Retrieval of Soil Heavy Metal Content for Environment Monitoring in Mining Area via Transfer Learning
Abstract
:1. Introduction
2. Materials
2.1. The Study Area
2.2. Data Preparation
2.2.1. Soil Sample Collection
2.2.2. Soil Sample Analysis and Preprocessing
2.2.3. Remote Sensing Data Preparation
3. Methodology
3.1. Optimal Factors of the Metals of Interest
3.1.1. Spectral Factors
3.1.2. Terrain Factors
3.1.3. Select the Optimal Factors for Each Metal of Interest
3.2. Model for Soil Heavy Metal Retrieval Using Transfer Learning
3.2.1. Construct a Pre-Trained GA-BP Model Using Samples in 2017
3.2.2. Construct Our Tr-GA-BP Model for Retrieval of Heavy Metals in 2019
4. Implementation and Results
4.1. Implementation
4.2. Results and Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Wu, Y.; Li, X.; Yu, L.; Wang, T.; Wang, J.; Liu, T. Review of soil heavy metal pollution in China: Spatial distribution, primary sources, and remediation alternatives. Resour. Conserv. Recycl. 2022, 181, 106261. [Google Scholar] [CrossRef]
- Krasowska, M.; Kowczyk-Sadowy, M.; Szatyłowicz, E.; Obidziński, S. Analysis of the Possibility of Heavy Metal Ions Removal from Aqueous Solutions on Fruit Pomace. J. Ecol. Eng. 2023, 24, 169–177. [Google Scholar] [CrossRef]
- Łapińśki, D.; Wiater, J.; Szatyłowicz, E. The Content of Heavy Metals in Waste as an Indicator Determining the Possibilities of their Agricultural Use. J. Ecol. Eng. 2019, 20, 225–230. [Google Scholar] [CrossRef]
- Huo, A.; Wang, X.; Zhao, Z.; Yang, L.; Zhong, F.; Zheng, C.; Gao, N. Risk Assessment of Heavy Metal Pollution in Farmland Soils at the Northern Foot of the Qinling Mountains. Int. J. Environ. Res. Public Health 2022, 19, 14962. [Google Scholar] [CrossRef]
- Tong, W.; Liu, J.; Fei, L.; Sun, Z. Inversion of soil heavy metals in Guanzhong area of Shaanxi based on VIS-NIR spectroscopy. J. Phys. Conf. Ser. 2020, 1549, 022145. [Google Scholar] [CrossRef]
- Xu, X.; Chen, S.; Ren, L.; Han, C.; Lv, D.; Zhang, Y.; Ai, F. Estimation of Heavy Metals in Agricultural Soils Using Vis-NIR Spectroscopy with Fractional-Order Derivative and Generalized Regression Neural Network. Remote Sens. 2021, 13, 2718. [Google Scholar] [CrossRef]
- Gu, Y.; Zhao, N.; Ma, M.; Meng, D.S.; Jia, Y.; Fang, L.; Liu, J.-G.; Liu, W.-Q. Mapping Analysis of Heavy Metal Elements in Polluted Soils Using Laser-Induced Breakdown Spectroscopy. Spectrosc. Spectr. Anal. 2018, 38, 982–989. [Google Scholar]
- Tan, K.; Wang, H.; Chen, L.; Du, Q.; Du, P.; Pan, C. Estimation of the spatial distribution of heavy metal in agricultural soils using airborne hyperspectral imaging and random forest. J. Hazard. Mater. 2020, 382, 120987. [Google Scholar] [CrossRef]
- Zhang, Y.; Xu, Y.; Xiong, W.; Qu, R.; Ten, J.; Lou, Q.; Lv, N. Inversion Study of Heavy Metals in Soils of Potentially Polluted Sites Based on UAV Hyperspectral Data and Machine Learning Algorithms. In Proceedings of the 2021 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, Amsterdam, The Netherlands, 24–26 March 2021. [Google Scholar]
- Wang, F.; Gao, J.; Zha, Y. Hyperspectral sensing of heavy metals in soil and vegetation: Feasibility and challenges. ISPRS J. Photogrammtry Remote Sens. 2018, 136, 73–84. [Google Scholar] [CrossRef]
- Liu, Y.; Luo, Q.; Cheng, H. Application and development of hyperspectral remote sensing technology to determine the heavy metal content in soil. J. Agro-Environ. Sci. 2020, 39, 2699–2709. [Google Scholar]
- Peng, Y.; Kheir, R.B.; Adhikari, K.; Malinowski, R.; Greve, M.B.; Knadel, M.; Greve, M.H. Digital Mapping of Toxic Metals in Qatari Soils Using Remote Sensing and Ancillary Data. Remote Sens. 2016, 8, 1003. [Google Scholar] [CrossRef]
