. Soil aggregate stability is crucial for maintaining the arrangement of solid particles and pore space in the soil, even under mechanical stresses. Traditional direct measurements of soil aggregate stability are time-consuming and expensive. This study aimed to spatially predict the soil aggregate stability indices, including the mean weight diameter of aggregates, the geometric mean diameter of aggregates, and the percentage of water stable aggregates, using five machine learning models and environmental covariates in the framework of digital soil mapping. A total of 100 samples were collected from the surface layer (0-15 cm) of soils in the Aji-Chai watershed, northwestern Iran, and their SAS indices were determined by standard laboratory methods. Four scenarios (S) were employed to evaluate the most influencing auxiliary variables, including (S 1 ): topographic attributes, (S 2 ): topographic attributes + remote sensing data, (S 3 ): S 2 + thematic maps (geology, land use/cover maps), and (S 4 ): S 3 + selected soil properties. Among the various machine learning models, the random forest showed exceptional performance and reduced uncertainty for S 4 , compared to the other machine learning models and desired scenarios. The coefficient of deter - mination, concordance correlation coefficient, and normalized root mean squared error values of the random forest model were 0.86, 0.87, and 31.42% for mean weight diameter; 0.80, 0.84, and 31.59% for geometric mean diameter; and 0.54, 0.68, and 20.75% for water stable aggregates, respectively. Additionally, properties such as soil organic matter and clay, followed by remote sensing data, demonstrated the highest relative importance when compared to the other covariates in predicting the soil aggregate stability indices. In conclusion, the random forest ML-based model seems to be able to accurately predict soil aggregate stability indices at the watershed scale. The generated maps can serve as a valuable baseline for land use planning and decision-making. These findings contribute to the scientific understanding of soil physical quality indicators and their application in sustainable land management practices.
.即使在机械应力的作用下,土壤集料的稳定性对于保持土壤中固体颗粒和孔隙的排列也至关重要。传统的土壤集料稳定性直接测量耗时且昂贵。本研究旨在数字土壤制图框架下,利用五种机器学习模型和环境协变量,从空间上预测土壤团聚体稳定性指数,包括团聚体平均重量直径、团聚体几何平均直径和水稳定团聚体百分比。从伊朗西北部阿吉-柴流域的土壤表层(0-15 厘米)共采集了 100 个样本,并通过标准实验室方法测定了其 SAS 指数。采用四种方案(S)来评估影响最大的辅助变量,包括(S 1):地形属性;(S 2):地形属性 + 遥感数据;(S 3):S 2 + 专题地图(地理信息系统):S 2 + 专题地图(地质、土地利用/覆盖图),以及 (S 4 ):S 3 + 选定的土壤特性。在各种机器学习模型中,与其他机器学习模型和理想方案相比,随机森林在 S 4 方面表现出卓越的性能,并降低了不确定性。随机森林模型的判定系数、一致性相关系数和归一化均方根误差值分别为:平均重量直径 0.86%、0.87% 和 31.42%;几何平均直径 0.80%、0.84% 和 31.59%;水稳定团聚体 0.54%、0.68% 和 20.75%。此外,在预测土壤团聚体稳定性指数方面,与其他协变量相比,土壤有机质和粘土等属性的相对重要性最高,其次是遥感数据。总之,基于随机森林 ML 的模型似乎能够准确预测流域尺度的土壤团聚体稳定性指数。生成的地图可作为土地利用规划和决策的宝贵基准。这些发现有助于科学理解土壤物理质量指标及其在可持续土地管理实践中的应用。
{"title":"Machine learning-based soil aggregation assessment under four scenarios in northwestern Iran","authors":"Parastoo Nazeri, S. Ayoubi, Hossein Khademi, Farideh Abbaszadeh Afshar, Rouhollah Mousavi","doi":"10.31545/intagr/188506","DOIUrl":"https://doi.org/10.31545/intagr/188506","url":null,"abstract":". Soil aggregate stability is crucial for maintaining the arrangement of solid particles and pore space in the soil, even under mechanical stresses. Traditional direct measurements of soil aggregate stability are time-consuming and expensive. This study aimed to spatially predict the soil aggregate stability indices, including the mean weight diameter of aggregates, the geometric mean diameter of aggregates, and the percentage of water stable aggregates, using five machine learning models and environmental covariates in the framework of digital soil mapping. A total of 100 samples were collected from the surface layer (0-15 cm) of soils in the Aji-Chai watershed, northwestern Iran, and their SAS indices were determined by standard laboratory methods. Four scenarios (S) were employed to evaluate the most influencing auxiliary variables, including (S 1 ): topographic attributes, (S 2 ): topographic attributes + remote sensing data, (S 3 ): S 2 + thematic maps (geology, land use/cover maps), and (S 4 ): S 3 + selected soil properties. Among the various machine learning models, the random forest showed exceptional performance and reduced uncertainty for S 4 , compared to the other machine learning models and desired scenarios. The coefficient of deter - mination, concordance correlation coefficient, and normalized root mean squared error values of the random forest model