Estimating the heavy metal contents in farmland soil from hyperspectral images based on Stacked AdaBoost ensemble learning
Heavy metal pollution poses a huge challenge to the soil environment. With the increasing pollution level, the traditional monitoring methods cannot quickly obtain information on large-area pollution. Therefore, a large-scale mapping method with high precision is urgently needed to effectively contr...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-10-01
|
| Series: | Ecological Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X22008020 |
| _version_ | 1811268176124575744 |
|---|---|
| author | Nan Lin Ranzhe Jiang Genjun Li Qian Yang Delin Li Xuesong Yang |
| author_facet | Nan Lin Ranzhe Jiang Genjun Li Qian Yang Delin Li Xuesong Yang |
| author_sort | Nan Lin |
| collection | DOAJ |
| description | Heavy metal pollution poses a huge challenge to the soil environment. With the increasing pollution level, the traditional monitoring methods cannot quickly obtain information on large-area pollution. Therefore, a large-scale mapping method with high precision is urgently needed to effectively control heavy metal pollution. This study explored a method for mapping soil heavy metal concentrations through hyperspectral images. On this basis, a new Stacked AdaBoost ensemble learning algorithm was constructed to construct the inversion model of soil heavy metal contents. The characteristic spectral bands of heavy metals were extracted as model input variables using Pearson’s correlation coefficient and successive projections algorithm. With three sets of heavy metal content data, the prediction accuracy and mapping outcomes of various machine learning methods were compared. Furthermore, the potential sources of heavy metal pollution in the study area were analyzed based on the Moran’s index. The results showed that the Stacked AdaBoost model was relatively stable with higher accuracy than traditional machine learning models. For Cr, Cu, and As, the determination coefficients (R2) of the verification set were 0.66, 0.61, and 0.74, respectively. Afterward, the results of this model were used to map the heavy metal concentration over the study area. The mapping results suggested that the heavy metal conditions of soils in the Ganhetan area were caused by nature and human activities. The As pollution in agricultural soils was the most serious, with an exceedance rate of 38.66%. Industrial areas were potential sources of soil heavy metal pollution in the study area. In summary, the Stacked AdaBoost ensemble learning model provides detailed and reliable data for agricultural ecological protection and industrial pollution control, allowing the effective management of heavy metal pollution sources. |
| first_indexed | 2024-04-12T21:17:09Z |
| format | Article |
| id | doaj.art-76844f13f42c427abf6abead37b87377 |
| institution | Directory Open Access Journal |
| issn | 1470-160X |
| language | English |
| last_indexed | 2024-04-12T21:17:09Z |
| publishDate | 2022-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Indicators |
| spelling | doaj.art-76844f13f42c427abf6abead37b873772022-12-22T03:16:24ZengElsevierEcological Indicators1470-160X2022-10-01143109330Estimating the heavy metal contents in farmland soil from hyperspectral images based on Stacked AdaBoost ensemble learningNan Lin0Ranzhe Jiang1Genjun Li2Qian Yang3Delin Li4Xuesong Yang5School of Geomatics and Prospecting Engineering, Jilin Jianzhu University, Changchun 130118, China; Corresponding author.School of Geomatics and Prospecting Engineering, Jilin Jianzhu University, Changchun 130118, ChinaQinghai Geological Survey Institute, Xining 810000, China; Key Laboratory of Geological Processes and Mineral Resources of the Northern Qinghai-Tibet Plateau, Xining 810012, ChinaSchool of Geomatics and Prospecting Engineering, Jilin Jianzhu University, Changchun 130118, ChinaQinghai Geological Survey Institute, Xining 810000, China; Key Laboratory of Geological Processes and Mineral Resources of the Northern Qinghai-Tibet Plateau, Xining 810012, ChinaQinghai Geological Survey Institute, Xining 810000, China; Key Laboratory of Geological Processes and Mineral