Research on the Quantitative Inversion of Soil Iron Oxide Content Using Hyperspectral Remote Sensing and Machine Learning Algorithms in the Lufeng Annular Structural Area of Yunnan, China DOI Creative Commons
Yingtao Qi, Shu Gan, Xiping Yuan

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(21), P. 7039 - 7039

Published: Oct. 31, 2024

This study used hyperspectral remote sensing to rapidly, economically, and non-destructively determine the soil iron oxide content of Dinosaur Valley annular tectonic region Lufeng, Yunnan Province. The laboratory determined original spectral reflectance (OR) in 138 surface samples. We first subjected OR data Savizky-Golay smoothing, followed by four transformations-continuum removal reflectance, reciprocal logarithm standard normal variate first-order differential reflectance-which improved signal-to-noise ratio curves highlighted features. Then, we combined correlation coefficient method (CC), competitive adaptive reweighting algorithm, Boruta algorithm screen out characteristic wavelength. From this, constructed linear partial least squares regression model, nonlinear random forest, XGBoost machine learning algorithms. results show that CC-Boruta can effectively remove any noise irrelevant information improve model's accuracy stability. model better captures complex relationship between spectra content, thus improving its accuracy. provides a relevant reference for rapid accurate inversion using data.

Language: Английский

Rapid detection of soil heavy metal pollution using hyperspectral data and multiscale spatial network DOI Creative Commons
Haicheng Wang, S. Xiao,

R. T. Shen

et al.

Environmental Technology & Innovation, Journal Year: 2025, Volume and Issue: 37, P. 104031 - 104031

Published: Jan. 15, 2025

Language: Английский

Citations

1
Potential of satellite hyperspectral imaging technology in soil health analysis: A step towards environmental sustainability DOI
Amitava Dutta, Brejesh Lall, Shilpi Sharma

et al.

Environmental Monitoring and Assessment, Journal Year: 2025, Volume and Issue: 197(3)

Published: Feb. 19, 2025

Language: Английский

Citations

1
A Fusion XGBoost Approach for Large-Scale Monitoring of Soil Heavy Metal in Farmland Using Hyperspectral Imagery DOI Creative Commons
Xuqing Li,

Huitao Gu,

Ruiyin Tang

et al.

Agronomy, Journal Year: 2025, Volume and Issue: 15(3), P. 676 - 676

Published: March 11, 2025

Heavy metal pollution of farmland is worsened by the excessive introduction heavy elements into soil systems, posing a substantial threat for global food security and human health. The traditional laboratory-based methods monitoring metals are limited large-scale applications, while hyperspectral imagery data-based still face accuracy challenges. Therefore, fusion XGBoost model based on superposition ensemble learning packaging proposed with high using imagery. We took Xiong’an New Area, Hebei Province, as study area, acquired content chemical analysis. XGB-Boruta-PCC algorithm was used precise feature selection to obtain final modeled spectral response features. On this basis, performance indicators Optuna-optimized were compared linear nonlinear models. optimal extended entire region drawing spatial distribution map content. results suggested that method effectively achieved double dimensionality reduction high-dimensional data, extracting features contribution, which, combined model, exhibited greater general estimation accuracies (Pb) in (i.e., Pb: R2 = 0.82, RMSE 11.58, MAE 9.89). mapping indicated there exceedances southwest parts west over research region. Factories activities potential causes Pb contamination farmland. In conclusion, innovative can quickly accurately achieve farmland, ZY-1-02E spaceborne proving be reliable tool

Language: Английский

Citations

1
Inversion of heavy metal elements in characteristic agricultural areas of Shanxi Province: Application of the airborne multimodular imaging spectrometer DOI
Hongyu Wang, Juan Wang,

Wei Zhou

et al.

Ecological Indicators, Journal Year: 2025, Volume and Issue: 173, P. 113393 - 113393

Published: March 29, 2025

Language: Английский

Citations

1
A remote sensing analysis method for soil heavy metal pollution sources at site scale considering source-sink relationships DOI

Yulong Wang,

Bin Zou,

Xuegang Zuo

et al.

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 946, P. 174021 - 174021

Published: June 17, 2024

Language: Английский

Citations

5
Monitoring Heavy Metals and Metalloids in Soils and Vegetation by Remote Sensing: A Review DOI Creative Commons
Viktoriia Lovynska, Bagher Bayat, Roland Bol

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(17), P. 3221 - 3221

Published: Aug. 30, 2024

Heavy metal contamination in soils and vegetation poses a significant problem due to its toxicity persistence. Toxic effects on include not only impaired growth, reduced yields, even plant death but also biodiversity loss ecosystem degradation. Addressing this issue requires comprehensive monitoring remediation efforts mitigate the environmental, human health, ecological impacts. This review examines state-of-the-art methodologies advancements remote sensing applications for detecting heavy soil subsequent vegetation. By synthesizing current research findings technological developments, offers insights into efficacy potential of terrestrial ecosystems. However, studies focus regression AI methods link spectral reflectances indices concentrations, which limited transferability other areas, times, discretizations, elements. We conclude that one important way forward is more thorough understanding simulation related physico-chemical processes plants their signatures. would offer profound basis individual circumstances allow disentangling from stressors such as droughts or salinity.

