Теоретическая и прикладная экология1995-43012618-840610.25750/1995-4301-2026-3-017-030OtherО применении искусственного интеллекта и больших языковых моделей в области почвенно-экологических исследований (обзор)On the application of artificial intelligence and large language models in soil and environmental research: a reviewБоковН. А.BokovN. A.biotekhnologiya@fanc-sv.ruhttps://orcid.org/0000-0002-1000-1192ШирокихН. Г.ShirokikhI. G.https://orcid.org/0000-0002-3319-2729Federal Agricultural Research Center of North-East named N. V. RudnitskyKirovRussiaФедеральный аграрный научный центр Северо-Востока им. Н. В. РудницкогоКировРоссияInstitute of Biology of Komi Science Centre of the Ural Branch of the Russian Academy of SciencesSyktyvkarRussiaИнститут биологии Коми научного центра Уральского отделения Российской академии наукСыктывкарРоссия2909202631730http://www.envjournal.ru/arhvr.php?q=1009

В последние годы в научных исследованиях активно развиваются методы, основанные на использовании искусственного интеллекта (ИИ) и больших языковых моделей (БИМ), которые способны обрабатывать и интерпретировать значительные объёмы текстовой и структурированной (таблицы, числовые и категориальные данные, данные датчиков и т. п.) информации. Экология почвы как область, характеризующаяся быстрым накоплением разнородных данных, включая результаты метагеномных анализов почвенных микробиомов, может потенциально извлечь существенную пользу от применения подобных инструментов. В настоящем обзоре рассмотрены основные направления использования ИИ в исследованиях в области почвенной экологии и микробиологии, включая анализ научной литературы, аннотирование и систематизацию микробиологических, агрохимических и агрофизических данных, а также создание моделей для прогнозирования на основе метагеномных данных почвенных микробиомов показателей плодородия и продуктивности сельскохозяйственных угодий. Обсуждаются ключевые преимущества данных подходов, их ограничения и возможные методологические риски. Несмотря на необходимость дальнейшего усовершенствования и оптимизации имеющихся к настоящему времени технологий ИИ и БИМ, выполненный анализ литературы свидетельствует об их значительном потенциале в обеспечении дальнейшего развития почвенно-экологических исследований и достижении практических результатов в аграрном производстве.

In recent years, scientific research has seen the rapid development of methods based on artificial intelligence (AI) and large language models (LLMs), which are capable of processing and interpreting significant volumes of text and structured information, including tables, numerical and categorical data, and sensor data and other heterogeneous information, using specialized and multimodal AI systems. Soil ecology, as a field characterized by the rapid accumulation of heterogeneous data, including the results of metagenomic analyses of soil microbiomes, can potentially benefit significantly from the application of such tools. The aim of this review is to identify, analyze, and summarize current approaches to the use of AI and LLM technologies in soil and environmental research. The review examines the main areas of AI application, including scientific literature search and analysis, semantic search for relevant publications, citation mapping, text summarization, and the use of generative AI assistants. Particular attention is paid to the application of AI methods in the analysis of soil microbiomes and to the potential use of metagenomic data for predicting soil fertility and agricultural productivity. The challenges associated with adapting AI methods originally developed for biomedical research to the specific characteristics of soil and environmental datasets are also considered. The key advantages of these approaches, their limitations, and potential methodological risks, including those related to data quality and the reliability of AI-generated information, are discussed. Despite the need for further improvement and optimization of currently available AI and LLM technologies, the literature review demonstrates their significant potential for advancing soil and environmental research and supporting practical applications in agriculture.

