Next Article in Journal
An Efficient Waste-To-Energy Model in Isolated Environments. Case Study: La Gomera (Canary Islands)
Next Article in Special Issue
Trace Elements in Soils of a Typical Industrial District in Ningxia, Northwest China: Pollution, Source, and Risk Evaluation
Previous Article in Journal
Synthesis of Nano-Calcium Oxide from Waste Eggshell by Sol-Gel Method
Previous Article in Special Issue
Application of Time-Lapse Ion Exchange Resin Sachets (TIERS) for Detecting Illegal Effluent Discharge in Mixed Industrial and Agricultural Areas, Taiwan
Article

Hyperspectral Prediction Model of Metal Content in Soil Based on the Genetic Ant Colony Algorithm

1
State Key Laboratory of Environmental Geochemistry, Institute of Geochemistry, Chinese Academy of Sciences, Guiyang 550081, Guizhou Province, China
2
School of Geography and Environmental Sciences, Guizhou Normal University, Guiyang 550001, Guizhou Province, China
3
Puding Karst Ecosystem Observation and Research Station, Chinese Academy of Sciences, Puding 562100, Guizhou Province, China
4
CAS Center for Excellence in Quaternary Science and Global Change, Xi’an 710061, Shanxi Province, China
5
Guizhou Provincial Key Laboratory of Geographic State Monitoring of Watershed, Guizhou Education University, Guiyang 550018, Guizhou Province, China
*
Author to whom correspondence should be addressed.
Sustainability 2019, 11(11), 3197; https://doi.org/10.3390/su11113197
Received: 27 May 2019 / Revised: 3 June 2019 / Accepted: 4 June 2019 / Published: 7 June 2019
(This article belongs to the Special Issue Sustainable Management of Heavy Metals)
The accumulation of metals in soil harms human health through different channels. Therefore, it is very important to conduct fast and effective non-destructive prediction of metals in the soil. In this study, we investigate the characteristics of four metal contents, namely, Sb, Pb, Cr, and Co, in the soil of the Houzhai River Watershed in Guizhou Province, China, and establish the content prediction back propagation (BP) neural network and genetic-ant colony algorithm BP (GAACA-BP) neural network models based on hyperspectral data. Results reveal that the four metals in the soil have different degrees of accumulation in the study area, and the correlation between them is significant, indicating that their sources may be similar. The fitting effect and accuracy of the GAACA-BP model are greatly improved compared with those of the BP model. The R values are above 0.7, the MRE is reduced to between 6% and 15%, and the validation accuracy is increased by 12–64%. The prediction ability of the model of the four metals is Cr > Co > Sb > Pb. These results indicate the possibility of using hyperspectral techniques to predict metal content. View Full-Text
Keywords: metal concentration; spectral reflectance; spatial distribution; machine learning metal concentration; spectral reflectance; spatial distribution; machine learning
Show Figures

Figure 1

MDPI and ACS Style

Tian, S.; Wang, S.; Bai, X.; Zhou, D.; Luo, G.; Wang, J.; Wang, M.; Lu, Q.; Yang, Y.; Hu, Z.; Li, C.; Deng, Y. Hyperspectral Prediction Model of Metal Content in Soil Based on the Genetic Ant Colony Algorithm. Sustainability 2019, 11, 3197. https://doi.org/10.3390/su11113197

AMA Style

Tian S, Wang S, Bai X, Zhou D, Luo G, Wang J, Wang M, Lu Q, Yang Y, Hu Z, Li C, Deng Y. Hyperspectral Prediction Model of Metal Content in Soil Based on the Genetic Ant Colony Algorithm. Sustainability. 2019; 11(11):3197. https://doi.org/10.3390/su11113197

Chicago/Turabian Style

Tian, Shiqi, Shijie Wang, Xiaoyong Bai, Dequan Zhou, Guangjie Luo, Jinfeng Wang, Mingming Wang, Qian Lu, Yujie Yang, Zeyin Hu, Chaojun Li, and Yuanhong Deng. 2019. "Hyperspectral Prediction Model of Metal Content in Soil Based on the Genetic Ant Colony Algorithm" Sustainability 11, no. 11: 3197. https://doi.org/10.3390/su11113197

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop