The use of diffuse reflectance spectroscopy for in situ carbon and nitrogen analysis of pastoral soils

Kusumo, Bambang Hari; Hedley, C. B.; Hedley, M. J.; Hueni, Andreas; Tuohy, M. P.; Arnold, Gregory C.

doi:10.1071/sr08118

Cited by 59 publications

(39 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 805 nm waveband is related to the red-edge, which is known to be sensitive to biomass [69], and the predictions of P, K, pH and OM were found to be correlated. The 1120 and 1155 nm wavebands may be related to the v S-O stretching bands of sulfate [70], which can be used to predict P and K. The 1225 nm [71] and 1315 nm [72] wavebands were found to be important bands for predicting soil organics; here, several properties are correlated. The 1450 nm waveband in the prediction of OM may be related to the carboxylic acids in organics [25].…”

Section: Feature Importance In Pls-rmentioning

confidence: 90%

Linear Multi-Task Learning for Predicting Soil Properties Using Field Spectroscopy

et al. 2017

View full text Add to dashboard Cite

Abstract:Field spectroscopy has been suggested to be an efficient method for predicting soil properties using quantitative mathematical models in a rapid and non-destructive manner. Traditional multivariate regression algorithms usually regard the modeling of each soil property as a single task, which means only one response variable is considered as the output during modeling. Therefore, these algorithms are less suitable for the prediction of several key soil properties with low concentrations or unobvious spectral absorption signals. In the current study, we investigated the performance of a linear multi-task learning (LMTL) algorithm based on a regularized dirty model for modeling and predicting several key soil properties using field spectroscopy (350-2500 nm) as an integrated approach. We tested seven key soil properties including available nitrogen (N), phosphorus (P) and potassium (K), pH, water content (WC), organic matter (OM), and electrical conductivity (EC) in drylands. The model performances of LMTL models were compared with the commonly used single-task algorithm of the partial least squares regression (PLS-R). Our results show that the LMTL models outperformed the PLS-R models with the advantage of shared features; the ratio of performance to deviation (RPD) values in the validation set improved by 10.24%, 4.93%, 25.77%, 11.76%, 6.74%, 53.13%, and 3.15% for N, P, K, pH, WC, OM, and EC, respectively. The best prediction was obtained for OM with RPD = 2.29, indicating high accuracy (RPD > 2). The prediction results of N, P, WC, and pH were categorized as of moderate accuracy (1.4 < RPD < 2), while K and EC were categorized as of poor accuracy (RPD < 1.4). However, the explanatory power of the LMTL models was moderate due to fewer features being selected by the regularization algorithm of the LMTL approach, which should be further studied in the soil spectral analysis. Our results highlight the use of LMTL in field spectroscopy analysis that can improve the generalization performance of regression models for predicting soil properties.

show abstract

Section: Feature Importance In Pls-rmentioning

confidence: 90%

Linear Multi-Task Learning for Predicting Soil Properties Using Field Spectroscopy

et al. 2017

View full text Add to dashboard Cite

show abstract

“…A soil core was sectioned at 5 depths (7.5, 15, 30, 45, and 60 cm) and at each depth the soil reflectance spectra was acquired in situ from the freshly cut surface using a purpose built soil probe ( Fig. 1b and c, and described in detail by Kusumo et al 2008aKusumo et al , 2009b attached by fibre optic cable to a field spectroradiometer (ASD FieldSpecPro, Boulder, Colorado, USA). The soil core was rotated 360°, to give a field of view (collection area) of 561 mm 2 (Fig.…”

Section: Site Locations and Plant And Soil Property Measurementmentioning

confidence: 99%

“…Vis-NIR reflectance spectroscopy has been successfully used to predict soil C (e.g. Chang and Laird 2002;Kusumo et al 2008a), ryegrass root density in a glasshouse experiment (Kusumo et al 2009a) and in field trials (Kusumo et al 2009b), despite variations in soil texture, structure (Udelhoven et al 2003) and other chromophores (e.g. clay and non-clay contents, iron oxides, water, decomposed organic matter) (Baumgardner et al 1985;Ben-Dor 2002).…”

Section: Introductionmentioning

confidence: 99%

Measuring carbon dynamics in field soils using soil spectral reflectance: prediction of maize root density, soil organic carbon and nitrogen content