- Wang, T.; Zhao, M.; Yang, Y.; Zhang, Y.; Cui, Q.-F.; Li, L.-T. Inversion of Heavy Metals Content in Soil Using Multispectral Remote Sensing Imagery in Daxigou Mining Area of Shaanxi. Spectrosc. Spectr. Anal. 2019, 39, 3880. [Google Scholar]
- Cui, Q. Research on Remote Sensing Estimation and Monitoring Method of Heavy Metal Content in Mining Area Soil Based on Machine Learning; Chang’an University: Xi’an, China, 2020. [Google Scholar]
- Zhou, W.; Yang, H.; Xie, L.; Li, H.; Huang, L.; Zhao, Y.; Yue, T. Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model. Catena 2021, 202, 105222. [Google Scholar] [CrossRef]
- Xia, X.; Yang, J. Molecular sequestration mechanisms of heavy metals by iron oxides in soils using synchrotron- based techniques: A review. J. Appl. Ecol. 2019, 30, 348–358. [Google Scholar]
- Wang, H.; Tan, K.; Wu, F.; Chen, Y.; Chen, L.-H. Study of the Retrieval and Adsorption Mechanism of Soil Heavy Metals Based on Spectral Absorption Characteristics. Spectrosc. Spectr. Anal. 2020, 40, 316–323. [Google Scholar]
- Chen, W.; Peng, L.; Hu, K.; Zhang, Z.; Peng, C.; Teng, C.; Zhou, K. Spectroscopic response of soil organic matter in mining area to Pb/Cd heavy metal interaction: A mirror of coherent structural variation. J. Hazard. Mater. 2020, 393, 122425. [Google Scholar] [CrossRef]
- Shin, H.; Yu, J.; Wang, L.; Jeong, Y.; Kim, J. Spectral Interference of Heavy Metal Contamination on Spectral Signals of Moisture Content for Heavy Metal Contaminated Soils. IEEE Trans. Geosci. Remote Sens. 2020, 58, 2266–2275. [Google Scholar] [CrossRef]
- Tao, C.; Wang, Y.; Zou, B.; Tu, Y.L.; Jiang, X.L. Assessment and Analysis of Migrations of Heavy Metal Lead and Zinc in Soil with Hyperspectral Inversion Model. Spectrosc. Spectr. Anal. 2018, 38, 1850–1855. [Google Scholar]
- Fang, W.X.; Hub, R.Z.; Huang, Z.Y. Mineralization Zoning in Yindongzi-Daxigou Barite-Siderite, Silver-Polymetallic Deposits in the Qinling Orogen. Chin. J. Geochem. 2001, 20, 45–51. [Google Scholar] [CrossRef]
- Chen, L.; Wang, J.; Gu, T. Study on Fuzzy Comprehensive Evaluation of Ecological Environment in Daxigou Iron Mine. Chin. J. Soil Sci. 2017, 48, 794–799. [Google Scholar]
- State Environmental Protection Administration (Ed.) Background Value of Soil Elements in China; China Environmental Science Press: Beijing, China, 1990; pp. 10–13. [Google Scholar]
- Jin, J.; Zhou, X.P.; Ma, K. The analysis of the optimum band combination based on the image of Landsat-8—A case study of thematic survey of heavy metals in soils in the mining area of Bayan Obo. Inn. Mong. Univ. Sci. Technol. 2016, 35, 37–41. [Google Scholar]
- Zhang, C.; Ren, H.; Dai, X.; Qin, Q.; Li, J.; Zhang, T.; Sun, Y. Spectral characteristics of copper-stressed vegetation leaves and further understanding of the copper stress vegetation index. Int. J. Remote Sens. 2019, 40, 4473–4488. [Google Scholar] [CrossRef]
- Hakan, M. Mineral composite assessment of Kelkit River Basin in Turkey by means of remote sensing. J. Earth Syst. Sci. 2009, 118, 701–710. [Google Scholar]
- Xu, H.Q. Modification of Normalized Difference Water Index (NDWI) to Enhance Open Water Features in Remotely Sensed Imager. Int. J. Remote Sens. 2006, 27, 3025–3033. [Google Scholar] [CrossRef]
- Piekarczyk, J.; Kazmierowski, C.; Krolewicz, S. Relationships between soil properties of the abandoned fields and spectral data derived from the advanced spaceborne thermal emission and reflection radiometer (ASTER). Adv. Space Res. 2012, 49, 280–291. [Google Scholar] [CrossRef]