Language: Английский

Citations

4
Improving Soil Heavy Metal Lead Inversion Through Combined Band Selection Methods: A Case Study in Gejiu City, China DOI Creative Commons
Ping He,

Xianfeng Cheng,

Xingping Wen

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(3), P. 684 - 684

Published: Jan. 23, 2025

Hyperspectral technology has become increasingly important in monitoring soil heavy metal pollution, yet hyperspectral data often contain substantial band redundancy, and selection methods are typically limited to single algorithms or simple combinations. Multi-algorithm combinations for remain underutilized. To address this gap, study, conducted Gejiu, Yunnan Province, China, proposes a multi-algorithm method enable the rapid prediction of lead (Pb) contamination levels soil. construct preliminary Pb content model, initial spectral bands utilized including CARS (Competitive Adaptive Reweighted Sampling), GA (Genetic Algorithm), MI (mutual information), SPA (Successive Projections WOA (Whale Optimization Algorithm). The results indicated that achieved highest modeling accuracy. Building on this, combined WOA-based was developed, such as WOA-CARS, WOA-GA, WOA-MI, WOA-SPA, with multi-level optimization further refined by (e.g., WOA-GA-MI, WOA-CARS-MI, WOA-SPA-MI). showed WOA-GA-MI model exhibited optimal performance, achieving an average R2 0.75, improvements 0.32, 0.11, 0.02 over full-spectrum WOA-selected WOA-GA respectively. Additionally, response analysis identified 22 common essential inversion. proposed not only significantly enhances accuracy but also provides new insights into optimizing selection, serving valuable scientific foundation assessing contamination.

Language: Английский

Citations

0
A Model Combining Sensitive Vegetation Indices and Fractional-Order Differential Characteristic Bands for SPAD Value Estimation in Cd-Contaminated Rice Leaves DOI Creative Commons

Rongcai Tian,

Bin Zou, Shenxin Li

et al.

Agriculture, Journal Year: 2025, Volume and Issue: 15(3), P. 311 - 311

Published: Jan. 31, 2025

Rapid and nondestructive estimation of leaf SPAD values is crucial for monitoring the effects cadmium (Cd) stress in rice. To address issue low accuracy value models due to loss spectral information existing studies, a new model, which combines sensitive vegetation indices (VIss) fractional order differential characteristic bands (FODcb), proposed this study. validate effectiveness three scenarios, with no Cd contamination, 1.0 mg/kg 1.4 were set up. Leaf reflectance measured during critical growth period Subsequently, 16 constructed, difference (FOD) transformation was applied process data. The variable importance projection (VIP) algorithm employed extract VIss FODcb. Finally, random forest (RF) used construct models, + FODcb-RF, VIss-RF. estimated showed that: (1) there significant between contamination those treated on 31st 87th days after transplanting; (2) 400–773 nm range estimating values, Cd-contaminated scenario exhibiting higher visible wavelength than Cd-uncontaminated scenario; (3) compared individual FODcb-RF Viss-RF combined model (VIss FODcb-RF) improved values. Particularly, Viss FOD1.2cb-RF provided best performance, R2v, RMSEv, RPDv 0.821, 2.621, 2.296, respectively. In conclusion, study demonstrates combining FODcb accurately rice This finding will provide methodological reference remote sensing

Language: Английский

Citations

0
Soil zinc content estimation using GF-5 hyperspectral image with mitigation of soil moisture influence DOI

Songtao Ding,

Weihao Wang, Weichao Sun

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 235, P. 110318 - 110318

Published: March 30, 2025

Language: Английский

Citations

0
Soil pollution and remediation: emerging challenges and innovations DOI Creative Commons
Hao Chen, Bin Gao, Li Y

et al.

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 13

Published: April 29, 2025

This perspective addresses the critical issue of soil pollution, exacerbated by rapid urbanization, intensive agriculture, and climate change, which introduces a complex mix contaminants such as heavy metals, pesticides, per- polyfluoroalkyl substances, microplastics into soil. These pollutants pose severe risks to environmental health agricultural productivity altering functionality contaminant mobility. summarizes innovative monitoring remediation technologies, including advanced sensors bioremediation strategies, that enable real-time detection effective management pollutants. The integration artificial intelligence machine learning offers significant advancements in predicting managing contamination dynamics. Furthermore, discusses challenges future directions pollution research, particularly need for robust policy frameworks international cooperation effectively manage mitigate contamination. Emphasizing multidisciplinary approach, this study calls enhanced global standards, public engagement, continued scientific research develop sustainable solutions ensure protection vital resources generations.

Language: Английский

Citations

0