were 0.86, 0.87, and 31.42% for mean weight diameter; 0.80, 0.84, and 31.59% for geometric mean diameter; and 0.54, 0.68, and 20.75% for water stable aggregates, respectively. Additionally, properties such as soil organic matter and clay, followed by remote sensing data, demonstrated the highest relative importance when compared to the other covariates in predicting the soil aggregate stability indices. In conclusion, the random forest ML-based model seems to be able to accurately predict soil aggregate stability indices at the watershed scale. The generated maps can serve as a valuable baseline for land use planning and decision-making. These findings contribute to the scientific understanding of soil physical quality indicators and their application in sustainable land management practices.","PeriodicalId":13959,"journal":{"name":"International Agrophysics","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141664965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gholamhossein Shahgholi, Ehsan Aghdamifar, Abdolmajid Moinfar, M. Szymanek, Wojciech Tanaś
. In order to determine the relationships between the soil stiffness constants of cohesive modulus of deformation, friction modulus of deformation and soil constant value and the rolling resistance, a series of tests was conducted using two types of loam and clay loam soil textures at four moisture contents of 10, 20, 30 and 40% and five loading speeds of 1, 2, 3, 4 and 5 mm s –1 . The results showed that all of the independent fac - tors had a significant effect on the soil stiffness constants, so with increases in moisture content and loading speed, the soil stiffness constants of cohesive modulus of deformation, friction modulus of deformation and soil constant value varied significantly. The highest cohesive modulus of deformation and friction modulus of deformation values were obtained at a moisture content of 10% and loading speed of 5 mm s –1 in a clay loam soil. All param - eters were significant in calculating the rolling resistance using Bekkers’ relationship. With increases in soil moisture content, the rolling resistance increased, while increasing the loading speed reduced the rolling resistance significantly. In general, the highest rolling resistance value of 16 887.1 N was obtained at a moisture content value of 40% and a loading speed of 1 mm s –1 in loam soil.
.为了确定土壤的内聚变形模量、摩擦变形模量和土壤恒定值等刚度常数与滚动阻力之间的关系,在 10%、20%、30% 和 40%四种含水量和 1、2、3、4 和 5 mm s -1 五种加载速度下,使用两种壤土和粘壤土质地进行了一系列试验。结果表明,所有独立因素都对土壤刚度常数有显著影响,因此随着含水量和加载速度的增加,土壤刚度常数(内聚变形模量、摩擦变形模量和土壤常数值)也有显著变化。在含水量为 10%、加载速度为 5 mm s -1 的粘壤土中,内聚变形模量和摩擦变形模量的值最高。所有参数在使用 Bekkers 关系计算滚动阻力时都很重要。随着土壤含水量的增加,滚动阻力也随之增加,而加载速度的增加则显著降低了滚动阻力。一般来说,在含水量为 40% 和加载速度为 1 mm s -1 的壤土中,滚动阻力的最高值为 16 887.1 N。
{"title":"Evaluation of the changes in Bekker's parameters and their use in determining\u0000the rolling resistance","authors":"Gholamhossein Shahgholi, Ehsan Aghdamifar, Abdolmajid Moinfar, M. Szymanek, Wojciech Tanaś","doi":"10.31545/intagr/187017","DOIUrl":"https://doi.org/10.31545/intagr/187017","url":null,"abstract":". In order to determine the relationships between the soil stiffness constants of cohesive modulus of deformation, friction modulus of deformation and soil constant value and the rolling resistance, a series of tests was conducted using two types of loam and clay loam soil textures at four moisture contents of 10, 20, 30 and 40% and five loading speeds of 1, 2, 3, 4 and 5 mm s –1 . The results showed that all of the independent fac - tors had a significant effect on the soil stiffness constants, so with increases in moisture content and loading speed, the soil stiffness constants of cohesive modulus of deformation, friction modulus of deformation and soil constant value varied significantly. The highest cohesive modulus of deformation and friction modulus of deformation values were obtained at a moisture content of 10% and loading speed of 5 mm s –1 in a clay loam soil. All param - eters were significant in calculating the rolling resistance using Bekkers’ relationship. With increases in soil moisture content, the rolling resistance increased, while increasing the loading speed reduced the rolling resistance significantly. In general, the highest rolling resistance value of 16 887.1 N was obtained at a moisture content value of 40% and a loading speed of 1 mm s –1 in loam soil.","PeriodicalId":13959,"journal":{"name":"International Agrophysics","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141269326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}