–4.4 %, and the mean square error of wind speed decreases by 0.1–0.2 m/s. Subsequent correction of WRF model forecasts using machine learning and neural network methods additionally increases the validity of numerical temperature forecasts by 3,2 % on average, and also reduces the RMS errors of surface pressure and wind speed forecasts by 0.20–0.74 hPa and 0.32–0.53 m/s, respectively.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>численный прогноз погоды</kwd><kwd>мезомасштабная модель</kwd><kwd>валидация моделей</kwd><kwd>оправдываемость прогноза</kwd><kwd>коррекция систематических ошибок</kwd><kwd>машинное обучение</kwd></kwd-group><kwd-group xml:lang="en"><kwd>numerical weather forecast</kwd><kwd>mesoscale model</kwd><kwd>model validation</kwd><kwd>forecast accuracy</kwd><kwd>correction of systematic errors</kwd><kwd>machine learning</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">Harvey, A. C. Time Series Models / A. C. Harvey. – 2nd ed. – New York : Harvester Wheatsheaf, 1993. – P. 179–198.</mixed-citation><mixed-citation xml:lang="en">Harvey A. C. Time Series Models. 2nd edition. New York, Harvester Wheatsheaf Publ., 1993, pp. 179–198.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Kalman, R. E. A new approach to linear filtering and prediction problems / R. E. Kalman // Journal of Basic Engineering. – 1960. – Vol. 82. – P. 35–45.</mixed-citation><mixed-citation xml:lang="en">Kalman R. E. A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 1960, vol. 82, pp. 35–45.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Alerskans, E. Local temperature forecasts based on statistical post-processing of numerical weather prediction data / E. Alerskans, E. Kaas // Meteorological Applications. – 2021. – Vol. 28, № 4. – 21 p.</mixed-citation><mixed-citation xml:lang="en">Alerskans E., Kaas E. Local temperature forecasts based on statistical post-processing of numerical weather prediction data. Meteorol. Appl., 2021, vol. 28, no. 4, 21 p.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Быков, Ф. Л. Статистическая коррекция прогнозов погоды по модели COSMO с помощью нейронных сетей / Ф. Л. Быков // Метеорология и гидрология. – 2020. – № 3. – С. 5–20.</mixed-citation><mixed-citation xml:lang="en">Bykov F. L. Statisticheskaya korrekciya prognozov pogody po modeli COSMO s pomoshch'yu nejronnyh setej [Statistical correction of weather forecasts based on the COSMO model using neural networks] Meteorologiya I gidrologiya = Meteorology and Hydrology, 2020, vol. 3, pp. 5–20. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Statistical Postprocessing for Weather Forecasts: Review, Challenges, and Avenues in a Big Data World / S. Vannitsem [et al.] // Bulletin of the American Meteorological Society. – 2021. – Vol. 102, № 3. – P. E681–E699.</mixed-citation><mixed-citation xml:lang="en">Vannitsem S., Bremnes J. B., Demaeyer J., Evans G., e.a. Statistical Postprocessing for Weather Forecasts: Review, Challenges, and Avenues in a Big Data World. Bulletin of the American Meteorological Society, 2021, vol. 102, no. 3, pp. E681–E699.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Bengtsson, L. Dynamic Meteorology: Data Assimilation Methods / L. Bengtsson, M. Ghil, E. Kallen. – New York : Springer-Verlag, 1981. – 330 p.</mixed-citation><mixed-citation xml:lang="en">Bengtsson L., Ghil M., Kallen E. Dynamic Meteorology: Data Assimilation Methods. New York, Springer-Verlag Publ., 1981, 330 p.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Lorenc, A. C. Analysis methods for numerical weather prediction / A. C. Lorenc // Quarterly Journal of the Royal Meteorological Society. – 1986. – Vol. 112. – P. 1177–1194.</mixed-citation><mixed-citation xml:lang="en">Lorenc A. C. Analysis methods for numerical weather prediction. Quart. J. Roy. Meteor. Soc., 1986, vol. 112, pp. 1177–1194.