Mapping soil organic carbon and total nitrogen in croplands of the Corn Belt of Northeast China based on geographically weighted regression kriging model

Li, Xiaoyan; Shang, Beibei; Wang, Dongyan; Wang, Zongming; Wen, Xin; Kang, Yingdong

doi:10.1016/j.cageo.2019.104392

Cited by 22 publications

(20 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The TN content of topsoil (0-20 cm) ranged from 0.45 to 1.05 g/kg, with an average value of 0.84 ± 0.19 g/kg. The value was more than twice of that in sloping farmland of the Loess Plateau (0.37 g/kg, [21]), less than half of that in East China (1.75 ± 0.43 g/kg, [22]) and about two-thirds of that in corn fields of Northeast China (1.3 ± 0.36 g/kg, [23]).…”

Section: Descriptive Statistics Of Soil Nitrogen Contentmentioning

confidence: 82%

The Influence of Climate, Soil Properties and Vegetation on Soil Nitrogen in Sloping Farmland

et al. 2021

View full text Add to dashboard Cite

Soil nitrogen in farmland ecosystems is affected by climate, soil physical and chemical properties and planting activities. To clarify the effects of these factors on soil nitrogen in sloping farmland quantitatively, the distribution of soil total nitrogen (TN) content, nitrate nitrogen (NO3-N) content and ammonium nitrogen (NH4-N) content at depth of 0–100 cm on 11 profiles of the Luanhe River Basin were analyzed. Meanwhile, soil physical and chemical properties, climatic factors and NDVI (Normalized Difference Vegetation Index) were used to construct a structural equation which reflected the influence mechanism of environmental factors on soil nitrogen concentration. The results showed that TN and NO3-N content decreased with the increase of soil depth in the Luanhe River Basin, while the variation of NH4-N content with soil depth was not obvious. Soil organic carbon (SOC) content, soil pH, soil area average particle size (SMD) and NDVI6 (NDVI of June) explained variation of TN content by 77.4%. SOC was the most important environmental factor contributing to the variation of TN content. NDVI5 (NDVI of May), annual average precipitation (MAP), soil pH and SOC explained 49.1% variation of NO3-N content. Among all environmental factors, only NDVI8 (NDVI of August) had significant correlation with soil NH4-N content, which explained the change of NH4-N content by 24.2%. The results showed that soil nitrogen content in the sloping farmland ecosystem was mainly affected by natural factors such as soil parent material and climate.

show abstract

Section: Descriptive Statistics Of Soil Nitrogen Contentmentioning

confidence: 82%

The Influence of Climate, Soil Properties and Vegetation on Soil Nitrogen in Sloping Farmland

et al. 2021

View full text Add to dashboard Cite

show abstract

“…There are two possible reasons for the poor performance of OK. Above all, the strong local variation of wetland SOCc is related to the changes in extrinsic environmental factors, such as vegetation [36], terrain [15], and climate [16] in this study area. Moreover, the spatial correlation of single type soil samples, which may be controlled by the intrinsic factors (i.e., soil properties), is not obvious when they are sparse on a large scale under low sampling density [37].…”

Section: Advantages Of Ann-ok In Predicting Wetland Soccmentioning

confidence: 78%

“…Three indices used in this study include mean error (ME), root mean square error (RMSE), and correlation coefficient (r) between the measured and predicted parameters. Both the ME and RMSE represent accuracy, uncertainty, and stability, while r denotes the correlation between predicted and measured values [15]. They are computed as follows:…”

Section: Evaluation Of the Accuracy Of Prediction Modelsmentioning

confidence: 99%

“…The application of ANNs could be one of the most effective methods because of its strong performance in characterizing the nonlinear relationships between soil parameters and environmental variables [12,13]. Multisource geospatial data correlated with SOCc, including topographic [14], meteorological [15], and remotely sensed data [16], can be combined to predict SOCc and reveal the relationship between SOCc and environmental variables. For example, Emadi et al reported that a deep neural network method had an excellent performance in predicting soil organic carbon in northern Iran by inputting 105 environmental variables as predictors [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining Artificial Neural Network and Ordinary Kriging to Predict Wetland Soil Organic Carbon Concentration in China’s Liao River Basin

