The paper is devoted to the task of searching for mentions of green practices in social media texts. The relevance of this task is dictated by the need to expand existing knowledge about the use of green practices in society and the spread of existing green practices. This paper uses a text corpus consisting of the texts published on the environmental communities of the VKontakte social network. The corpus is equipped with an expert markup of the mention of nine types of green practices. As part of this work, a semi-automatic approach is proposed to the collection of additional texts to reduce the class imbalance in the corpus. The approach includes the following steps: detecting the most frequent words for each practice type; automatic collecting texts in social media that contain the detected frequent words; expert verification and filtering of collected texts. The four machine learning models are compared to find the mentions of green practices on the two variants of the corpus: original and augmented using the proposed approach. Among the listed models, the highest averaged F1-score (81.32%) was achieved by Conversational RuBERT fine-tuned on the augmented corpus. Conversational RuBERT model was chosen for the implementation of the application prototype. The main function of the prototype is to detect the presence of the mention of nine types of green practices in the text. The prototype is implemented in the form of the Telegram chatbot.

This study analyzes the forest flammability hazard in the south of Tyumen Oblast (Western Siberia, Russia) and identifies variation patterns in fire areas depending on weather and climate characteristics in 2008–2023. Using correlation analysis, we proved that the area of forest fires is primarily affected by maximum temperature, relative air humidity, and the amount of precipitation, as well as by global climate change associated with an increase in carbon dioxide in the atmosphere and the maximum height of snow cover. As a rule, a year before the period of severe forest fires in the south of Tyumen Oblast, the height of snow cover is insignificant, which leads to insufficient soil moisture in the following spring, less or no time for the vegetation to enter the vegetative phase, and the forest leaf floor remaining dry and easily flammable, which contributes to an increase in the fire area. According to the estimates of the CMIP6 project climate models under the SSP2-4.5 scenario, by the end of the 21st century, a gradual increase in the number of summer temperatures above 35 °C is expected, whereas the extreme SSP5-8.5 scenario forecasts the tripling in the number of such hot days. The forecast shows an increase of fire hazardous conditions in the south of Tyumen Oblast by the late 21st century, which should be taken into account in the territory’s economic development.

Balyk river basin for the period 2006–2017 using ArcGIS Pro statistical analysis tools are presented in this article. The information basis of the research is the local environment monitoring data of license areas of Ugra, Khanty-Mansiysk Autonomous Okrug, RF. The research was implemented in two stages. At the first stage, pollution hot spots were revealed basing on the calculation of local Getis-Ord Gi* index for each year. The calculation was made taking into account the mutual location of sampling points and value of the neighborhood. At the second stage hot spots genesis for 12 years was analyzed via modelling space-and-time cube. Clustering time series of hydrocarbons average annual concentration according to the Getis-Ord Gi* indicator made it possible to determine the places of one-off pollution, most likely associated with oil spills, and to track pollutants transportation along the current. The location of the increasing river ecosystem pollution was also determined. The obtained results enable bringing out basic zones of permanent high hydrocarbon concentrations and places of periodic discharges into the river basin.

Proceedings of the International conference

The article is focused on some features of the landscape structure of the Kuchak Carbon landfill in the Tyumen region. The research area is located 35 km northeast of Tyumen City in the subtaiga subzone and covers the area of 106.7 km2. As part of the research, the authors have complied a landscape map using the QGIS freely distributed geographic information system (version 3.32). Eight types of terrain have been identified within the research area: terraces (85 landscape units), mineral islands (one landscape unit), lake terraces (23 landscape units), raised bogs (one landscape unit), mesotrophic bogs (five landscape units), lowland eutrophic swamps (nine landscape units), and floodplains (one landscape unit). The study also revealed anthropogenic landscapes (ten units). The information obtained as a result of inventory and subsequent mapping of landscapes on the morphological structure of natural complexes may serve as the basis for further spatial modeling of ecological processes at the Carbon polygon. A promising line of further research is the integration of the landscape approach and the analysis of special parameters, including measurements of radon volumetric activity in soil, greenhouse gas fluxes, and other biophysical indicators. The findings testify to the efficiency of GIS technologies in studying the spatial organization of landscape complexes in terms of the carbon balance monitoring. В статье представлены результаты исследования ландшафтной структуры территории карбонового полигона «Кучак» (Тюменская область). Район исследований расположен в подтайге в южной части Нижнетавдинского района на площади 106,7 км². Использованная методика ландшафтного картографирования включает тематическое дешифрирование данных дистанционного зондирования Земли и полевые исследования. В качестве основных использованы типологические единицы классификации – типы местности и виды урочищ. В результате проведенных исследований идентифицировано восемь типов местности (включая 135 видов урочищ): террасовый (85), минерально-островной (1), приозерно-террасовый (23), верховых болот (1), мезотрофных болот (5), низинных болот (9), пойменный (1) и антропогенные ландшафты (10). Полученные данные ландшафтной инвентаризации составляют основу для пространственного моделирования экологических процессов на карбоновом полигоне. Перспективным направлением дальнейших исследований является интеграция ландшафтного подхода с анализом специализированных параметров, включая измерения объемной активности радона в почвах, потоков парниковых газов и других биофизических показателей. Проведенное исследование демонстрирует эффективность применения ГИС-технологий для изучения пространственной организации природных комплексов в контексте мониторинга углеродного баланса.

Proceedings of the International conference