Hyperspectral estimation of petroleum hydrocarbon content in soil using ensemble learning method and LASSO feature extraction

Rapid and accurate estimation of soil petroleum hydrocarbon content is crucial for analyzing the degree of soil pollution and evaluating pollution status. Surface soil samples and hyperspectral measurements in the reservoir area in Lenghu Town, Qinghai Province, China, were viewed as research object...

Full description

Saved in:
Bibliographic Details
Published in:Environmental pollutants & bioavailability 2022-12, Vol.34 (1), p.308-320
Main Authors: Wu, Menghong, Lin, Nan, Li, Genjun, Liu, Hanlin, Li, Delin
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Decision trees
Ensemble learning
ERT
Feature extraction
GBDT
Hydrocarbons
Hyperspectral remote sensing
Hypotheses
Laboratories
LASSO algorithm
Machine learning
Petroleum
petroleum hydrocarbon content
Petroleum hydrocarbons
Pollutants
Regression analysis
Remote sensing
Soil
Soil analysis
Soil contamination
Soil fertility
Soil pollution
Soil surfaces
Spectrum analysis
Variables
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Rapid and accurate estimation of soil petroleum hydrocarbon content is crucial for analyzing the degree of soil pollution and evaluating pollution status. Surface soil samples and hyperspectral measurements in the reservoir area in Lenghu Town, Qinghai Province, China, were viewed as research objects, and the correlation between different spectral forms of original data and petroleum hydrocarbon content in soil was analyzed. To improve the estimation accuracy, we proposed a solution that introduces least absolute shrinkage and selection operator (LASSO) combined with extremely randomized trees (ERT) and gradient boosting decision tree (GBDT) ensemble learning for constructing hyperspectral estimation model. The results show: LASSO algorithm can not only solve the spectral multicollinearity problem effectively but also reduce the number and calculation complexity of soil hyperspectral variables to a great extent. Compared with traditional machine learning, ERT and GBDT perform superior. In particular, the estimation accuracy of the LASSO-GBDT model is the highest.
ISSN:2639-5932
2639-5940
DOI:10.1080/26395940.2022.2102543