Predicting Spatial Variations in Soil Nutrients with Hyperspectral Remote Sensing at Regional Scale.

Rapid acquisition of the spatial distribution of soil nutrients holds great implications for farmland soil productivity safety, food security and agricultural management. To this end, we collected 1297 soil samples and measured the content of soil total nitrogen (TN), soil available phosphorus (AP) and soil available potassium (AK) in Zengcheng, north of the Pearl River Delta, China. Hyperspectral remote sensing images (115 bands) of the Chinese Environmental 1A satellite were used as auxiliary variables and dimensionality reduction was performed using Pearson correlation analysis and principal component analysis. The TN, AP and AK of soil were predicted in the study area based on auxiliary variables after dimensionality reduction, along with stepwise linear regression (SLR), support vector machine (SVM), random forest (RF) and back-propagation neural network (BPNN) models; 324 independent points were used to verify the predictive performance. The BPNN model, which demonstrated the best predictive accuracy among all methods, combined ordinary kriging (OK) with mapping the spatial variations of soil nutrients. Results show that the BPNN model with double hidden layers had better predictive accuracy for soil TN (root mean square error (RMSE) = 0.409 mg kg-1, R² = 44.24%), soil AP (RMSE = 40.808 mg kg-1, R² = 42.91%) and soil AK (RMSE = 67.464 mg kg-1, R² = 48.53%) compared with the SLR, SVM and RF models. The back propagation neural network-ordinary kriging (BPNNOK) model showed the best predictive results of soil TN (RMSE = 0.292 mg kg-1, R² = 68.51%), soil AP (RMSE = 29.62 mg kg-1, R² = 69.30%) and soil AK (RMSE = 49.67 mg kg-1 and R² = 70.55%), indicating the best fitting ability between hyperspectral remote sensing bands and soil nutrients. According to the spatial mapping results of the BPNNOK model, concentrations of soil TN (north-central), soil AP (central and southwest) and soil AK (central and southeast) were respectively higher in the study area. The most important bands (464⁻517 nm) for soil TN (b10, b14, b20 and b21), soil AP (b3, b19 and b22) and soil AK (b4, b11, b12 and b25) exhibited the best response and sensitivity according to the SLR, SVM, RF and BPNN models. It was concluded that the application of hyperspectral images (visible-near-infrared data) with BPNNOK model was found to be an efficient method for mapping and monitoring soil nutrients at the regional scale.

Vertical distributions and potential contamination assessment of seldom monitored trace elements in three different land use types of Yellow River Delta.

The Yellow River Delta (YRD) is the second largest petrochemical base in China and the impact of human activities has been continuously increasing in recent decades, however, the contamination status of seldom monitored trace elements (SMTEs) in YRD has rarely been reported. This study evaluated the levels, vertical distributions, contamination status and sources of SMTEs in soil samples of three different land use types in YRD. The results indicated that the vertical distributions of SMTEs contents showed a gradually upward increasing trend for the soil profiles of black locust forest, while the SMTEs contents displayed a gradually upward decreasing trend for the soil profiles of cotton field. However, the SMTEs contents in the oil field area showed no significant difference among different depths. The vertical distributions of SMTEs were very likely related to the anthropogenic disturbance in the later stage. The environmental pollution status assessment of SMTEs showed obvious enrichment of Cs, Sn, and U in the soils of YRD. Moreover, the potential source analysis based on multivariate statistical methods indicated that Ga, Rb, Cs, Sc, Sn, Tl, Be, Bi, Ca and Mo were clustered together and positively correlated with Al, Fe, Mg and K, and may be mainly associated with geochemical weathering process, while the Ce, La, Th, U, Nb, Ta, and Hf may be impacted by both natural process and human activities. Though the SMTEs pollution status was not very serious, our results highlighted the non-negligible influence of anthropogenic activities on vertical distributions of SMTEs in three different land use types from YRD. Our results provide valuable information for understanding the vertical distribution and pollution status of SMTEs in YRD.

Spatial distribution, sources and risk assessment of potentially toxic elements contamination in surface soils of Yellow River Delta, China.

The contamination status and ecological risk of soil potentially toxic elements (PTEs) in Yellow River Delta (YRD) are still poorly understood. Thirty surface soil samples were collected in YRD, determined for contents of PTEs, and assessed using four kinds of proxies. Results indicated that PTEs contents basically met the Environmental Quality Standard for Soils, and spatial heterogeneity of PTEs was not distinctive except for a few sampling sites. Results of geo-accumulation index (Igeo) and enrichment factor (EF) indicated significant enrichment of As and Sb in YRD. The multivariate analysis results distinguished the possible sources of these PTEs and demonstrated that sources of Ag, As, Cd, Cu, Pb, Sb and Zn could be influenced by anthropogenic activities (industrial and agricultural sources). Moreover, Ni, Cr and As had relatively high contributions to sum of toxicity units (ΣTUs). This study provides basic information for understanding soil PTEs contamination status of YRD.