искусственный интеллектнейронные сетимашинное обучениебольшие языковые моделиэкология микроорганизмовпочвенный микробиомметагеномикааграрное производствоartificial intelligenceneural networksmachine learninglarge language modelsmicrobial ecologysoil microbiomemetagenomicsagricultural productionРабота выполнена в рамках Государственных заданий ФАНЦ Северо-Востока имени Н.В. Рудницкого (тема № FNWE-2025-0005) и ФИЦ «Коми научный центр Уральского отделения Российской академии наук» (по теме «Оценка состояния трансформированных экосистем подзоны южной тайги, методические подходы к их биоремедиации», номер государственной регистрации в ЕГИСУ № 125021402208-5).Dobrovol’skii G.V. Dokuchaev and present-day natural science // Eurasian Soil Sc. 1996. V. 29. No. 2. P. 105–110.Dokuchaev V.V. Essays: in 9 volumes. Moskva; Leningrad: Publishing House of the USSR Academy of Sciences, 1949–1961. (in Russian).Montgomery D.R. Soil erosion and agricultural sustainability // Proc. Natl. Acad. Sci. USA. 2007. V. 104. No. 33. P. 13268–13272. doi: 10.1073/pnas.0611508104Dobrovolskiy G.V. Soil degradation as a threat of global ecological crisis // Vek globalizatsii. 2008. No. 2. P. 54–65 (in Russian).Giller K.E., Delaune T., Silva J.V., Descheemaeker K., van de Ven G., Schut A.G.T., van Wijk M., Hammond J., Hochman Z., Taulya G., Chikowo R., Narayanan S., Kishore A., Bresciani F., Teixeira H.M., Andersson J.A., van Ittersum M.K. The future of farming: who will pro- duce our food? // Food Sec. 2021. V. 13. P. 1073–1099. doi: 10.1007/s12571-021-01184-6Kurmanbayev A.A., Syndet T.R. Soil health con- cept and modern soil health indicators // Soil Science and Agrichemistry. 2023. No. 2. P. 91–106 (in Russian). doi: 10.51886/1999-740Х_2023_2_91Nikitin D.A., Semenov M.V., Chernov T.I., Kseno- fontova N.A., Zhelezova A.D., Ivanova E.A., Khitrov N.B., Stepanov A.L. Microbiological indicators of ecological soil functions: a review // Eurasian Soil Sc. 2022. V. 55. P. 221–234. doi: 10.1134/S1064229322020090Golubev A.S., Berestetskiy A.O. Future direc- tions for use of biological and biorational herbicides in Russia (review) // Agricultural Biology. 2021. V. 56. No. 5. P. 868–884 (in Russian). doi: 10.15389/ agrobiology.2021.5.868rusMohanty L.K., Singh N.K., Raj P., Prakash A., Tiwari A.K., Singh V., Sachan P. Nurturing crops, en- hancing soil health, and sustaining agricultural prosperity worldwide through agronomy // J. Exp. Agric. Int. 2024. V. 46. No. 2. P. 46–67. doi: 10.9734/jeai/2024/v46i22308Ryazanov S.S., Kulagina V.I. Soil health: an overview of concepts and monitoring methods // Moscow Univ. Soil Sci. Bull. 2026. V. 81. P. 16–31. doi: 10.3103/Slobodkin A.I., Slobodkina G.B. Diversity of sul- fur-disproportionating microorganisms // Microbiology. 2019. V. 88. P. 509–522. doi: 10.1134/S0026261719050138Zavarzina D.G. The role of dissimilatory Fe(III)- reducing bacteria in transformation of iron minerals // Paleontol. J. 2004. V. 38. No. 3. P. 231–237.Vecherskii M.V., Semenov M.V., Lisenkova A.A., Stepankov A.A. Metagenomics: a new direction in eco- logy // Biol. Bull. Russ. Acad. Sci. 2022. V. 48. Suppl. 