Digital mapping of soil organic carbon using remote sensing data: A systematic review

CATENA, Год журнала: 2023, Номер 232, С. 107409 - 107409

Опубликована: Июль 27, 2023

Язык: Английский

---

Estimation of soil organic carbon by combining hyperspectral and radar remote sensing to reduce coupling effects of soil surface moisture and roughness

Geoderma, Год журнала: 2024, Номер 444, С. 116874 - 116874

Опубликована: Апрель 1, 2024

Soil organic carbon (SOC) is important in the global cycle. Accurate estimation of SOC content cultivated land a prerequisite for evaluating sequestration potential and quality soils. However, existing prediction studies based on hyperspectral remote sensing neglect spectral response physical properties surface soil, leading to inadequate model generalization. With exponential growth data, development pixel-level soil correction methods multi-source data has become an interesting challenging topic. This method aims minimize effect spectra, thus addressing poor spatiotemporal transferability models due uncertain variations properties. In this study, strategy constructed using satellite image (HSI) synthetic aperture radar (SAR) images through multi-order polynomial regression convolutional neural networks. considers variables such as moisture (SM) root mean square height (RMSH) roughness. The were established 80 samples collected from Site 1. Afterward, performance both verified remaining 25 1 50 2. results showed that: 1) SM RMSH pixel spectrum can be significantly reduced after correcting HSI strategy. correlation coefficients between corrected ground-based increase by over 60 % compared with those original spectrum. 2) improves accuracy mapping capability content, highest RP2 0.743 RMSEP 3.455 g/kg at 3) Compared HSI-based model, network 2 5.082 5.454 g/kg, increased 0.390 0.409, respectively. 4) When predicting raw HIS, contribute more than bias, having larger bias RMSH. findings study emphasize influence research SAR data.

Язык: Английский

---

Using Machine-Learning Algorithms to Predict Soil Organic Carbon Content from Combined Remote Sensing Imagery and Laboratory Vis-NIR Spectral Datasets

Remote Sensing, Год журнала: 2023, Номер 15(17), С. 4264 - 4264

Опубликована: Авг. 30, 2023

Understanding spatial and temporal variability in soil organic carbon (SOC) content helps simultaneously assess fertility several parameters that are strongly associated with it, such as structural stability, nutrient cycling, biological activity, aeration. Therefore, it appears necessary to monitor SOC regularly investigate rapid, non-destructive, cost-effective approaches for doing so, proximal remote sensing. To increase the accuracy of predictions content, this study evaluated combining sensing time series laboratory spectral measurements using machine deep-learning algorithms. Partial least squares (PLS) regression, random forest (RF), deep neural network (DNN) models were developed Sentinel-2 (S2) 58 sampling points bare according three approaches. In first approach, only S2 bands used calibrate compare performance models. second, indices, Sentinel-1 (S1) S1 moisture added separately during model calibration evaluate their effects individually then together. third, we indices incrementally tested influence on accuracy. Using bands, DNN outperformed PLS RF (ratio interquartile distance RPIQ = 0.79, 1.36 1.67, respectively). Additional information improved performances calibration, yielding most stable improvement among iterations. Including equivalent calculated spectra obtained under conditions prediction SOC, use two achieved good validation (mean 2.01 1.77,

Язык: Английский

---

Combing transfer learning with the OPtical TRApezoid Model (OPTRAM) to diagnosis small-scale field soil moisture from hyperspectral data

Agricultural Water Management, Год журнала: 2024, Номер 298, С. 108856 - 108856

Опубликована: Май 9, 2024

Язык: Английский

---

A critical systematic review on spectral-based soil nutrient prediction using machine learning

Environmental Monitoring and Assessment, Год журнала: 2024, Номер 196(8)

Опубликована: Июль 4, 2024

Язык: Английский

---

Effects of land use/cover changes on soil organic carbon stocks in Qinghai-Tibet plateau: A comparative analysis of different ecological functional areas based on machine learning methods and soil carbon pool data

Journal of Cleaner Production, Год журнала: 2023, Номер 434, С. 139854 - 139854

Опубликована: Дек. 3, 2023

Язык: Английский

---

The inversion of arid-coastal cultivated soil salinity using explainable machine learning and Sentinel-2

Ecological Indicators, Год журнала: 2024, Номер 166, С. 112364 - 112364

Опубликована: Июль 29, 2024

Язык: Английский

---

Remote estimation of soil organic carbon under different land use types in agroecosystems of Eastern China

CATENA, Год журнала: 2023, Номер 231, С. 107369 - 107369

Опубликована: Июль 12, 2023

Язык: Английский

---

Assessing the potential of multi-source remote sensing data for cropland soil organic matter mapping in hilly and mountainous areas

CATENA, Год журнала: 2024, Номер 245, С. 108312 - 108312

Опубликована: Авг. 12, 2024

Язык: Английский

---

Soil Organic Carbon Estimation and Transfer Framework in Agricultural Areas Based on Spatiotemporal Constraint Strategy Combined with Active and Passive Remote Sensing

Remote Sensing, Год журнала: 2025, Номер 17(2), С. 333 - 333

Опубликована: Янв. 19, 2025

Mapping soil organic carbon (SOC) plays a crucial role in agricultural productivity and water management. This study discusses the potential of active passive remote sensing for SOC estimation modeling areas, incorporating synthetic aperture radar (SAR) data (L-band quad-polarization C-band dual-polarization), multi-spectrum (MS) data, brightness temperature (TB) data. The performance five advanced machine learning regression (MLR) models was assessed, focusing on spatial interpolation accuracy cross-spatial transfer accuracy, using two field observation datasets validation. Results indicate that when MS alone is comparable to TB alone, both perform slightly better than SAR Radar cross-polarization ratio index, microwave polarization difference shortwave infrared reflectance, parameters (elevation moisture) demonstrate high correlation with measured SOC. Incorporating temporal features, as opposed single-phase allows each model reach its upper limit accuracy. MLR algorithm satisfactory, Gaussian process (GPR) demonstrating optimal performance. When SAR, MS, or are used individually modeling, errors (RMSE) 0.637 g/kg, 0.492 0.229 g/kg SMAPVEX12 sampling campaign, 0.706 0.454 0.474 SMAPVEX16-MB respectively. After moisture topographic factors, above RMSEs further reduced by 57.8%, 35.6%, 3.5% SMAPVEX12, 18.4%, 8.8%, 3.4% SMAPVEX16-MB, However, remains limited (RMSE = 0.866–1.043 0.995–1.679 different sources). To address this, this reduces uncertainties introducing terrain factors sensitive 0.457–0.516 0.799–1.198 proposed framework, based provides guidance high-resolution regional-scale mapping applications.

Язык: Английский

---