The relationship between diffuse spectral reflectance of the soil and its cation exchange capacity is scale-dependent

Savvides, A.; Corstanje, Ron; Baxter, S.J.; Rawlins, Barry G.; Lark, R. M.

doi:10.1016/j.geoderma.2009.11.007

Cited by 31 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, our results indicate that MBL and Cubist outperformed the global PLSR and RF models. In large and complex datasets, the relationship between soil properties and spectra can be highly nonlinear [14,86]. As a result, both MBL and Cubist were able to better predict soil physical and chemical properties.…”

Section: Best Model Performancementioning

confidence: 99%

Accurate and Precise Prediction of Soil Properties from a Large Mid-Infrared Spectral Library

et al. 2019

View full text Add to dashboard Cite

Diffuse reflectance spectroscopy (DRS) is emerging as a rapid and cost-effective alternative to routine laboratory analysis for many soil properties. However, it has primarily been applied in project-specific contexts. Here, we provide an assessment of DRS spectroscopy at the scale of the continental United States by utilizing the large (n > 50,000) USDA National Soil Survey Center mid-infrared spectral library and associated soil characterization database. We tested and optimized several advanced statistical approaches for providing routine predictions of numerous soil properties relevant to studying carbon cycling. On independent validation sets, the machine learning algorithms Cubist and memory-based learner (MBL) both outperformed random forest (RF) and partial least squares regressions (PLSR) and produced excellent overall models with a mean R2 of 0.92 (mean ratio of performance to deviation = 6.5) across all 10 soil properties. We found that the use of root-mean-square error (RMSE) was misleading for understanding the actual uncertainty about any particular prediction; therefore, we developed routines to assess the prediction uncertainty for all models except Cubist. The MBL models produced much more precise predictions compared with global PLSR and RF. Finally, we present several techniques that can be used to flag predictions of new samples that may not be reliable because their spectra fall outside of the calibration set.

show abstract

Section: Best Model Performancementioning

confidence: 99%

Accurate and Precise Prediction of Soil Properties from a Large Mid-Infrared Spectral Library

et al. 2019

View full text Add to dashboard Cite

show abstract

“…It is necessary to select characteristic bands that can not only eliminate irrelevant or nonlinear variables and reduce redundancy, but also simplify the model to obtain a model with better prediction ability and that is more robust. As an optimization algorithm, GA has been widely used in the field of spectral analysis (Savvides et al, 2010). In addition, PLSR was selected as the regression model for GA to obtain a more efficient and steadier model.…”

Section: Chemometric Analysesmentioning

confidence: 99%

Multi‐sensor fusion for the determination of several soil properties in the Yangtze River Delta, China

Zhao

et al. 2018

European J Soil Science

View full text Add to dashboard Cite

Summary Soil organic matter (SOM), total nitrogen (TN), available nitrogen (AN), available phosphorus (AP), available potassium (AK) and pH are key chemical properties for evaluating soil fertility and quality. This study involved the integration of four soil sensors, visible near‐infrared (vis–NIR) spectrometer, mid‐infrared (mid‐IR) spectrometer, portable X‐ray fluorescence (PXRF) analyser and laser‐induced breakdown spectroscopy (LIBS), to achieve rapid measurement of these soil properties. A genetic algorithm and partial least‐squares regression (GA–PLSR) were used to select characteristic bands to reduce data redundancy. We then calibrated models from three aspects: models using partial least‐squares regression (PLSR) based on single sensor data, models using PLSR based on fused sensor data, involving data combined from the four sensors into a new dataset to create a data fusion (DF) model, and models with Bayesian model averaging (BMA) based on prediction results of fused sensor data, involving prediction results combined from the four sensors into a new dataset to form the BMA model. The results showed the following. (i) For the single sensor, the predictive performance decreased as follows: mid‐IR > vis–NIR > LIBS > PXRF. (ii) Compared with the single sensor approach, the DF approach slightly improved or even reduced prediction accuracy and caused a large amount of redundancy. We suggest that this approach is not able to improve predictive ability. (iii) The BMA approach achieved the best prediction for the six soil properties. Our findings suggest that model averaging of vis–NIR, mid‐IR and LIBS could be a reliable and stable approach for the fast measurement of soil properties. Highlights We used four proximal soil sensors to evaluate six key properties for evaluating soil fertility and quality. GA–PLSR was used to select characteristic bands. We compared predictions of six soil properties from single sensor, DF and BMA approaches. BMA predictions were more accurate than predictions from single and fused sensor data.