- Kheir, R.B.; Shomar, B.; Greve, M.B.; Greve, M.H. On the quantitative relationships between environmental parameters and heavy metals pollution in Mediterranean soils using GIS regression-trees: The case study of Lebanon. J. Geochem. Explor. 2014, 147, 250–259. [Google Scholar] [CrossRef]
- Zhang, S.; Wang, Z.; Zou, X.; Qian, Y.; Yu, L. Recognition of tea disease spot based on hyperspectral image and genetic optimization neural network. Trans. Chin. Soc. Agric. Eng. 2017, 33, 200–207. [Google Scholar]
- Li, B.; Tan, Y.; Wu, A.; Duan, G. A distributionally robust optimization based method for stochastic model predictive control. IEEE Trans. Autom. Control 2021, 67, 5762–5776. [Google Scholar] [CrossRef]
Type | Factors | Definition |
---|---|---|
Spectral index | MNDWI | |
DVI | ||
CMR | ||
EVI | ||
NDVI | ||
Greenness | ||
Brightness | ||
Wetness |
Cu | Pb | ||
---|---|---|---|
Factors | Correlation Coefficients | Factors | Correlation Coefficients |
B2 | 0.518 | B2 | 0.419 |
B3 | 0.466 | B3 | 0.418 |
B4 | 0.363 | B4 | 0.428 |
EVI | −0.364 | B6 | 0.313 |
CMR | −0.453 | B7 | 0.332 |
NDVI | −0.371 | EVI | −0.326 |
MNDWI | 0.396 | Brightness | 0.354 |
Greenness | −0.386 | Aspect | −0.262 |
Aspect | 0.023 | Elevation | −0.179 |
Cu | Pb | ||
---|---|---|---|
Factors | Correlation Coefficients | Factors | Correlation Coefficients |
B2 | 0.618 | B2 | 0.407 |
B3 | 0.598 | B3 | 0.415 |
B4 | 0.497 | B4 | 0.401 |
EVI | −0.372 | B6 | 0.329 |
CMR | 0.516 | B7 | 0.314 |
NDVI | −0.360 | EVI | −0.540 |
MNDWI | 0.447 | Brightness | 0.365 |
Greenness | −0.411 | Aspect | −0.578 |
Aspect | −0.569 | Altitude | 0.415 |
Number of Input Layer Neurons | Number of Hidden Layer Neurons | Number of Output Layer Neurons | Weight Joining Input Layer with Hidden Layer | Threshold between Input and Hidden Layer | |
---|---|---|---|---|---|
9 | 4 | 1 | 40 | 5 | |
Number of population | Maximum of evolutionary | Crossover probability | Mutation probability | ||
30 | 50 | 0.3 | 0.1 | ||
Optimization algorithm | Maximum of iterations | training accuracy | learning rate | ||
Levenberg Marquardt | 50 | 0.3 | 0.1 |
Cu | Pb | |||
---|---|---|---|---|
GA-BP Model | Tr-GA-BP Model | GA-BP Model | Tr-GA-BP Model | |
RMSE | 13.432 | 9.078 | 4.390 | 2.804 |
MRE | 1.902 | 0.369 | 1.753 | 0.521 |
Minimum | Maximum | Average | Standard Derivation | |||||
---|---|---|---|---|---|---|---|---|
Estimated | Reference | Estimated | Reference | Estimated | Reference | Estimated | Reference | |
Cu | 23 | 6.80 | 82 | 43.60 | 49.37 | 21.40 | 15.81 | 7.74 |
Pb | 8.1 | 13.70 | 38.9 | 34.50 | 21.45 | 21.40 | 6.88 | 5.04 |
Cu | Content(mg/kg) | 0–30 | 30–50 | 50–70 | 70–90 | 90–110 |
Percent (%) | 2.6 | 2.4 | 80.1 | 6.9 | 8.4 | |
Pb | Content(mg/kg) | 0–30 | 30–35 | 35–40 | 40–45 | 45–50 |
Percent (%) | 84.1 | 4.9 | 1.6 | 2.1 | 7.3 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yang, Y.; Cui, Q.; Cheng, R.; Huo, A.; Wang, Y. Retrieval of Soil Heavy Metal Content for Environment Monitoring in Mining Area via Transfer Learning. Sustainability 2023, 15, 11765. https://doi.org/10.3390/su151511765
Yang Y, Cui Q, Cheng R, Huo A, Wang Y. Retrieval of Soil Heavy Metal Content for Environment Monitoring in Mining Area via Transfer Learning. Sustainability. 2023; 15(15):11765. https://doi.org/10.3390/su151511765
Chicago/Turabian StyleYang, Yun, Qinfang Cui, Rongjie Cheng, Aidi Huo, and Yanting Wang. 2023. "Retrieval of Soil Heavy Metal Content for Environment Monitoring in Mining Area via Transfer Learning" Sustainability 15, no. 15: 11765. https://doi.org/10.3390/su151511765