Kusumo

Hedley

et al. 2010

Plant Soil

View full text Add to dashboard Cite

This paper reports the development of a proximal sensing technique used to predict maize root density, soil carbon (C) and nitrogen (N) content from the visible and near-infrared (Vis-NIR) spectral reflectance of soil cores. Eighteen soil cores (0-60 cm depth with a 4.6 cm diameter) were collected from two sites within a field of 90-day-old maize silage; Kairanga silt loam and Kairanga fine sandy loam (Gley Soils). At each site, three replicate soil cores were taken at 0, 15 and 30 cm distance from the row of maize plants (rows were 60 cm apart). Each soil core was sectioned at 5 depths (7.5, 15, 30, 45, and 60 cm) and soil reflectance spectra were acquired from the freshly cut surface at each depth. A 1.5 cm soil slice was taken at each surface to obtain root mass and total soil C and N reference (measured) data. Root densities decreased with depth and distance from plant and were lower in the silt loam, which had the higher total C and N contents. Calibration models, developed using partial least squares regression (PLSR) between the first derivative of soil reflectance and the reference data, were able to predict with moderate accuracy the soil profile root density (r 2 =0.75; ratio of prediction to deviation [RPD]=2.03; root mean square error of crossvalidation [RMSECV] = 1.68 mg/cm 3 ), soil% C (r 2 =0.86; RPD=2.66; RMSECV=0.48%) and soil% N (r 2 =0.81; RPD=2.32; RMSECV=0.05%) distribution patterns. The important wavelengths chosen by the PLSR model to predict root density were different to those chosen to predict soil C or N. In addition, predicted root densities were not strongly autocorrelated to soil C (r=0.60) or N (r=0.53) values, indicating that root density can be predicted independently from soil C. This research has identified a potential method for assessing root densities in field soils enabling study of their role in soil organic matter synthesis.

show abstract

“…R 2 shows the percentage of the variance in the y variable that is calculated by the x variables, and RMSE indicates the prediction error. Generally, the best prediction model is shown by the largest R 2 and the smallest RMSE [47].…”

Section: Assessment Statisticsmentioning

confidence: 99%

“…The R 2 and the root mean square error (RMSE) have been reported as standard methods for validation of the prediction models [47]. Therefore, to compare the ability of different established calibration methods, the R 2 and the RMSE of cross-validation from the PLSR, as well as the R 2 and the RMSE from the test-set for PARACUDA II ® at both institutions, were considered.…”

Section: Assessment Statisticsmentioning

confidence: 99%

Agricultural Soil Spectral Response and Properties Assessment: Effects of Measurement Protocol and Data Mining Technique

et al. 2017

View full text Add to dashboard Cite

Abstract:Soil spectroscopy has shown to be a fast, cost-effective, environmentally friendly, non-destructive, reproducible and repeatable analytical technique. Soil components, as well as types of instruments, protocols, sampling methods, sample preparation, spectral acquisition techniques and analytical algorithms have a combined influence on the final performance. Therefore, it is important to characterize these differences and to introduce an effective approach in order to minimize the technical factors that alter reflectance spectra and consequent prediction. To quantify this alteration, a joint project between Czech University of Life Sciences Prague (CULS) and Tel-Aviv University (TAU) was conducted to estimate Cox, pH-H 2 O, pH-KCl and selected forms of Fe and Mn. Two different soil spectral measurement protocols and two data mining techniques were used to examine seventy-eight soil samples from five agricultural areas in different parts of the Czech Republic. Spectral measurements at both laboratories were made using different ASD spectroradiometers. The CULS protocol was based on employing a contact probe (CP) spectral measurement scheme, while the TAU protocol was carried out using a CP measurement method, accompanied with the internal soil standard (ISS) procedure. Two spectral datasets, acquired from different protocols, were both analyzed using partial least square regression (PLSR) technique as well as the PARACUDA II ® , a new data mining engine for optimizing PLSR models. The results showed that spectra based on the CULS setup (non-ISS) demonstrated significantly higher albedo intensity and reflectance values relative to the TAU setup with ISS. However, the majority of statistics using the TAU protocol was not noticeably better than the CULS spectra. The paper also highlighted that under both measurement protocols, the PARACUDA II ® engine proved to be a powerful tool for providing better results than PLSR. Such initiative is not only a way to unlock current limitations of soil spectroscopy, but also offers considerable efficiency and cost-and time-saving possibilities, which lead to further improvements in prediction performance of spectral models.

show abstract

The use of diffuse reflectance spectroscopy for in situ carbon and nitrogen analysis of pastoral soils

Cited by 59 publications

References 43 publications

Linear Multi-Task Learning for Predicting Soil Properties Using Field Spectroscopy

Linear Multi-Task Learning for Predicting Soil Properties Using Field Spectroscopy

Measuring carbon dynamics in field soils using soil spectral reflectance: prediction of maize root density, soil organic carbon and nitrogen content

Agricultural Soil Spectral Response and Properties Assessment: Effects of Measurement Protocol and Data Mining Technique

Contact Info

Product

Resources

About