show abstract

“…In the last years, several studies have addressed the potential of soil spectroscopy, which typically is used at the laboratory scale, to provide predictors to estimate a large number of soil properties such as clay, sand, and silt contents (Ben‐Dor and Banin, 1995; Brown, 2007; Gomez et al, 2008a; Lagacherie et al, 2008; Janik et al, 2009; Ramirez‐Lopez et al, 2013), organic C content (Nocita et al, 2013; Cambule et al, 2012; Ramirez‐Lopez et al, 2013), soil moisture (Minasny et al, 2008; Rijal et al, 2013; Kodaira and Shibusawa, 2013), CaCO 3 content (Gomez et al, 2008a; Lagacherie et al, 2008), salt content (Wang et al, 2012), pH (Janik et al, 1998; Viscarra Rossel and Behrens, 2010), cation exchange capacity (Janik et al, 2009; Savvides et al, 2010; Kodaira and Shibusawa, 2013), and some macro‐ and micronutrients (Janik et al, 2009; Kodaira and Shibusawa, 2013).…”

mentioning

confidence: 99%

Towards Retrieving Soil Hydraulic Properties by Hyperspectral Remote Sensing

Babaeian

Homaee

Montzka

et al. 2015

Vadose Zone Journal

View full text Add to dashboard Cite

In this study, we developed spectrotransfer functions (STFs) that relate soil hydraulic properties (SHPs) to spectral relectance values to estimate hydraulic parameters of the Mualem -van Genuchten (MvG) model. We investigated the general potential of airborne as well as space-borne remote sensors to retrieve MvG hydraulic parameters of a bare soil agricultural ield. Based on the ASD full spectrum (Scenario I), simple spectral signatures were generated mimicking the hyperspectral EnMAP sensor (Scenario II), and the multispectral Sentinel-2 sensor (Scenario III). A stepwise multiple linear regression method was used for each scenario to derive STFs. We further tested laboratory-and soil-map-based HYPRES and Rosetta pedotransfer functions (PTFs) to parameterize MvG parameters and thus provide soil water characteristics and hydraulic conductivity functions in the region. The best results were obtained for Scenarios I and II, with similar R 2 values for shape parameters a* and n and the lognormal saturated hydraulic conductivity (K s *). The R 2 values were highest for K s * in Scenarios I and II (0.58 and 0.57, respectively). The R 2 values for a* and n were 0.30 and 0.34 in Scenario I and 0.39 and 0.31 in Scenario II, respectively. In all scenarios, the lowest R 2 values were obtained for saturated water content (q s ), with values around 0.10 for Scenarios I and II and almost zero in Scenario III. Compared with HYPRES and Rosetta PTFs, the spectral approach performed reasonably well in terms of predicting soil water retention characteristics and unsaturated hydraulic conductivity. These indings suggest that spectral relectance data provide a promising indirect and quick method for large-scale parameter estimation.

show abstract

The relationship between diffuse spectral reflectance of the soil and its cation exchange capacity is scale-dependent

Cited by 31 publications

References 23 publications

Accurate and Precise Prediction of Soil Properties from a Large Mid-Infrared Spectral Library

Accurate and Precise Prediction of Soil Properties from a Large Mid-Infrared Spectral Library

Multi‐sensor fusion for the determination of several soil properties in the Yangtze River Delta, China

Towards Retrieving Soil Hydraulic Properties by Hyperspectral Remote Sensing

Contact Info

Product

Resources

About