3. P. S107–S117. doi: 10.1134/S1062359022010150Semenov M.V. Metabarcoding and metagenomics in soil ecological research: achievements, problems and opportunities // Biol. Bull. Rev. 2021. V. 11. P. 40–53. doi: 10.1134/S2079086421010084Nesme J., Achouak W., Agathos S.N., Bailey M., Baldrian P., Brunel D., Frostegård Å., Heulin T., Jansson J.K., Jurkevitch E., Kruus K.L., Kowalchuk G.A., Lagares A., Lappin-Scott H.M., Lemanceau P., Le Paslier D., Mandic-Mulec I., Murrell J.C., Myrold D.D., Nalin R., Nan- nipieri P., Neufeld J.D., O’Gara F., Parnell J.J., Pühler A., Py- lro V., Ramos J.L., Roesch L.F.W., Schloter M., Schleper C., Sczyrba A., Sessitsch A., Sjöling S., Sørensen J., Sørensen S.J., Tebbe C.C., Topp E., Tsiamis G., van Elsas J.D., van Keulen G., Widmer F., Wagner M., Zhang T., Zhang X., Zhao L., Zhu Y.G., Vogel T.M., Simonet P. Back to the future of soil metagenomics // Front. Microbiol. 2016. V. 7. Article No. 73. doi: 10.3389/fmicb.2016.00073Leite M.F.A., van den Broek S.W.E.B., Kuramae E.E. Current challenges and pitfalls in soil metagenomics // Microorganisms. 2022. V. 10. No. 10. Article No. 1900. doi: 10.3390/microorganisms10101900Wydro U. Soil microbiome study based on DNA extraction: a review // Water. 2022. V. 14. No. 24. Article No. 3999. doi: 10.3390/w14243999Veselovsky V., Romanov M., Zoruk P., Larin A., Babenko V., Morozov M., Strokach A., Zakharevich N., Khamidova S., Danilova A., Vatlin A., Pavshintsev V., Chenguang F., Tsybizov D., Mitkin N., Galanova O., Zakharenko A., Golokhvast K., Klimina K. Compara- tive evaluation of sequencing platforms: Pacific Biosci- ences, Oxford Nanopore Technologies, and Illumina for 16S rRNA-based soil microbiome profiling // Front. Mi- crobiol. 2025. V. 16. Article No. 1633360. doi: 10.3389/ fmicb.2025.1633360D’Argenio V. The high-throughput analyses era: are we ready for the data struggle? // High Throughput. 2018. V. 7. No. 1. Article No. 8. doi: 10.3390/ht7010008Sharpton T.J. An introduction to the analysis of shotgun metagenomic data // Front. Plant Sci. 2014. V. 5. Article No. 209. doi: 10.3389/fpls.2014.00209Panciu B.-I., Barbu Dragne G.-L. A.I. in agri- culture – a bibliometric approach // Proceedings of the International Conference on Business Excellence. 2025. V. 19. No. 1. P. 5189–5199. doi: 10.2478/picbe-2025-0397Zhao Y., Liang J., Chen B., Deng X., Zhang Y., Xiong Z., Pan M., Meng X. Applications research progress and prospects of multi-agent large language models in agricultural // Smart Agric. 2025. V. 7. No. 5. P. 37–51. doi: 10.12133/j.smartag.SA202503026Sirilertmekasakul C., Rattanawong W., Gong- vatana A., Srikiatkhachorn A. The current state of artificial intelligence-augmented digitized neurocognitive screen- ing test // Front. Hum. Neurosci. 2023. V. 17. Article No. 1133632. doi: 10.3389/fnhum.2023.1133632Saied M., Mokhtar N., Badr A., Adel M., Boles P., Khoriba G. AI in literature reviews: a survey of current and emerging methods // Proceedings of the 2024 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC). Cairo, Egypt, 2024. P. 61–65. doi: 10.1109/Naudé W. Artificial intelligence vs COVID-19: limitations, constraints and pitfalls // AI & Soc. 2020. V. 35. No. 3. P. 761–765. doi: 10.1007/s00146-020-00978-0Gerlich M. AI tools in society: impacts on cognitive offloading and the future of critical thinking // Societies. 