Resources of the Northern Qinghai-Tibet Plateau, Xining 810012, ChinaHeavy metal pollution poses a huge challenge to the soil environment. With the increasing pollution level, the traditional monitoring methods cannot quickly obtain information on large-area pollution. Therefore, a large-scale mapping method with high precision is urgently needed to effectively control heavy metal pollution. This study explored a method for mapping soil heavy metal concentrations through hyperspectral images. On this basis, a new Stacked AdaBoost ensemble learning algorithm was constructed to construct the inversion model of soil heavy metal contents. The characteristic spectral bands of heavy metals were extracted as model input variables using Pearson’s correlation coefficient and successive projections algorithm. With three sets of heavy metal content data, the prediction accuracy and mapping outcomes of various machine learning methods were compared. Furthermore, the potential sources of heavy metal pollution in the study area were analyzed based on the Moran’s index. The results showed that the Stacked AdaBoost model was relatively stable with higher accuracy than traditional machine learning models. For Cr, Cu, and As, the determination coefficients (R2) of the verification set were 0.66, 0.61, and 0.74, respectively. Afterward, the results of this model were used to map the heavy metal concentration over the study area. The mapping results suggested that the heavy metal conditions of soils in the Ganhetan area were caused by nature and human activities. The As pollution in agricultural soils was the most serious, with an exceedance rate of 38.66%. Industrial areas were potential sources of soil heavy metal pollution in the study area. In summary, the Stacked AdaBoost ensemble learning model provides detailed and reliable data for agricultural ecological protection and industrial pollution control, allowing the effective management of heavy metal pollution sources.http://www.sciencedirect.com/science/article/pii/S1470160X22008020Hyperspectral imageSoil heavy metalsConcentration predictionStackingAdaBoost |
| spellingShingle | Nan Lin Ranzhe Jiang Genjun Li Qian Yang Delin Li Xuesong Yang Estimating the heavy metal contents in farmland soil from hyperspectral images based on Stacked AdaBoost ensemble learning Ecological Indicators Hyperspectral image Soil heavy metals Concentration prediction Stacking AdaBoost |
| title | Estimating the heavy metal contents in farmland soil from hyperspectral images based on Stacked AdaBoost ensemble learning |
| title_full | Estimating the heavy metal contents in farmland soil from hyperspectral images based on Stacked AdaBoost ensemble learning |
| title_fullStr | Estimating the heavy metal contents in farmland soil from hyperspectral images based on Stacked AdaBoost ensemble learning |
| title_full_unstemmed | Estimating the heavy metal contents in farmland soil from hyperspectral images based on Stacked AdaBoost ensemble learning |
| title_short | Estimating the heavy metal contents in farmland soil from hyperspectral images based on Stacked AdaBoost ensemble learning |
| title_sort | estimating the heavy metal contents in farmland soil from hyperspectral images based on stacked adaboost ensemble learning |
| topic | Hyperspectral image Soil heavy metals Concentration prediction Stacking AdaBoost |
| url | http://www.sciencedirect.com/science/article/pii/S1470160X22008020 |
| work_keys_str_mv | AT nanlin estimatingtheheavymetalcontentsinfarmlandsoilfromhyperspectralimagesbasedonstackedadaboostensemblelearning AT ranzhejiang estimatingtheheavymetalcontentsinfarmlandsoilfromhyperspectralimagesbasedonstackedadaboostensemblelearning AT genjunli estimatingtheheavymetalcontentsinfarmlandsoilfromhyperspectralimagesbasedonstackedadaboostensemblelearning AT qianyang estimatingtheheavymetalcontentsinfarmlandsoilfromhyperspectralimagesbasedonstackedadaboostensemblelearning AT delinli estimatingtheheavymetalcontentsinfarmlandsoilfromhyperspectralimagesbasedonstackedadaboostensemblelearning AT xuesongyang estimatingtheheavymetalcontentsinfarmlandsoilfromhyperspectralimagesbasedonstackedadaboostensemblelearning |