Development of a Model for Soil Salinity Segmentation Based on Remote Sensing Data and Climate Parameters
Abdikerimova G. Khamitova D. Kassymova A. Bissengaliyeva A. Nurova G. Aitimov M. Shynbergenov Y.A. Yessenova M. Bekbayeva R.
May 2025Multidisciplinary Digital Publishing Institute (MDPI)
Algorithms
2025#18Issue 5
The paper presents a hybrid machine learning model for the spatial segmentation of soils by salinity using multispectral satellite data from Sentinel-2 and climate parameters of the ERA5-Land model. The proposed method aims to solve the problem of accurate soil cover segmentation under climate change and high spatial heterogeneity of data. The approach includes the sequential application of unsupervised learning algorithms (K-Means, hierarchical clustering, DBSCAN), the XGBoost model, and a multitasking neural network that performs simultaneous classification and regression. At the first stage, pseudo-labels are formed using K-Means, then a probabilistic assessment of object membership in classes and ensemble voting of clustering algorithms are carried out. The final model is trained on an extended feature space and demonstrates improved results compared to traditional approaches. Experiments on a sample of 33,624 observations (23,536—training sample, 10,088—test sample) showed an increase in the Silhouette Score value from 0.7840 to 0.8156 and a decrease in the Davies–Bouldin Score from 0.3567 to 0.3022. The classification accuracy was 99.99%, with only one error in more than 10,000 test objects. The results confirmed the proposed method’s high efficiency and applicability for remote monitoring, environmental analysis, and sustainable land management.
ensemble clustering , ERA5-Land , multi-task neural network , remote sensing , Sentinel-2 , soil salinity segmentation , XGBoost
Text of the article Перейти на текст статьи
Department of Information Systems, L.N. Gumilyov Eurasian National University, Astana, 010000, Kazakhstan
Department of Information Technology, Zhangir Khan University, Uralsk, 090000, Kazakhstan
Academy of Public Administration Under the President of the Republic of Kazakhstan in the Kyzylorda Region, Kyzylorda, 120000, Kazakhstan
Faculty of Natural Sciences, Educational Program of Informatics and Information and Communication Technologies, Korkyt Ata Kyzylorda University, Kyzylorda, 120000, Kazakhstan
Kyzylorda Regional Branch Within the Academy of Public Administration Under the President of the Republic of Kazakhstan, Kyzylorda, 120000, Kazakhstan
Department of Automation, Information Technology, Urban Development of Non-Profit Limited Company Semey University Named After Shakarim, Semey, 070000, Kazakhstan
Department of Information Systems
Department of Information Technology
Academy of Public Administration Under the President of the Republic of Kazakhstan in the Kyzylorda Region
Faculty of Natural Sciences
Kyzylorda Regional Branch Within the Academy of Public Administration Under the President of the Republic of Kazakhstan
Department of Automation
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026