Limits...
Evaluating the utility of mid-infrared spectral subspaces for predicting soil properties.

Sila AM, Shepherd KD, Pokhariyal GP - Chemometr Intell Lab Syst (2016)

Bottom Line: The root mean square error of prediction was computed using a one-third-holdout validation set.In summary, the results show that global models outperformed the subspace models.We, therefore, conclude that global models are more accurate than the local models except in few cases.

View Article: PubMed Central - PubMed

Affiliation: World Agroforestry Centre (ICRAF), P.O. Box 30677-00100 GPO, Nairobi, Kenya; School of Mathematics, University of Nairobi, P.O Box 30196-00100 GPO, Nairobi, Kenya.

ABSTRACT

We propose four methods for finding local subspaces in large spectral libraries. The proposed four methods include (a) cosine angle spectral matching; (b) hit quality index spectral matching; (c) self-organizing maps and (d) archetypal analysis methods. Then evaluate prediction accuracies for global and subspaces calibration models. These methods were tested on a mid-infrared spectral library containing 1907 soil samples collected from 19 different countries under the Africa Soil Information Service project. Calibration models for pH, Mehlich-3 Ca, Mehlich-3 Al, total carbon and clay soil properties were developed for the whole library and for the subspace. Root mean square error of prediction was used to evaluate predictive performance of subspace and global models. The root mean square error of prediction was computed using a one-third-holdout validation set. Effect of pretreating spectra with different methods was tested for 1st and 2nd derivative Savitzky-Golay algorithm, multiplicative scatter correction, standard normal variate and standard normal variate followed by detrending methods. In summary, the results show that global models outperformed the subspace models. We, therefore, conclude that global models are more accurate than the local models except in few cases. For instance, sand and clay root mean square error values from local models from archetypal analysis method were 50% poorer than the global models except for subspace models obtained using multiplicative scatter corrected spectra with which were 12% better. However, the subspace approach provides novel methods for discovering data pattern that may exist in large spectral libraries.

No MeSH data available.


Related in: MedlinePlus

Figure linear regression for the calibration set (n = 1325) of predicted against measured soil property values (r2, a coefficient of determination; RMSEC, root mean square error of calibration) using 1st derivative spectra.
© Copyright Policy - CC BY
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4834557&req=5

f0030: Figure linear regression for the calibration set (n = 1325) of predicted against measured soil property values (r2, a coefficient of determination; RMSEC, root mean square error of calibration) using 1st derivative spectra.

Mentions: Fig. 6 gives scatter plots for the global calibration models showing predicted values against the actual measurement values. Similar scatter plots were found for archetype subspaces but with lower r2 and higher RMSE values. We have not shown the scatter plot for the combined archetype models. Our results showed that the best RF model combinations for the Savitzky‚ÄďGolay 1st derivative processed spectra are to be 500 trees but different numbers of random variables were tried at each split in the six calibration models (pH¬†=¬†182; m3.Al¬†=¬†388; m3.Ca¬†=¬†40; total carbon¬†=¬†40; clay¬†=¬†19 and sand¬†=¬†86). A similar number of trees was reported by McDowell et al. [22] for soil total carbon analysis using MIR data for 307 Hawaiian soil samples. But, their model used up to 396 random variables, which are about 10 times the number of variables, used in this study for total carbon.


Evaluating the utility of mid-infrared spectral subspaces for predicting soil properties.

Sila AM, Shepherd KD, Pokhariyal GP - Chemometr Intell Lab Syst (2016)

Figure linear regression for the calibration set (n = 1325) of predicted against measured soil property values (r2, a coefficient of determination; RMSEC, root mean square error of calibration) using 1st derivative spectra.
© Copyright Policy - CC BY
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4834557&req=5

f0030: Figure linear regression for the calibration set (n = 1325) of predicted against measured soil property values (r2, a coefficient of determination; RMSEC, root mean square error of calibration) using 1st derivative spectra.
Mentions: Fig. 6 gives scatter plots for the global calibration models showing predicted values against the actual measurement values. Similar scatter plots were found for archetype subspaces but with lower r2 and higher RMSE values. We have not shown the scatter plot for the combined archetype models. Our results showed that the best RF model combinations for the Savitzky‚ÄďGolay 1st derivative processed spectra are to be 500 trees but different numbers of random variables were tried at each split in the six calibration models (pH¬†=¬†182; m3.Al¬†=¬†388; m3.Ca¬†=¬†40; total carbon¬†=¬†40; clay¬†=¬†19 and sand¬†=¬†86). A similar number of trees was reported by McDowell et al. [22] for soil total carbon analysis using MIR data for 307 Hawaiian soil samples. But, their model used up to 396 random variables, which are about 10 times the number of variables, used in this study for total carbon.

Bottom Line: The root mean square error of prediction was computed using a one-third-holdout validation set.In summary, the results show that global models outperformed the subspace models.We, therefore, conclude that global models are more accurate than the local models except in few cases.

View Article: PubMed Central - PubMed

Affiliation: World Agroforestry Centre (ICRAF), P.O. Box 30677-00100 GPO, Nairobi, Kenya; School of Mathematics, University of Nairobi, P.O Box 30196-00100 GPO, Nairobi, Kenya.

ABSTRACT

We propose four methods for finding local subspaces in large spectral libraries. The proposed four methods include (a) cosine angle spectral matching; (b) hit quality index spectral matching; (c) self-organizing maps and (d) archetypal analysis methods. Then evaluate prediction accuracies for global and subspaces calibration models. These methods were tested on a mid-infrared spectral library containing 1907 soil samples collected from 19 different countries under the Africa Soil Information Service project. Calibration models for pH, Mehlich-3 Ca, Mehlich-3 Al, total carbon and clay soil properties were developed for the whole library and for the subspace. Root mean square error of prediction was used to evaluate predictive performance of subspace and global models. The root mean square error of prediction was computed using a one-third-holdout validation set. Effect of pretreating spectra with different methods was tested for 1st and 2nd derivative Savitzky-Golay algorithm, multiplicative scatter correction, standard normal variate and standard normal variate followed by detrending methods. In summary, the results show that global models outperformed the subspace models. We, therefore, conclude that global models are more accurate than the local models except in few cases. For instance, sand and clay root mean square error values from local models from archetypal analysis method were 50% poorer than the global models except for subspace models obtained using multiplicative scatter corrected spectra with which were 12% better. However, the subspace approach provides novel methods for discovering data pattern that may exist in large spectral libraries.

No MeSH data available.


Related in: MedlinePlus