Hyperspectral Inversion of Soil Cu Content in Agricultural Land Based on Continuous Wavelet Transform and Stacking Ensemble Learning DOI Creative Commons
Kai Yang, Fan Wu,

Hongxu Guo

et al.

Land, Journal Year: 2024, Volume and Issue: 13(11), P. 1810 - 1810

Published: Nov. 1, 2024

Heavy metal pollution in agricultural land poses significant threats to both the ecological environment and human health. Therefore, rapid accurate prediction of heavy content soil is crucial for environmental protection remediation. Acknowledging limitations traditional single linear or nonlinear machine learning models terms accuracy, this study developed an ensemble model that integrates multiple with a random forest (RF) improve accuracy reliability. In study, we selected typical copper (Cu) polluted area Pearl River Delta Guangdong Province as research site collected Cu data indoor reflectance spectral from 269 surface samples. First, were preprocessed using Savitzky–Golay (SG) smoothing, multiplicative scattering correction (MSC), continuous wavelet transform (CWT) reduce noise interference. Next, principal components analysis (PCA) was employed dimensionality data, eliminating redundant features lowering computational complexity. Finally, based on dimensionality-reduced content, established stacked model, where base included SVR, PLSR, BPNN, XGBoost, RF serving meta-model estimate content. To evaluate performance stacking compared its individual models. The results indicate that, models, superior (R2 = 0.77; RMSE 7.65 mg/kg; RPD 2.29). This suggests integrated algorithm demonstrates greater robustness generalization capability. presents method estimation hyperspectral technology, ensuring robust supports policymakers making informed decisions about use, agriculture, protection.

Language: Английский

Handheld In Situ Methods for Soil Organic Carbon Assessment DOI Open Access
Nancy Loria, Rattan Lal,

Ranveer Chandra

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(13), P. 5592 - 5592

Published: June 29, 2024

Soil organic carbon (SOC) assessment is crucial for evaluating soil health and supporting sequestration efforts. Traditional methods like wet digestion dry combustion are time-consuming labor-intensive, necessitating the development of non-destructive, cost-efficient, real-time in situ measurements. This review focuses on handheld methodologies SOC estimation, underscoring their practicality reasonable accuracy. Spectroscopic techniques, visible near-infrared, mid-infrared, laser-induced breakdown spectroscopy, inelastic neutron scattering each offer unique advantages. Preprocessing such as external parameter orthogonalization standard normal variate, employed to eliminate moisture content particle size effects estimation. Calibration methods, partial least squares regression support vector machine, establish relationships between spectral reflectance, properties, SOC. Among 32 studies selected this review, 14 exhibited a coefficient determination (R2) 0.80 or higher, indicating potential accurate estimation using approaches. Each study meticulously adjusted factors range, pretreatment method, calibration model improve accuracy content, highlighting both methodological diversity continuous pursuit precision direct field Continued research validation imperative ensure across diverse environments. Thus, underscores devices with good leveraging that influence its precision. Crucial optimizing farming, these measurements, empowering land managers enhance promote sustainable management agricultural landscapes.

Language: Английский

Citations

7
Estimation of Maize Residue Cover Using Remote Sensing Based on Adaptive Threshold Segmentation and CatBoost Algorithm DOI Creative Commons

Nan Lin,

Xunhu Ma,

Ranzhe Jiang

et al.

Agriculture, Journal Year: 2024, Volume and Issue: 14(5), P. 711 - 711

Published: April 30, 2024

Maize residue cover (MRC) is an important parameter to quantify the degree of crop in field and its spatial distribution characteristics. It also a key indicator conservation tillage. Rapid accurate estimation maize mapping are great significance increasing soil organic carbon, reducing wind water erosion, maintaining water. Currently, large areas suffers from low modeling accuracy poor working efficiency. Therefore, how improve efficiency has become research hotspot. In this study, adaptive threshold segmentation (Yen) CatBoost algorithm integrated fused construct coverage method based on multispectral remote sensing images. The planting around Sihe Town Jilin Province, China, were selected as typical experimental regions, unmanned aerial vehicle (UAV) was employed capture images sample plots within area. Yen applied calculate analyze cover. successive projections (SPA) used extract spectral feature indices Sentinel-2A Subsequently, model indices, thereby plotting map results show that image outperforms traditional methods, with highest Dice coefficient reaching 81.71%, effectively improving recognition plots. By combining index calculation SPA algorithm, features extracted, such NDTI STI determined. These significantly correlated built using surpasses machine learning models, maximum determination (R2) 0.83 validation set. constructed algorithms enhances reliability estimating imagery, providing reliable data support services for precision agriculture

