Mapping soil organic carbon content using multi-source remote sensing variables in the Heihe River Basin in China

Zhou, Tao; Geng, Yajun; Chen, Jie; Liu, Mengmeng; Haase, Dagmar; Lausch, Angela

doi:10.1016/j.ecolind.2020.106288

Cited by 64 publications

(46 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Many studies have demonstrated the effectiveness of this estimation method (Yang et al, 2016;Wang et al, 2020). Although different researches used different modeling methods such as linear models (Razakamanarivo et al, 2011;Xie et al, 2021), nonlinear models (Mondal et al, 2017), and machine learning (Lin et al, 2020;Zhou et al, 2020), the selection of predictor variables was the common foundation of all such methods (Mirchooli et al, 2020). The selection of these predictors can be roughly divided into terrain-related predictors and vegetation-related predictors (Mirchooli et al, 2020;Wang et al, 2020).…”

Section: Choices Of Environmental Variables Of Remote Sensing For Soc and Stn Stocks Estimationsmentioning

confidence: 99%

Estimating the Spatial Distribution of Soil Organic Carbon and Soil Total Nitrogen Stocks by Remote Sensing Methods: A Case Study in a Forest-dominated Alpine Watershed, Western China

wang

Peng

et al. 2021

Preprint

View full text Add to dashboard Cite

Soil organic carbon and soil total nitrogen stocks are important indicators for evaluating soil health and stability. Accurately predicting the spatial distribution of soil organic carbon and total nitrogen stocks is an important basis for mitigating global warming, ensuring regional food security, and maintaining the sustainable development of ecologically fragile areas. On the basis of field sampling data and remote sensing technology, this study divided the topsoil (0–30 cm) into three soil layers of 0–10 cm, 10–20 cm, and 20–30 cm to carry out soil organic carbon and soil total nitrogen stocks estimation experiments in the Qilian Mountains in western China. A multiple linear regression model and a stepwise multiple linear regression model were used to estimate soil organic carbon and soil total nitrogen stocks. A total of 119 topsoil samples and nine remotely sensed environmental variables were collected and used for model development and validation. The results indicated that these two linear regression models showed good performance. The modified soil-adjusted vegetation index (MSAVI), perpendicular vegetation index (PVI), aspect, elevation, and solar radiation were the key environmental variables affecting soil organic carbon and total nitrogen stocks. In topsoil, remote sensing technology could be used to predict the soil properties in layers; however, as the soil depth increased, the performance of the linear regression models gradually decreased.

show abstract

Section: Choices Of Environmental Variables Of Remote Sensing For Soc and Stn Stocks Estimationsmentioning

confidence: 99%

Estimating the Spatial Distribution of Soil Organic Carbon and Soil Total Nitrogen Stocks by Remote Sensing Methods: A Case Study in a Forest-dominated Alpine Watershed, Western China

wang

Peng

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…선형회 귀분석은 적용과 해석이 쉽다는 장점이 있지만, 변수 사용에 대한 제약이 있어 다양한 변수에 의해 비선형적으로 복잡 하게 영향을 받는 토양 탄소 함량을 예측하는 데 정확도가 낮은 경향이 있다 (Franklin, 2005). 이러한 제약을 해결하 고 예측의 정확도를 높이기 위해 최근 기계학습 기반의 Random Forest 모델이 이용되고 있다 (Grimm et al, 2008;Kim and Grunwald, 2016;Nabiollahi et al, 2019;Zhou et al, 2020;Sothe et al, 2022;Zeraatpisheh et al, 2022)…”

Section: Introductionunclassified

Prediction of Soil Organic Carbon Contents of Rice Paddies in South-Western Coastal Area of Korea Using Random Forest Models

Park¹,

Choi²

2022

Korean J. Soil. Sci. Fert.

