Identifying optimal spectral bands to assess soil properties with VNIR radiometry in semi-arid soils

Melendez-Pastor, Ignacio; Pedreño, José Navarro; Gómez, Ignacio; Koch, Magaly

doi:10.1016/j.geoderma.2008.08.004

Cited by 45 publications

(35 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The climate is arid or semiarid according to the aridity index of Martonne [26] and the aridity index of UNEP [27] respectively. Major soil groups in the study area include Fluvisols, Calcisols, Solonchaks and Gleysols [28,29] based on the World Reference Base for Soil Resources [30].…”

Section: Methodsmentioning

confidence: 99%

Land-Cover Phenologies and Their Relation to Climatic Variables in an Anthropogenically Impacted Mediterranean Coastal Area

et al. 2010

Self Cite

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Land-Cover Phenologies and Their Relation to Climatic Variables in an Anthropogenically Impacted Mediterranean Coastal Area

et al. 2010

Self Cite

View full text Add to dashboard Cite

“…We identified four feature-block regions with high importance existing in the entire VNIR/SWIR region whose properties were associated with soil OM, WC, clay minerals and Fe oxides [64]. The first region, ranging from 410 to 650 nm, is mostly related to the Fe oxides [19,25], with the 560 nm waveband related to OM [24,65]. The second region ranges from 850 to 1075 nm; of this, the 850-930 nm range is related to hydroxyl in Fe oxides [19,25], the 970 nm waveband is related to the soil water absorption waveband [66], the 1010 nm waveband is a hydrate-related absorption feature [67], and the 1025-1075 nm range is mostly related to the electronic transition bands of Fe 2+ or Fe 3+ [19].…”

Section: Soil Properties and Spectral Responsementioning

confidence: 99%

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

“…Cross-validation is a way to predict the fit of a model to a hypothetical validation set when an explicit validation set is not available. Due to the low number of soil samples, all samples were used to develop the calibration model in the study, and the crossvalidation was used to verify the models (Bartholomeus et al, 2008;Melendez-Pastror et al, 2008;Escribano et al, 2010).…”

Section: Evaluation Of Som Prediction Modelmentioning

confidence: 99%

“…Many studies have found wavebands in the visible range around 350-760 nm (Krishnan et al, 1980), 450-590 nm (Melendez-Pastror et al, 2008), 550-760 nm (Sha et al, 2003), 616 and 724 nm (Sha et al, 2003), and 675 nm (He et al, 2006) to be important for the calibration models of SOM and soil organic carbon (SOC) (often approximated to be 1.72 times that of SOM). A strong correlation also exists between SOM and wavelengths in the near infrared (NIR) range.…”

Section: Correlation Analysismentioning

confidence: 99%

Prediction of soil organic matter content in a litchi orchard of South China using spectral indices

Chen

Peng

et al. 2012

Soil and Tillage Research

View full text Add to dashboard Cite

Identifying optimal spectral bands to assess soil properties with VNIR radiometry in semi-arid soils

Cited by 45 publications

References 24 publications

Land-Cover Phenologies and Their Relation to Climatic Variables in an Anthropogenically Impacted Mediterranean Coastal Area

Land-Cover Phenologies and Their Relation to Climatic Variables in an Anthropogenically Impacted Mediterranean Coastal Area

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

Prediction of soil organic matter content in a litchi orchard of South China using spectral indices

Contact Info

Product

Resources

About