Language: Английский

Citations

4
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
Spatial Inversion of Soil Organic Carbon Content Based on Hyperspectral Data and Sentinel‐2 Images DOI

Xiaoyu Huang,

Xuemei Wang, Yanping Guo

et al.

Land Degradation and Development, Journal Year: 2025, Volume and Issue: unknown

Published: April 3, 2025

ABSTRACT Given that Sentinel‐2 (S2) multispectral images provide extensive spatial information and ground‐based hyperspectral data capture refined spectral characteristics, their integration can enhance both the comprehensiveness precision of surface acquisition. This study seeks to leverage these sources develop an optimized estimation model for accurately monitoring large‐scale soil organic carbon (SOC) content, thereby addressing current limitations in multi‐source fusion research. In this study, using mathematical transformation discrete wavelet transform process ground delta oasis Weigan Kuqa rivers Xinjiang, China, combination with S2 image, machine learning algorithms were employed construct models SOC content total variables characteristic variables, inversion oases was carried out. We found R ‐DWT‐H9 significantly correlation between ( p < 0.001). The accuracy constructed based on feature selected by SPA IRIV generally higher than variable models. IRIV‐RFR had highest stable capability. values 2 training validation sets 0.66 0.64, respectively. RMSE 1.5 g∙kg −1 , RPD > 1.4. interior oasis, mainly deficient (61.35%) or relatively (8.17%), while periphery it extremely (30.48%). Combine providing a reference evaluating fertility arid regions.

Language: Английский

Citations

0
Machine learning-based estimation of soil organic carbon in Thailand’s cash crops using multispectral and SAR data fusion combined with environmental variables DOI Creative Commons

Ousaha Sunantha,

Zhenfeng Shao,

Phodee Pattama

et al.

Geo-spatial Information Science, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 23

Published: April 4, 2025

Language: Английский

Citations

0
Land use modeling and carbon storage projections of the Bosten Lake Basin in China from 1990 to 2050 across multiple scenarios DOI Creative Commons
Kunyu Li, Xuemei Wang,

Feng Zhao

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 7, 2024

Given the escalating issue of global climate change, it is imperative to comprehend and quantify effects land use change on carbon storage (CS), which pertains not only preservation ecosystem functions but also directly influences equilibrium stability cycle. This study examines correlation between CS forecasts future spatial distribution CS, offers a reference for rational planning watershed space. Focusing Bosten Lake Basin Xinjiang in China, employing simulation (PLUS) model integrated valuation services trade-offs (InVEST) forecast stocks across three developmental scenarios, while examining shift center gravity autocorrelation their distribution. The findings derived from are as follows: (1) From 1990 2020, predominant type was grassland, there an upward trend areas cropland, forest land, built-up wetland, alongside downward water, unused land. (2) In long term, regional exhibits trend, with most significant increase anticipated EPS scenario. Grassland constitutes extensive reservoir Basin, wetlands exhibit highest sequestration potential. (3) alteration associated expansion or reduction major reservoirs types characterized by (4) consistent pronounced observed under EPS.

