نوع مقاله : مقاله پژوهشی
نویسندگان
1 بخش علوم و مهندسی خاک، دانشکده کشاورزی-دانشگاه شهیدباهنر کرمان
2 عضو هیأت علمی گروه مهندسی علوم خاک، پردیس کشاورزی و منابع طبیعی دانشگاه تهران
3 گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشکدگان کشاورزی و منابع طبیعی، دانشگاه تهران، کرج، ایران
چکیده
کلیدواژه‌ها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Soil salinity and sodicity are affecting soils in arid and semi-arid regions, reducing soil fertility and leading to land degradation, posing threats to the sustainable development of resources. Creating maps of these soil variables throughout soil profile is crucial for effective land management. This study aims to investigate the spatial variability of soil salinity and sodicity in a part of the arid and semi-arid region of Abyek. Three critical depths for the cultivation of important agricultural products (0-50, 0-100, and 0-150 cm) were examined. The models were conducted using 281 soil data and environmental covariates. The modeling and prediction of soil electrical conductivity (salinity) and sodium absorption ratio (sodicity) were performed using four machine learning models: Cubist, random forest, artificial neural network, and XGBoost. The final maps were derived from a simple weighted ensemble model. The model uncertainty was assessed using bootstrapping with 50 repetitions. The results indicated high spatial variability of EC and SAR (exceeding 35%), with an increase from north to south of the region and from surface to deeper soil layers. Results showed that topography, climate, and vegetation are primary controlling factors of spatial distribution of soil salinity and alkalinity. R² for the final models predicting both EC and SAR across all three depths ranged from 0.61 to 0.81, demonstrating the models’ high efficiency, increasing with depth. The highest level of model uncertainty was observed in the southern parts of the region with high variability in EC and SAR values in short distances, fewer soil observations, and less topography, which was lower for models predicting sodium content at all depths compared to salinity. More than 65% of the area was non-saline, while non-alkaline areas covered 70% of it. Acquiring these maps represents a significant step towards improving land management practices based on the land’s potential.
کلیدواژه‌ها [English]
Soil salinity and sodicity are critical environmental issues that pose significant challenges to sustainable agricultural development and global food security. These phenomena represent the primary soil degradation processes in arid and semi-arid regions, which encompass approximately 20% of Iran's land and are expanding at an increasing rate. Creating maps of these soil variables throughout soil profile is crucial for effective land management. Digital Soil Mapping (DSM) is a powerful tool in this context and has been globally employed to predict the spatial distribution of soil salinity and sodicity. Given the vertical variations of these characteristics along the soil profile due to the accumulation of salts at different depths and their impact on the growth of plant species with superficial, semi-deep, and deep roots, this study aims to investigate the changes in salinity and sodicity of soils in the arid and semi-arid region of Abyek at three management depths: 0-50 cm, 0-100 cm, and 0-150 cm.
To achieve the objectives of this study, electrical conductivity (EC) and sodium absorption ratio (SAR) data from different layers of 281 soil profiles were utilized to model and predict soil salinity and sodicity, respectively. The values of these two properties were averaged using vertical weighted interpolation functions at three depths: 0-50 cm, 0-100 cm, and 0-150 cm. Considering the conditions of the study area and based on expert opinion, nine environmental covariates with a spatial resolution of 12.5 meters were used as representatives of the scorpan factors for modeling and spatial prediction of these two soil properties. The modeling was conducted using different machine learning (ML) models including cubist, random forest, artificial neural network, gradient boosting, and their simple weighted combination. The models were evaluated using common indicators, including the coefficient of determination (R²), root mean square error (RMSE), and Lin's concordance correlation coefficient (LCCC), and their uncertainty was assessed based on the bootstrapping method with 50 replicates.
The results indicated high spatial variability of EC and SAR (exceeding 35%), with an increase from north to south of the region and from surface to deeper soil layers. This can be attributed to the substantial variations in climate, soil characteristics, and differing management practices. Additionally, the investigations showed that topography, climate, and vegetation are primary controlling factors of spatial distribution of soil salinity and alkalinity. R² for the final models predicting both EC and SAR across all three depths ranged from 0.61 to 0.81, demonstrating the models’ high efficiency, increasing with depth. The highest level of model uncertainty was observed in the southern parts of the region with high variability in EC and SAR values in short distances, fewer soil observations, and less topography, which was lower for models predicting sodium content at all depths compared to salinity. More than 65% of the area was non-saline, while non-alkaline areas covered 70% of it.
In general, the findings of this study validate the use of digital soil mapping methods, particularly the combination of different models, as an effective approach for creating accurate maps of soil salinity and sodicity in the arid and semi-arid regions of Abyek. Acquiring these maps represents a significant step towards improving land management practices based on the land’s potential. The results, presented as soil salinity and sodicity maps along with their uncertainty maps can serve as valuable guides for managers, soil and water experts, and land users in future land use planning. Additionally, this information can be utilized for soil conservation, especially in the southern parts of the region. Finally, the method employed in this study can be applied to other arid and semi-arid regions of the country that face issues of soil salinization and alkalinization.
Conceptualization, A.J., F.S. and Z.R.; methodology, A.J., and Z.R.; software, A.J.; validation, A.J., and Z.R.; formal analysis, A.J.; investigation, A.J., F.S. and Z.R.; resources, A.J. and F.S.; data curation, F.S.; writing—original draft preparation, A.J.; writing—review and editing, A.J., F.S. and Z.R.; visualization, A.J., F.S. and Z.R.; supervision, F.S.; project administration, F.S.. All authors have read and agreed to the published version of the manuscript.
Not applicable.
The authors would like to thank the University of Tehran for support of the present study.
The authors avoided data fabrication, falsification, plagiarism, and misconduct.
The author declares no conflict of interest.
)