Operational Mapping of Salinization Areas in Agricultural Fields Using Machine Learning Models Based on Low-Altitude Multispectral Images

• Published in: Drones (Basel) Vol. 7; no. 6; p. 357
• Main Authors: Mukhamediev, Ravil, Amirgaliyev, Yedilkhan, Kuchin, Yan, Aubakirov, Margulan, Terekhov, Alexei, Merembayev, Timur, Yelis, Marina, Zaitseva, Elena, Levashenko, Vitaly, Popova, Yelena, Symagulov, Adilkhan, Tabynbayeva, Laila
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-06-2023
• Subjects: Agricultural land; Agricultural production; Algorithms; Arable land; Artificial intelligence; Cameras; Cloud cover; Crop yield; Drone aircraft; Electrical resistivity; Environmental conditions; Feature selection; Flowers & plants; Genetic algorithms; Irrigation; Landsat satellites; LightGBM; Low altitude; Machine learning; Mapping; Remote sensing; Salinity; Soil layers; soil salinity; Soils, Salts in; spectral indexes; Support vector machines; unmanned aerial vehicle; Unmanned aerial vehicles; Vegetation; XGBoost; Kazakhstan; Mongolia; China
• ISSN: 2504-446X; 2504-446X
• DOI: 10.3390/drones7060357

Salinization of cultivated soil is an important negative factor that reduces crop yields. Obtaining accurate and timely data on the salinity of soil horizons allows for planning the agrotechnical measures to reduce this negative impact. The method of soil salinity mapping of the 0–30 cm layer on irrigated arable land with the help of multispectral data received from the UAV is described in this article. The research was carried out in the south of the Almaty region of Kazakhstan. In May 2022, 80 soil samples were taken from the ground survey, and overflight of two adjacent fields was performed. The flight was carried out using a UAV equipped with a multispectral camera. The data preprocessing method is proposed herein, and several machine learning algorithms are compared (XGBoost, LightGBM, random forest, support vector machines, ridge regression, elastic net, etc.). Machine learning methods provided regression reconstruction to predict the electrical conductivity of the 0–30 cm soil layer based on an optimized list of spectral indices. The XGB regressor model showed the best quality results: the coefficient of determination was 0.701, the mean-squared error was 0.508, and the mean absolute error was 0.514. A comparison with the results obtained based on Landsat 8 data using a similar model was performed. Soil salinity mapping using UAVs provides much better spatial detailing than satellite data and has the possibility of an arbitrary selection of the survey time, less dependence on the conditions of cloud cover, and a comparable degree of accuracy of estimates.