2025. V. 15. No. 1. Article No. 6. doi: 10.3390/soc15010006Schmidt L., Cree I., Campbell F., WCT EVI MAP group. Digital tools to support the systematic review pro- cess: an introduction // J. Eval. Clin. Pract. 2025. V. 31. No. 3. Article No. e70100. doi: 10.1111/jep.70100Filimonov V.Yu. Large language models and their role in modern scientific discoveries // Philosophical Prob- lems of IT and Cyberspace (PhilIT&C). 2024. V. 25. No. 1. P. 42–57 (in Russian). doi: 10.17726/philIT.2024.1.3Mtotywa M.M., Mowers J.L.J., Ndou W., Mole- ko T.V.Q., Ledwaba M.J. Artificial intelligence in lit- erature review synthesis: a step-by-step methodological approach for researchers and academics // Informatics. 2026. V. 13. No. 3. Article No. 43. doi: 10.3390/infor-Sa I., Ge Z., Dayoub F., Upcroft B., Perez T., Mc- Cool C. DeepFruits: a fruit detection system using deep neural networks // Sensors. 2016. V. 16. No. 8. Article No. 1222. doi: 10.3390/s16081222Fallico N. Exploring Research Rabbit: your new favourite reference manager // Medical Writing. 2025. V. 34. No. 1. P. 67–69. doi: 10.56012/wxzm3433Zhang Y., Long J., Zhao W. The curvilinear relation- ships between relational embeddedness and dynamic capabili- ties: the mediating effect of ambidextrous learning // Front. Psychol. 2022. V. 13. Article No. 830377. doi: 10.3389/ fpsyg.2022.830377Correa-Garcia S., Constant P., Yergeau E. The forecasting power of the microbiome // Trends Micro- biol. 2022. V. 31. No. 5. P. 444–452. doi: 10.1016/j. tim.2022.11.013De Andrade V.H.G.Z., Redmile-Gordon M., Barbosa B.H.G., Andreote F.D., Roesch L.F.W., Pylro V.S. Artificially intelligent soil quality and health indices for ‘next generation’ food production systems // Trends Food Sci. Tech- nol. 2021. V. 107. P. 195–200. doi: 10.1016/j.tifs.2020.10.018Wilhelm R.C., van Es H.M., Buckley D.H. Pre- dicting measures of soil health using the microbiome and supervised machine learning // Soil Biol. Biochem. 2022. V. 164. Article No. 108472. doi: 10.1016/j.soilbio.2021.108472Breiman L. Random forests // Mach. Learn. 2001. V. 45. P. 5–32. doi: 10.1023/A:1010933404324Cortes C., Vapnik V. Support-vector networks // Mach. Learn. 1995. V. 20. P. 273–297. doi: 10.1007/ BF00994018Hermans S.M., Buckley H.L., Case B.S., Curran- Cournane F., Taylor M., Lear G. Using soil bacterial com- munities to predict physico-chemical variables and soil quality // Microbiome. 2020. V. 8. No. 1. Article No. 79. doi: 10.1186/s40168-020-00858-1Chang H.X., Haudenshield J.S., Bowen C.R., Hartman G.L. Metagenome-wide association study and machine learning prediction of bulk soil microbiome and crop productivity // Front. Microbiol. 2017. V. 8. Article No. 519. doi: 10.3389/fmicb.2017.00519Sadeghi S., Petermann B.J., Steffan J.J., Bre- vik E.C., Gedeon C. Predicting microbial responses to changes in soil physical and chemical properties under dif- ferent land management // Appl. Soil Ecol. 2023. V. 188.Tajik S., Ayoubi S., Nourbakhsh F. Prediction of soil enzymes activity by digital terrain analysis: compar- ing artificial neural network and multiple linear regres- sion models // Environ. Eng. Sci. 2012. V. 29. No. 8. P. 798–806. doi: 10.1089/ees.2011.0313Larsen P.E., Field D., Gilbert J.A. Predicting bacterial community assemblages using an artificial neu- ral network approach // Nat. Methods. 