Language: Английский

Citations

2
Exploring the Potential of PRISMA Satellite Hyperspectral Image for Estimating Soil Organic Carbon in Marvdasht Region, Southern Iran DOI Creative Commons

Mehdi Golkar Amoli,

Mahdi Hasanlou, Ruhollah Taghizadeh‐Mehrjardi

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(12), P. 2149 - 2149

Published: June 13, 2024

Soil organic carbon (SOC) is a crucial factor for soil fertility, directly impacting agricultural yields and ensuring food security. In recent years, remote sensing (RS) technology has been highly recommended as an efficient tool producing SOC maps. The PRISMA hyperspectral satellite was used in this research to predict the map Fars province, located southern Iran. main purpose of investigate capabilities estimating examine processing techniques improving estimation accuracy. To end, denoising methods feature generation strategy have used. For denoising, three distinct algorithms were employed over image, including Savitzky–Golay + first-order derivative (SG FOD), VisuShrink, total variation (TV), their impact on compared four different methods: Method One (reflectance bands without shown M#1), Two (denoised with SG FOD, M#2), Three M#3), Four TV, M#4). Based results, best algorithm TV (Method or M#4), which increased accuracy by about 27% (from 40% 67%). After VisuShrink FOD improved 23% 18%, respectively. addition new proposed enhance further. This comprised two steps: first, number endmembers using Harsanyi–Farrand–Chang (HFC) algorithm, second, employing Principal Component Analysis (PCA) Independent (ICA) transformations generate high-level features based estimated from HFC algorithm. unfolded scenarios compare ability PCA ICA transformation features: Scenario (without adding any extra features, S#1), (incorporating S#2), S#3). Each these repeated each method (M#1–4). generation, added outputs Methods One, Three, Four. Subsequently, machine learning (LightGBM, GBRT, RF) modeling. results showcased highest when obtained Four—Scenario M#4–S#2), yielding R2 81.74%. Overall, significantly enhanced accuracy, escalating it approximately (M#1–S#1) 82% (M#4–S#2). underscores remarkable potential sensors studies.

Language: Английский

Citations

1
Hyperspectral Inversion of Soil Cu Content in Agricultural Land Based on Continuous Wavelet Transform and Stacking Ensemble Learning DOI
Kai Yang, Fan Wu,

Hongxu Guo

et al.

Published: Jan. 1, 2024

Language: Английский

Citations

1
Potential of Hyperspectral Data Combined With Optimal Band Combination Algorithm for Estimating Soil Organic Carbon Content in Lakeside Oasis DOI
Jixiang Yang, Xinguo Li, Xiaofei Ma

et al.

Land Degradation and Development, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 9, 2024

ABSTRACT Accurate estimation of soil organic carbon (SOC) content is essential for promoting regional sustainable agriculture and improving land quality. Visible near‐infrared (Vis‐NIR) near‐Earth remote sensing spectroscopy has become an effective alternative to the traditional time‐consuming costly methods due its high‐resolution nondestructive application, but it vulnerable redundancy spectral information overlap between bands. This study delves into potential optimal parameters estimating SOC in arid lakeside oases, using Bosten Lake Xinjiang, China, as a focal point. Soil samples (0–10 cm, 10–20 20–30 30–40 cm) were collected, their hyperspectral reflectance measured. The data underwent preprocessing techniques, including continuum removal (CR), standard normal variate (SNV), continuous wavelet transform (CWT). was predicted back propagation neural network models constructed based on one‐dimensional (1D), two‐dimensional (2D), three‐dimensional (3D) correlation coefficients. Results showcased effectiveness CWT method accentuating enhancing variable correlation. Among indices, 3D exhibited highest performance ( R 2 = 0.82, RPD 2.02 TDI‐1 at 0–10 cm; 0.85, 2.28 TDI‐2 0.83, 2.24 0.86, 2.53 TDI‐4 cm), followed by 2D then 1D. These insights offer guidance future strategies index determination, facilitating spatial distribution mapping advancing agricultural planning. They also have implications determining interpolation, which would contribute planning development.

Language: Английский

Citations

1
Comparative Analysis of Wavelet Transformation Techniques in Enhancing Soil Organic Carbon Detection Through Hyperspectral Imaging DOI
Bishal Roy, Vasit Sagan, Haireti Alifu

et al.

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Journal Year: 2024, Volume and Issue: unknown, P. 8010 - 8014

Published: July 7, 2024

Language: Английский

Citations

1