Issue |
E3S Web Conf.
Volume 494, 2024
International Conference on Ensuring Sustainable Development: Ecology, Energy, Earth Science and Agriculture (AEES2023)
|
|
---|---|---|
Article Number | 02013 | |
Number of page(s) | 9 | |
Section | Earth Science and Fuel and Energy Complex | |
DOI | https://doi.org/10.1051/e3sconf/202449402013 | |
Published online | 22 February 2024 |
Ensemble data mining methods for assessing soil fertility
1 National Research University "Tashkent Institute of Irrigation and Agricultural Mechanization Engineers institute", Tashkent, 100000, Uzbekistan
2 Gulistan State University, Associate professor at the department of "Applied Mathematics and Information Technologies", micro-district 4, Gulistan, Sir-Darya region, 120100, Uzbekistan
3 Tashkent University of Information Technologies named after Mukhammad al-Khwarizmi, 108, Amir Temur ave., Tashkent, 100200, Uzbekistan
* Corresponding author: dziyadullaev@inbox.ru
The application of ensemble data mining methods in assessing soil fertility and the use of methods such as random forest, gradient boosting and bagging to determine the level of soil fertility are examined in the article. Ensemble methods combine multiple machine learning models to improve the accuracy and stability of estimates. These methods consider various factors, including soil chemistry, climatic conditions, and historical crop yield data. The study also examines the application of the decision tree algorithm and such methods as random forest and bagging to estimate soil fertility. Performance results of these methods are provided using precision, recall, and F1-measure metrics. The results obtained show the high performance of ensemble methods in the task of classifying soil fertility levels. They have important implications for agricultural farms and research organizations that are working to improve soil management and increase crop yields.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.