2012. V. 9. No. 6. P. 621–625. doi: 10.1038/nmeth.1975Santos E.C., Armas E.D., Crowley D., Lambais M.R. Artificial neural network modeling of microbial com- munity structures in the Atlantic Forest of Brazil // Soil Biol. Biochem. 2014. V. 69. P. 101–109. doi: 10.1016/j. soilbio.2013.10.049Shirokih I.G., Bokov N.A., Shirokih A.A., Ashikh- mina T.Ya. Antibiotic resistance profiles of streptomycetes from different soils of the Vyatka Prikamye // Theoretical and Applied Ecology. 2026. No. 2. P. 183–191 (in Russian). doi: 10.25750/1995-4301-2026-2-183-191Langley P. The changing science of machine lear- ning // Mach. Learn. 2011. V. 82. P. 275–279. doi: 10.1007/LeCun Y., Bengio Y., Hinton G. Deep learning // Nature. 2015. V. 521. No. 7553. P. 436–444. doi: 10.1038/ nature14539Ghannam R.B., Techtmann S.M. Machine learn- ing applications in microbial ecology, human microbiome ТЕОРЕТИЧЕСКИЕ ПРОБЛЕМЫ ЭКОЛОГИИ Теорeтическая и прикладная экология. 2026. № 3 / Theoretical and Applied Ecology. 2026. No. 3 studies, and environmental monitoring // Comput. Struct. Biotechnol. J. 2021. V. 19. P. 1092–1107. doi: 10.1016/j. csbj.2021.01.028Pace R., Schiano Di Cola V., Monti M.M., Affinito A., Cuomo S., Loreto F., Ruocco M. Artificial intelligence in soil microbiome analysis: a potential application in predicting and enhancing soil health – a review // Discov. Appl. Sci. 2025. V. 7. Article No. 85. doi: 10.1007/s42452-024-06381-4Iadanza E., Fabbri R., Bašić-Čičak D., Amedei A., Telalovic J.H. Gut microbiota and artificial intelligence ap- proaches: a scoping review // Health Technol. 2020. V. 10. P. 1343–1358. doi: 10.1007/s12553-020-00486-7Gewers F.L., Ferreira G.R., de Arruda H.F., Silva F.N., Comin C.H., Amancio D.R., Costa L.F. Principal compo- nent analysis: a natural approach to data exploration // ACM Comput. Surv. 2021. V. 54. No. 4. Article No. 70. doi: 10.1145/3447755Van der Maaten L., Hinton G. Visualizing data us- ing t-SNE // J. Mach. Learn. Res. 2008. V. 9. P. 2579–2605.Becht E., McInnes L., Healy J., Dutertre C.A., Kwok I.W.H., Ng L.G., Ginhoux F., Newell E.W. Dimensio- nality reduction for visualizing single-cell data using UMAP // Nat. Biotechnol. 2019. V. 37. P. 38–44. doi: 10.1038/nbt.4314Zeng T., Yu X., Chen Z. Applying artificial intel- ligence in the microbiome for gastrointestinal diseases: a review // J. Gastroenterol. Hepatol. 2021. V. 36. No. 4. P. 832–840. doi: 10.1111/jgh.1550Friedman J.H. Stochastic gradient boosting // Comput. Stat. Data Anal. 2002. V. 38. No. 4. P. 367–378. doi: 10.1016/S0167-9473(01)00065-2LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D. Backpropagation applied to handwritten zip code recognition // Neural Comput. 1989. V. 1. No. 4. P. 541–551. doi: 10.1162/ neco.1989.1.4.541Hopfield J.J. Neural networks and physical systems with emergent collective computational abili- ties // Proc. Natl. Acad. Sci. USA. 1982. V. 79. No. 8. P. 2554–2558. doi: 10.1073/pnas.79.8.255Liou C.Y., Cheng W.C., Liou J.W., Liou D.R. Autoencoder for words // Neurocomputing. 