View full text Add to dashboard Cite

Random forest models (RFM) are useful in predicting the soil carbon (C) contents because RFM predicts soil C with high accuracy under complicated environmental conditions. However, there are very few studies on prediction of soil C using RFM in Korea. Moreover, there is no case study using RFM to predict soil C content of reclaimed tideland (RTL) soils, which have high C sequestration capacity. Therefore, in this study, the applicability of RFM was evaluated using published soil properties data, including soil C and soil variables, for RTL soils located in southwestern coastal areas of Korea. In the present study, RFM was built using the data of 16 variables (e.g., sand, silt, and clay contents, pH, electrical conductivity of saturated soil paste (EC e ), and nutrient concentrations) obtained from five RTLs with similar climate, topography, and vegetation. The 80% of the total data were trained to build the model, and searched optimal hyper parameters were used to improve accuracy. The determination coefficient (R 2 ) of the model was 0.67, and the difference between measured and predicted soil C content was 25.9% on average. However, when the measured values were out of the range of the data trained for building the model or the measured values were close to the minimum or maximum value, the difference between the predicted and measured values became larger (73.9%). The contribution of the independent variables to the prediction of soil C using the model was the greatest (14.9%) for soil NH 4 + concentrations. Meanwhile, the contribution of EC e , which was highly correlated with soil C content, was not detected, suggesting that the importance of the number and range of training data used to build model. Our study shows the possible application of RFM to predict soil C contents of RTL soils in Korea, and further highlights that a large amount of data should be accumulated for high accuracy prediction of soil C using RFM.

show abstract

“…Synthetic aperture radar (SAR) technology has the advantages of all-weather, day and night imaging [33]. Therefore, the spectral range from remote sensing used for SOC prediction is not limited to the visible and infrared; radar can and have also be used [34][35][36]. Recent studies have found that multitemporal SAR data could capture the soil-vegetation relationship to predict soil chemical properties, and its ability depends on capturing vegetation characteristics from remote sensing images that indicate variation of soil properties [37].…”

Section: Introductionmentioning

confidence: 99%

“…Yang and Guo [38] reported fluctuation correlations between the backscattering coefficients of multitemporal Sentinel-1 images and SOC. SAR data have broad application prospects for the prediction of soil properties [33,38], but its application in predicting SOC is still limited and rarely reported in the literature due to its complexity, diversity, and availability (e.g., the preprocessing of SAR data is more complicated and has less information than optical data) [36,39]. The newly released Sentinel satellites developed by the European Space Agency (ESA) have the advantages of short revisit time (Sentinel-1: 6 days; Sentinel-2: 5 days), high spatial resolution (Sentinel-1: 5-20 m; Sentinel-2: 10-60 m), free download, and high-quality physical calibration data.…”

Section: Introductionmentioning

confidence: 99%

“…Land use effects on SOC are related to the land use conversion that has led to the exposure of soils and the rapid decomposition of SOC [42], so the prediction accuracy of SOC content may be affected by land use types. Zhou et al [36], Zhang et al [43], and Paul et al [44] used land use type as a variable to predict SOC content, but the results showed that it did not contribute much to the model. In recent studies, remote sensing data were used to predict SOC content based on multiple land use types, while the results showed that the accuracy of SOC prediction using satellite remote sensing data was lower than that using airborne remote sensing and laboratory reflectance spectra data [19,45].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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 content using multi-source remote sensing variables in the Heihe River Basin in China

Cited by 64 publications

References 88 publications

Estimating the Spatial Distribution of Soil Organic Carbon and Soil Total Nitrogen Stocks by Remote Sensing Methods: A Case Study in a Forest-dominated Alpine Watershed, Western China

Estimating the Spatial Distribution of Soil Organic Carbon and Soil Total Nitrogen Stocks by Remote Sensing Methods: A Case Study in a Forest-dominated Alpine Watershed, Western China

Prediction of Soil Organic Carbon Contents of Rice Paddies in South-Western Coastal Area of Korea Using Random Forest Models

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

Contact Info

Product

Resources

About