Kang

Mao

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Accurate prediction of wetland soil organic carbon concentration and an understanding of its controlling factors are important for studying regional climate change and wetland carbon cycles; with that knowledge mechanisms can be put in place that are conducive to sustainable ecosystem management for environmental health. In this study, a hybrid approach combining an artificial neural network and ordinary kriging and 103 soil samples at three soil depth ranges (0–30, 30–60, and 60–100 cm) were used to predict wetland soil organic carbon concentration in China’s Liao River Basin. The model evaluation indicated that a combination of artificial neural network and ordinary kriging and limited soil samples achieved good performance in predicting wetland soil organic carbon concentration. Wetland soil organic carbon concentration in the Liao River Basin has apparent spatial and vertical heterogeneities with values decreasing from southeast to northwest and concentrates present mainly in the topsoil (0–30 cm). Mean wetland soil organic carbon concentration values at the three soil depths were 10.43 ± 0.38, 7.93 ± 0.25, and 7.61 ± 0.22 g/kg, respectively, which are smaller than those over other wetland regions in Northeast China. Terrain aspect contributed the most in predicting wetland soil organic carbon concentration at each of the three soil depths, followed by normalized difference vegetation index at 0–30 cm and mean annual precipitation at 30–60 and 60–100 cm. This study provides a framework method and baseline to quantify the soil organic carbon concentration dynamics in response to climatic and anthropogenic drivers.

show abstract

“…Therefore, it is necessary to explore the contribution of remote sensing data to SOC prediction. There have been some studies on SOC prediction based on remote sensing data that achieved good prediction results, especially optical data (e.g., Sentinel-2 [15][16][17][18][19][20][21], Landsat [22][23][24][25][26][27][28], and MODIS satellite data [29][30][31]); their bands cover from visible to short-wave infrared, providing more information. However, the application of optical data is susceptible to weather conditions, especially in the Sichuan Basin where clouds occur most frequently [32], so the available optical data are very limited.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Soil Organic Carbon under Different Land Use Types Using Sentinel-1/-2 Data in a Small Watershed

Wang

Zhang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Soil organic carbon (SOC) is a key property for evaluating soil quality. SOC is thus an important parameter of agricultural soils and needs to be regularly monitored. The aim of this study is to explore the potential of synthetic aperture radar (SAR) satellite imagery (Sentinel-1), optical satellite imagery (Sentinel-2), and digital elevation model (DEM) data to estimate the SOC content under different land use types. The extreme gradient boosting (XGboost) algorithm was used to predict the SOC content and evaluate the importance of feature variables under different land use types. For this purpose, 290 topsoil samples were collected and 49 features were derived from remote sensing images and DEM. Feature selection was carried out to prevent data redundancy. Coefficient of determination (R2), mean absolute error (MAE), mean squared error (MSE), percent root mean squared error (%RMSE), ratio of performance to interquartile range (RPIQ), and corrected akaike information criterion (AICc) were employed for evaluating model performance. The results showed that Sentinel-1 and Sentinel-2 data were both important for the prediction of SOC and the prediction accuracy of the model differed with land use types. Among them, the prediction accuracy of this model is the best for orchard (R2 = 0.86 and MSE = 0.004%), good for dry land (R2 = 0.74 and MSE = 0.008%) and paddy field (R2 = 0.66 and MSE = 0.009%). The prediction model of SOC content is effective and can provide support for the application of remote sensing data to soil property monitoring.

show abstract

Mapping soil organic carbon and total nitrogen in croplands of the Corn Belt of Northeast China based on geographically weighted regression kriging model

Cited by 22 publications

References 45 publications

The Influence of Climate, Soil Properties and Vegetation on Soil Nitrogen in Sloping Farmland

The Influence of Climate, Soil Properties and Vegetation on Soil Nitrogen in Sloping Farmland

Combining Artificial Neural Network and Ordinary Kriging to Predict Wetland Soil Organic Carbon Concentration in China’s Liao River Basin

Prediction of Soil Organic Carbon under Different Land Use Types Using Sentinel-1/-2 Data in a Small Watershed

Contact Info

Product

Resources

About