Ecological risk assessment on heavy metals in soils: Use of soil diffuse reflectance mid-infrared Fourier-transform spectroscopy

Abstract

The bioavailability of heavy metals in soil is controlled by their concentrations and soil properties. Diffuse reflectance mid-infrared Fourier-transform spectroscopy (DRIFTS) is capable of detecting specific organic and inorganic bonds in metal complexes and minerals and therefore, has been employed to predict soil composition and heavy metal contents. The present study explored the potential of DRIFTS for estimating soil heavy metal bioavailability. Soil and corresponding wheat grain samples from the Yangtze River Delta region were analyzed by DRIFTS and chemical methods. Statistical regression analyses were conducted to correlate the soil spectral information to the concentrations of Cd, Cr, Cu, Zn, Pb, Ni, Hg and Fe in wheat grains. The principal components in the spectra influencing soil heavy metal bioavailability were identified and used in prediction model construction. The established soil DRIFTS-based prediction models were applied to estimate the heavy metal concentrations in wheat grains in the mid-Yangtze River Delta area. The predicted heavy metal concentrations of wheat grain were highly consistent with the measured levels by chemical analysis, showing a significant correlation (r² > 0.72) with acceptable root mean square error RMSE. In conclusion, DRIFTS is a promising technique for assessing the bioavailability of soil heavy metals and related ecological risk.

Figure 1. Coefficients of correlation between heavy metal concentrations of wheat grain and reflectance of soil DRIFTS.

Reflectances at the 400–2400 cm⁻¹ band were significantly correlated to the concentrations of Hg, Cu, Zn, Fe, Cd and Ni, respectively, but not significantly correlated to those of Pb and Cr. “Sensitive band for metal” refers to the band at which soil MIR reflectance shows significant correlation to the metal concentration of wheat grain. The sensitive band ranges are marked with hollow arrows in the first diagram (for Cd, Fe and Ni) and a pink rectangle in the second diagram (for Fe, Cu, Zn and Hg).

Figure 2. Results of principal component analysis (PCA) and the optimization of adopted spectral bands for prediction models.

A total of 10 and 11principal components were extracted for Fe and Cd, respectively, based on the sensitive bands using PCA analysis. The corresponding band of each PC factor is indicated by a trough (peak value) of correlation coefficient. To optimize the prediction models, for each PC-corresponding spectral region, one representative band showing the highest correlation with metal concentration was chosen to establish the regression model. Simultaneously, reflectance of the chosen band should also significantly correlates to the heavy metal concentration of wheat grain (|R²| > 0.229, p < 0.01). Since the processes for Cu, Zn, Ni and Hg are consistent, the information about these metals is not reported.

Figure 3. Spatial distribution of ecological risks assessment of Cd in arable soils.

Cd* denotes the predicted Cd concentration of wheat grain. The grade division was based on the Chinese Maximum Permissible Concentration of Cd, for which five grades are classified. The “Grade IV” (color denoted by orange) means that the corresponding sites should be early-warned as “Not suitable for planting wheat”, and “Grade V” (color denoted by red) should be early-warned as “obviously unsafe for wheat production”. The map was created by software ArcGIS 9.3.

Figure 4

Figure 5. Comparison the chemically-measured concentrations of Cd in wheat grain versus the result of ecological risk assessment of Cd in soils (i.e., spatial distribution map of model-predicted Cd concentrations in wheat grain from the Yangtze River Delta region).

Cd concentration* represents the chemically-measured Cd concentrations, and is denoted as filled circles; different filled colors denote varying risk grades (for example, red indicates that the Cd concentration of wheat grain reached or exceeded the threshold value of Grade V). According to the results of ecological risk assessment on Cd (Fig. 4 and Table S-3, SI), the wheat grown in arable soils in the Suzhou-Wuxi region will generate Cd in the wheat grain at three concentration grades (III, IV and V), with the corresponding zones delineated with yellow, orange and red color dashed lines, respectively. The spatial patterns of model-predicted and chemically-measured concentrations of Cd in wheat grain, demonstrated high consistence. The map was created by software ArcGIS 9.3.

Figure 6