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Формирование продукции систем негидростатического моделирования атмосферы COSMO-RuBy (Гидрометцентр России) и WRF-ARW (Белгидромет) для краткосрочного прогноза погоды / И. А. Розинкина [и др.] // Гидрометеорологические исследования и прогнозы. – 2021. – № 4 (382). – С. 6–29.</mixed-citation><mixed-citation xml:lang="en">Rozinkina I. A., Rivin G. S., Burak R. N., e.a. Formirovanie produkcii sistem negidrostaticheskogo modelirovaniya atmosfery COSMO-RuBy (Gidrometcentr Rossii) i WRF-ARW (Belgidromet) dlya kratkosrochnogo prognoza pogody [Product development of COSMO-RuBy (Hydrometeorological Center of Russia) and WRF-ARW (Belhydromet) nonhydrostatic atmospheric modeling systems for short-term weather forecast]. Gidrometeorologicheskie issledovaniya i prognozy = Hydrometeorological studies and forecasts, 2021, vol. 4 (382), pp. 6–29. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Лысенко, С. А. Оценки влияния подстилающей поверхности на точность численного прогноза температуры воздуха на территории Беларуси с использованием модели WRF / С. А. Лысенко, П. О. Зайко // Гидрометеорологические исследования и прогнозы. – 2021. – № 4. – С. 50–68.</mixed-citation><mixed-citation xml:lang="en">Lysenko S. A., Zaiko P. O. Ocenki vliyaniya podstilayushchej poverhnosti na tochnost' chislennogo prognoza temperatury vozduha na territorii Belarusi s ispol'zovaniem modeli WRF [Estimation of the influence of the underlying surface on the accuracy of the numerical forecast of air temperature in Belarus using the WRF model]. Gidro meteorologicheskie issledovaniya i prognozy = Hydrometeorological studies and forecasts, 2021, vol. 4, pp. 50–68. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Лысенко, С. А. Геоинформационная система повышения оправдываемости гидродинамического прогноза погоды для территории Беларуси на основе данных дистанционного зондирования Земли и объективного анализа метеорологических полей / С. А. Лысенко, П. О. Зайко // Природопользование. – 2024. – № 1. – С. 30–40.</mixed-citation><mixed-citation xml:lang="en">Lysenko S. A., Zaiko P. O. Geoinformacionnaya sistema povysheniya opravdyvaemosti gidrodinamicheskogo prognoza pogody dlya territorii Belarusi na osnove dannyh distancionnogo zondirovaniya Zemli i ob"ektivnogo analiza meteorologicheskih polej [Geoinformation system for improving the accuracy of hydrodynamic weather forecasting for the territory of Belarus based on remote sensing data and objective analysis of meteorological fields]. Prirodopol'zovanie = Nature Management, 2024, no. 1, pp. 30–40. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Kipf, T. N. Semi-Supervised Classification with Graph Convolutional Networks / T. N. Kipf, M. Welling // ArXiv preprint. – 2016. – arXiv:1609.02907.</mixed-citation><mixed-citation xml:lang="en">Kipf T. N., Welling M. Semi-Supervised Classification with Graph Convolutional Networks. ArXiv preprint, 2016, arXiv:1609.02907.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction / L. Zhao [et al.] // IEEE Transactions on Intelligent Transportation Systems. – 2020. – Vol. 21, № 9. – P. 3848–3858.</mixed-citation><mixed-citation xml:lang="en">Zhao L., Song Y., Zhang C., e.a. T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction. IEEE Transactions on Intelligent Transportation Systems, 2020, vol. 21, no. 9, pp. 3848–3858.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting / Bai J. [et al.] // ISPRS International Journal of Geo-Information. – 2021. – Vol. 10, № 7. – P. 485.</mixed-citation><mixed-citation xml:lang="en">Bai J., Zhu J., Song Y., e.a. A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting. ISPRS International Journal of Geo-Information, 2021, vol. 10, no. 7, p. 485.</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>