2014. V. 139. P. 84–96. doi: 10.1016/j.neucom.2013.09.055Oh M., Zhang L. DeepMicro: deep representation learning for disease prediction based on microbiome data // Sci. Rep. 2020. V. 10. No. 1. Article No. 6026. doi: 10.1038/ s41598-020-63159-5Cuomo S., de Rosa M., Piccialli F., Pompameo L., Vocca V. A numerical approach for soil microbiota growth prediction through physics-informed neural network // Appl. Numer. Math. 2024. V. 207. P. 97–110. doi: 10.1016/j.Papoutsoglou G., Tarazona S., Lopes M.B., Klam- msteiner T., Ibrahimi E., Eckenberger J., Novielli P., Tonda A., Simeon A., Shigdel R., Béreux S., Vitali G., Tangaro S., Lahti L., Temko A., Claesson M.J., Berland M. Machine learning approaches in microbiome research: challenges and best practices // Front. Microbiol. 2023. V. 14. Article No. 1261889. doi: 10.3389/fmicb.2023.1261889Deng Z., Zhang J., Li J., Zhang X. Application of deep learning in plant–microbiota association analysis // Front. Genet. 2021. V. 12. Article No. 697090. doi: 10.3389/ fgene.2021.697090Zhao B., Jin W., Del Ser J., Yang G. ChatAgri: Ex- ploring potentials of ChatGPT on cross-linguistic agricul- tural text classification // Neurocomputing. 2023. V. 557. Article No. 126708. doi: 10.1016/j.neucom.2023.126708Popova L.V., Gorshkova N.V., Shaldokhina S.Yu. The introduction of Agriculture technology 4.0: conditions and forecasts // Bulletin of the Adyghe State University, Series “Economics”. 2019. No. 1. P. 83–89 (in Russian).Zayats O.A., Nazarova Yu.N., Strizhakova E.A., Penkova R.I. Big Data technologies in agriculture // Fun- damental research. 2022. No. 7. P. 35–40 (in Russian). doi: 10.17513/fr.43280Cravero A., Pardo S., Sepúlveda S., Muñoz L. Chal- lenges to use machine learning in agricultural Big Data: a systematic literature review // Agronomy. 2022. V. 12. No. 3. Article No. 748. doi: 10.3390/agronomy12030748Raevskaya E.G. Introducing artificial intelligence in Chinese agriculture (review) // Agrarnaya nauka Euro- Severo-Vostoka. 2024. V. 25. No. 5. P. 739–753 (in Rus- sian). doi: 10.30766/2072-9081.2024.25.5.739-753Fenu G., Malloci F.M. DSS LANDS: a decision support system for agriculture in Sardinia // HighTech and Innovation Journal. 2020. V. 1. No. 3. P. 129–135. doi: 10.28991/HIJ-2020-01-03-05Folorunso O., Ojo O., Busari M., Adebayo M., Joshua A., Folorunso D., Ugwunna C.O., Olabanjo O., Olabanjo O. Ex- ploring machine learning models for soil nutrient properties prediction: a systematic review // Big Data Cogn. Comput. 2023. V. 7. No. 2. Article No. 113. doi: 10.3390/bdcc7020113Shen Y., Song K., Tan X., Li D., Lu W., Zhuang Y. HuggingGPT: solving AI tasks with ChatGPT and its friends in Hugging Face // Advances in Neural Information Processing Systems: proceedings of the 37th conference on neural information processing systems. 2024. V. 36. P. 38154–38180. doi: 10.52202/075280-1657Zhu H., Qin S., Su M., Lin C., Li A., Gao J. Har- nessing large vision and language models in agriculture: a review // Front. Plant Sci. 2025. V. 16. Article No. 1579355. doi: 10.3389/fpls.2025.1579355Radford A., Kim J.W., Xu T., Brockman G., McLeavey C., Sutskever I. Robust speech recognition via large-scale weak supervision // Proceedings of the 40th International Conference on Machine Learning. Honolulu, 2023. V. 202. P. 28492–28518.Ren Y., Ruan Y., Tan X., Qin T., Zhao S., Zhao Z., Liu T.Y. FastSpeech: Fast, robust and controllable text to speech // Advances in neural information processing systems: proceedings of the 33rd conference on neural information processing systems. Vancouver, 2019. V. 32. No. 285. P. 3171–3180.