Automatic Knowledge Extraction from Environmental Reports with Reference to Time and Spatial Coordinates of Water Bodies
DOI:
https://doi.org/10.31649/1997-9266-2025-180-3-101-110Keywords:
knowledge mining, SPO-triplets, artificial intelligence, data georeferencing, water array, large language models, Retrieval-Augmented GenerationAbstract
The paper presents a new method for automatically extracting environmental knowledge from reports and news texts related to facts about the state of river waters or their pollution. Knowledge extraction is carried out taking into account the binding of the obtained facts to the spatial coordinates of specific water bodies and time intervals. The relevance of the work is due to the significant availability of such environmental data in the news, websites of institutions, and social media, and the need for their quick and accurate processing. The proposed method combines the detection of facts about the state of waters or their pollution, recognition of geographical names from the text and headlines, as well as the determination of time features by analyzing the hierarchical structure of the document. The method optimizes the contextual-semantic criterion, which maximizes the completeness and probability of detecting all existing connections between key phrases in the text of facts, time periods and water bodies and, at the same time, minimizes the number of false positive connections between them, by formalizing the connections in the form of “subject–predicate–object” (SPO) triplets and using the Jaccard measure to find the degree of similarity between the lists of key phrases that characterize these facts and water bodies. Knowledge extraction is based on identifying and using the hierarchical structure of the document, using large language models, and actualization the knowledge base with information with Retrieval-Augmented Generation (RAG) for regular knowledge update and binding to the time intervals and spatial coordinates. The result is a structured knowledge base in the form of “fact – water body – time interval” triplets, which can be used to analyze the dynamics of water status, identify trends, and make management decisions to improve the state of surface waters.
The result of applying the proposed method is presented using the example of the annual report on the activities of the Southern Booh River Basin Water Resources Management for 2019, which illustrates its efficiency.
References
Верховна Рада України, «Водний Кодекс України», Постанова ВР № 214/95-ВР від 06.06.95, Відомості Верховної Ради (ВВР), 1995, № 24, ст. 189). [Електронний ресурс]. Режим доступу: http://zakon2.rada.gov.ua/laws/show /213/95-%D0%B2%D1%80 .
Кабінет Міністрів України, Водна стратегія України на період до 2050 року. Розпорядження від 9 грудня 2022 р. № 1134-р. [Електронний ресурс]. Режим доступу: https://zakon.rada.gov.ua/laws/show/1134-2022-%D1%80#Text .
Водна Рамкова Директива ЄС 2000/60/ЄС. Основні терміни та їх визначення. Київ, Україна, 2006, 240 с. [Електронний ресурс]. Режим доступу: http://dbuwr.com.ua/docs/Waterdirect.pdf .
J. Zhu, “A Temporal Knowledge Graph Generation Dataset Supervised Distantly by Large Language Models,” Scientific Data, no. 12, p. 734, 2025. [Electronic resource]. Available: https://doi.org/10.1038/s41597-025-05062-0 .
К. Salmas et al., “Extracting Geographic Knowledge from Large Language Models: An Experiment,” Workshop LM-KBC, 2023, [Electronic resource]. Available: https://lm-kbc.github.io/workshop2023/proceedings/13_Salmas.pdf .
М. Gritta et al., “What’s missing in geographical parsing?” Springer Nature Link. [Electronic resource]. Available: https://link.springer.com/article/10.1007/s10579-017-9385-8 .
A. Halterman “Mordecai 3: A Neural Geoparser,” arXiv, 2023, [Electronic resource]. Available: https://arxiv.org/pdf/2303.13675 .
Hanwen Zheng, et al., “A Comprehensive Survey on Document-Level Information Extraction,” in Proceedings of the Workshop on the Future of Event Detection (FuturED), 2024, pp. 58-72, USA: Association for Computational Linguistics. [Electronic resource]. Available: https://aclanthology.org/2024.futured-1.6.pdf .
J. Dagdelen, et al., “Structured information extraction from scientific text with large language models,” Nature Commun. no. 15, pp.1418, 2024. [Electronic resource]. Available: https://doi.org/10.1038/s41467-024-45563-x .
В. Б. Мокін, К. О. Бондалєтов, Є. М. Крижановський, і В. О. Караваєв, «Метод аугментації текстів про стан масивів вод на основі інтелектуальної прив’язки до багатозв’язних геоінформаційних систем іменованих сутностей», Вісник Вінницького політехнічного інституту, № 3, с. 55-65, 2023. https://doi.org/10.31649/1997-9266-2023-168-3-55-65 .
D. Dessí, et al., “CS-KG 2.0: A Large-scale Knowledge Graph of Computer Science,” Scientific Data, no. 12, pp. 964, 2025. [Electronic resource]. Available: https://doi.org/10.1038/s41597-025-05200-8 .
Yunyi Zhang, “Automated Mining of Structured Knowledge from Text in the Era of Large Language Models,” in KDD‘24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. [Electronic resource]. Available: https://doi.org/10.1145/3637528.3671469 .
Haoran Luo, et al., “Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction,” Advances in Neural Information Processing Systems 37 (NeurIPS), 2024. [Electronic resource]. Available: https://proceedings.neurips.cc/paper_files/paper/2024/hash/Abstract-Conference.html (date of access: 06.06.2025) .
R. Bommasani, et al. “On the Opportunities and Risks of Foundation Models,” Computer Science, Machine Learning, 2021. [Electronic resource]. Available: https://arxiv.org/abs/2108.07258 .
К. Бондалєтов, і В. Мокін, « Інтелектуальна автоматизація геоприв’язки повідомлень з соцмереж до масивів вод за допомогою зваженої Jaccard-міри,» ВНТКП ВНТУ. Факультет інтелектуальних інформаційних технологій та автоматизації ВНТУ, Вінниця, 24-27 березня 2025. [Електронний ресурс]. Режим доступу: https://conferences.vntu.edu.ua/index.php/all-fksa/all-fksa-2025/paper/view/23298/19275 .
Річний звіт про діяльність басейнового управління водних ресурсів річки Південний Буг з питань управління водними ресурсами за 2019 рік, Вінниця. Україна: БУВР, 2019.
Downloads
-
pdf (Українська)
Downloads: 9
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
