Multifaceted Spectral Feature Interaction Effects Enhance Remote Sensing Inversion of Chlorophyll in Cadmium-Stressed Rice DOI
Jie Liu, Zhao Zhang, Xingwang Liu

et al.

Published: Jan. 1, 2023

AbstractEnhancing the remote sensing inversion of chlorophyll (Chl) in rice under cadmium (Cd) stress can help improve accuracy and efficiency large-scale monitoring soil Cd pollution. Spectral characteristics capture subtle changes Chl content stress; however, a more comprehensive exploration relationship between multifaceted spectral features has not been fully conducted. Moreover, most studies have overlooked impact interaction term effects on effectiveness prediction. In this study, sensitive to were selected, including first-order derivatives, envelope removal, inverse logarithmic transformations, wavelet parameters, characteristic using an interpretable neural network (GAMI-Net) quantify screen interactive terms. The application GAMI-Net model elucidated mechanisms by which these their respond stress. robustness enhanced grid-search algorithm based k-Fold cross-validation technique (GS-kFCV). Comparisons made traditional Vegetation Index (VI), Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN) models. Subsequently, Sentinel-2 satellite data used optimal invert modeling area prediction area, was validated with actual data. results indicated that improved model, compared original, showed increase 18.4% coefficient determination (R2) 90.9% ratio performance deviation (RPD), 76.5% reduction root mean square error (RMSE) test set. when other machine learning models, achieved R2 value 0.90 This surpassed values VI, RF, SVM, ANN, 0.71, 0.74, 0.34, respectively. addition, outperformed terms RMSE RPD metrics, 0.09 3.2, respectively, indicating higher robustness. Interpretative analysis significant variables revealed red-edge position accounted for 25.3% 17.7% variation stress, whereas 39.4% variation. predicted measurements 0.7988, 0.7233. Therefore, novel method proposed study exhibited high robustness, providing new insights into use estimation

Language: Английский

High-Accuracy Mapping of Soil Organic Carbon by Mining Sentinel-1/2 Radar and Optical Time-Series Data with Super Ensemble Model DOI Creative Commons

Zhibo Cui,

Songchao Chen, Bifeng Hu

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(4), P. 678 - 678

Published: Feb. 17, 2025

Accurate digital soil organic carbon mapping is of great significance for regulating the global cycle and addressing climate change. With advent remote sensing big data era, multi-source multi-temporal techniques have been extensively applied in Earth observation. However, how to fully mine time-series high-accuracy SOC remains a key challenge. To address this challenge, study introduced new idea mining data. We used 413 topsoil samples from southern Xinjiang, China, as an example. By (Sentinel-1/2) 2017 2023, we revealed temporal variation pattern correlation between Sentinel-1/2 SOC, thereby identifying optimal time window monitoring using integrating environmental covariates super ensemble model, achieved Southern China. The results showed following aspects: (1) windows were July–September July–August, respectively; (2) modeling accuracy sensor integrated with was superior single-source alone. In model based on data, cumulative contribution rate Sentinel-2 51.71% higher than that Sentinel-1 data; (3) stacking model’s predictive performance outperformed weight average simple models. Therefore, covariates, driven represents strategy mapping.

Language: Английский

Citations

1
Mapping Soil Organic Carbon by Integrating Time-Series Sentinel-2 Data, Environmental Covariates and Multiple Ensemble Models DOI Creative Commons

Zhibo Cui,

Songchao Chen, Bifeng Hu

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(7), P. 2184 - 2184

Published: March 30, 2025

Despite extensive use of Sentinel-2 (S-2) data for mapping soil organic carbon (SOC), how to fully mine the potential time-series S-2 still remains unclear. To fill this gap, study introduced an innovative approach mining data. Using 200 top samples as example, we revealed temporal variation patterns in correlation between SOC and subsequently identified optimal monitoring time window SOC. The integration environmental covariates with multiple ensemble models enabled precise arid region southern Xinjiang, China (6109 km2). Our results indicated following: (a) exhibited both interannual monthly variations, while July August is SOC; (b) adding properties texture information could greatly improve accuracy prediction models. Soil contribute 8.85% 61.78% best model, respectively; (c) among different models, stacking model outperformed weight averaging sample terms performance. Therefore, our proved that spectral from window, integrated has a high accurate mapping.

Language: Английский

Citations

0
Improving in-situ spectral estimation of wetland soil organic carbon by integrating multiple optimization strategies DOI
Hongyi Li, Jiang-Tao Yang, Bifeng Hu

et al.

CATENA, Journal Year: 2025, Volume and Issue: 255, P. 109078 - 109078

Published: April 23, 2025

Language: Английский

Citations

0
Spatiotemporal Responses of River Water Quality Characterization to Multi-Source Pollution: A Case Study of the Jinjing Watershed in Subtropical China DOI
Lingling Tong, Feng Liu, Fatimah Md. Yusoff

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Unraveling the threshold and interaction effects of environmental variables on soil organic carbon mapping in plateau watershed DOI Creative Commons
Chengqi Zhang, Yiyun Chen, Yujiao Wei

et al.

Geoderma, Journal Year: 2024, Volume and Issue: 450, P. 117032 - 117032

Published: Sept. 23, 2024

Language: Английский

Citations

3
A Novel Framework for Improving Soil Organic Carbon Mapping Accuracy by Mining Temporal Features of Time-Series Sentinel-1 Data DOI Creative Commons

Zhibo Cui,

Bifeng Hu, Songchao Chen

et al.

Land, Journal Year: 2025, Volume and Issue: 14(4), P. 677 - 677

Published: March 23, 2025

Digital soil organic carbon (SOC) mapping is used for ecological protection and addressing global climate change. Sentinel-1 (S-1) microwave radar remote sensing data offer critical insights into SOC dynamics through tracking variations in moisture vegetation characteristics. Despite extensive studies using S-1 mapping, most focus on either single or multi-date periods without achieving satisfactory results. Few have investigated the potential of time-series high-accuracy mapping. This study utilized from 2017 to 2021 analyze temporal correlation between southern Xinjiang, China. The primary objective was determine optimal monitoring period SOC. Within this period, feature subsets were extracted variable selection algorithms. performance partial least squares regression, random forest, convolutional neural network–long short-term memory (CNN-LSTM) models evaluated a 10-fold cross-validation approach. findings revealed following: (1) exhibited both interannual monthly variations, with July October. volume reduced by 73.27% relative initial dataset when determined. (2) Introducing significantly improved CNN-LSTM model (R2 = 0.80, RPD 2.24, RMSE 1.11 g kg⁻1). Compared single-date 0.23) 0.33) data, R2 increased 0.57 0.47, respectively. (3) newly developed vertical–horizontal maximum mean annual cumulative indices made significant contribution (17.93%) Therefore, integrating selection, deep learning offers enhancing accuracy digital

Language: Английский

Citations

0
Prediction of soil heavy metal contents in urban residential areas and the strength of deep learning: A case study of Beijing DOI
Ying Hou,

Wenhao Ding,

Tian Xie

et al.

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 950, P. 175133 - 175133

Published: July 30, 2024

Language: Английский

Citations

2
Interpretable Digital Soil Organic Matter Mapping Based on Geographical Gaussian Process-Generalized Additive Model (GGP-GAM) DOI Creative Commons

Liangwei Cheng,

Mingzhi Yan,

Wenhui Zhang

et al.

Agriculture, Journal Year: 2024, Volume and Issue: 14(9), P. 1578 - 1578

Published: Sept. 11, 2024

Soil organic matter (SOM) is a key soil component. Determining its spatial distribution necessary for precision agriculture and to understand the ecosystem services that provides. However, field SOM studies are severely limited by time costs. To obtain spatially continuous map of content, it conduct digital mapping (DSM). In addition, there vital need both accuracy interpretability in mapping, which difficult achieve with conventional DSM models. address above issues, particularly coefficient variation (SVC) regression model, Geographic Gaussian Process Generalized Additive Model (GGP-GAM), was used. The root mean squared error (RMSE), average (MAE), adjusted determination (adjusted R2) this model Leizhou area 7.79, 6.01, 0.33 g kg−1, respectively. GGP-GAM more accurate compared other three models (i.e., Geographical Random Forest, Geographically Weighted Regression, Regression Kriging). Moreover, patterns covariates affecting interpreted coefficients each predictor individually. results show can be used high-precision content good interpretability. This technique will turn contribute agricultural sustainability decision making.

Language: Английский

Citations

2
Improved soil organic matter monitoring by using cumulative crop residue indices derived from time-series remote sensing images in the central black soil region of China DOI
Meiwei Zhang, Xiaolin Sun, Meinan Zhang

et al.

Soil and Tillage Research, Journal Year: 2024, Volume and Issue: 246, P. 106357 - 106357

Published: Nov. 13, 2024

Language: Английский

Citations

2
A long-term global Mollisols SOC content prediction framework: Integrating prior knowledge, geographical partitioning, and deep learning models with spatio-temporal validation DOI
Xiangtian Meng, Yilin Bao, Xinle Zhang

et al.

Remote Sensing of Environment, Journal Year: 2024, Volume and Issue: 318, P. 114592 - 114592

Published: Dec. 31, 2024

Language: Английский

Citations

2