Estimation of Farmland Soil Organic Carbon Stocks by Using Single-Year and Multi-Year Landsat Imagery: A Comparison Across Different Time Periods and Indicator Combinations DOI

Xinyao Hao,

Jizhen Zhang, Yansong Wang

и другие.

Опубликована: Янв. 1, 2023

Soil carbon pool in the farmland has short sequestration period, large storage, and strong activities, so accurate soil organic (SOC) estimation is vital to analyze globe cycle maintain food security. With requirement of SOC quantification mapping at scale, earth observation satellite imagery provide a valuable data source obtain relationships between environmental predictors content. However, datasets needed be assessed for prediction, work labor-intensive time-consuming. The main aim this study determine optimized time period length indicators or indicator combinations farmland.In study, case was carried out Nongan, national grain-producing county which located Mollisol region Northeastern China. A time-series Landsat 8 Operational Land Imager (OLI) multi-temporal images were obtained from 2013 2018, aiming generate represented changes, across single-date, single-year, multi-years. properties (S), terrain attributes (T), vegetation conditions (V), farm management practices (F) employed predict spatial distribution by using random forest (RF) model both bare crop cover conditions. Meanwhile, performance different lengths evaluated prediction SOC. results showed that single-date single-year cannot reliable site. Multi-temporal multiple years (3 longer) produced with coefficient determination (R2) root mean squared error (RMSE) 0.89-0.91 1.83-1.85 g/kg, respectively. Four types combination (S+T+V+F) best validation 5470 field observations, followed V+F, S+V+F, T+V+F combinations. longer), contributions properties, attributes, 6-9%, 7-9%, 55-58%, 27-29% condition, This provides possible way shorter choose open up opportunity

Язык: Английский

SHAP values accurately explain the difference in modeling accuracy of convolution neural network between soil full-spectrum and feature-spectrum DOI
Liang Zhong, Guo Xi, Meng Ding

и другие.

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 217, С. 108627 - 108627

Опубликована: Янв. 13, 2024

Язык: Английский

Процитировано

21
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

и другие.

Remote Sensing, Год журнала: 2025, Номер 17(4), С. 678 - 678

Опубликована: Фев. 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.

Язык: Английский

Процитировано

1
Assessing the potential of multi-source remote sensing data for cropland soil organic matter mapping in hilly and mountainous areas DOI
Peng Li, Xiaobo Wu,

C Feng

и другие.

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

Опубликована: Авг. 12, 2024

Язык: Английский

Процитировано

6
Complementarity of Sentinel-1 and Sentinel-2 Data for Soil Salinity Monitoring to Support Sustainable Agriculture Practices in the Central Bolivian Altiplano DOI Open Access
J. W. Sirpa-Poma, Frédéric Satgé, Ramiro Pillco Zolá

и другие.

Sustainability, Год журнала: 2024, Номер 16(14), С. 6200 - 6200

Опубликована: Июль 19, 2024

Soil salinization will affect 50% of global cropland areas by 2050 and represents a major threat to agricultural production food sovereignty. As soil salinity monitoring is costly time consuming, many regions the world undertake very limited observation (in space time), preventing accurate assessment hazards. In this context, study assesses relative performance Sentinel-1 radar Sentinel-2 optical images, combination two, for changes in at high spatial temporal resolution, which essential evaluate mitigation measures required sustainable adaptation agriculture practices. For purpose, an improved learning database made 863 electrical conductivity (i.e., salinity) observations considered training/validation step Random Forest (RF) model. The RF model successively trained with (1) only Sentinel-1, (2) (3) both -2 features using Genetic Algorithm (GA) reduce multi-collinearity independent variables. Using k-fold cross validation (3-fold), overall accuracy (OA) values 0.83, 0.88 0.95 are obtained when considering Sentinel-2, as Therefore, these results highlight clear complementarity Sentinel-1) Sentinel-2) images improve mapping, OA increases approximately 10% 7% compared alone. Finally, pre-sowing maps over five-year period (2019–2023) presented benefit proposed procedure support management lands context on regional scale.

Язык: Английский

Процитировано

4
Using the MSFNet Model to Explore the Temporal and Spatial Evolution of Crop Planting Area and Increase Its Contribution to the Application of UAV Remote Sensing DOI Creative Commons

Gui Hu,

Zhigang Ren, Jian Chen

и другие.

Drones, Год журнала: 2024, Номер 8(9), С. 432 - 432

Опубликована: Авг. 26, 2024

Remote sensing technology can be used to monitor changes in crop planting areas guide agricultural production management and help achieve regional carbon neutrality. Agricultural UAV remote is efficient, accurate, flexible, which quickly collect transmit high-resolution data real time precision agriculture management. It widely monitoring, yield prediction, irrigation However, the application of faces challenges such as a high imbalance land cover types, scarcity labeled samples, complex changeable coverage types long-term images, have brought great limitations monitoring cultivated changes. In order solve abovementioned problems, this paper proposed multi-scale fusion network (MSFNet) model based on input feature series further combined MSFNet Model Diagnostic Meta Learning (MAML) methods, using particle swarm optimization (PSO) optimize parameters neural network. The method applied crops tomatoes. experimental results showed that average accuracy, F1-score, IoU optimized by PSO + MAML (PSML) were 94.902%, 91.901%, 90.557%, respectively. Compared with other schemes U-Net, PSPNet, DeepLabv3+, has better effect solving problem ground objects image samples provides technical support for subsequent technology. study found change different was closely related climatic conditions policies, helps use realization

Язык: Английский

Процитировано

3
Application of Google Earth Engine to Monitor Greenhouse Gases: A Review DOI Creative Commons

D. R. Wilson,

Gebrekidan Worku Tefera, Ram L. Ray

и другие.

Data, Год журнала: 2025, Номер 10(1), С. 8 - 8

Опубликована: Янв. 11, 2025

Google Earth Engine (GEE) is a cloud-based platform revolutionizing geospatial analysis by providing access to vast satellite datasets and computational capabilities for monitoring environmental societal issues. It incorporates machine learning (ML) techniques algorithms as part of its tools analyzing processing large data. This review explores the diverse applications GEE in mitigating greenhouse gas emissions uptakes. built on Google’s infrastructure visualizing large-scale datasets. offers (GHG) understanding their impact. By leveraging GEE’s capabilities, researchers have developed analyze remotely sensed data accurately quantify GHG examines progress trends applications, focusing carbon dioxide (CO2), methane (CH4), nitrous oxide/nitrogen (N2O/NO2) emissions. discusses integration with different methods challenges opportunities optimizing ensuring interoperability. Furthermore, it highlights role pinpointing emission hotspots, demonstrated studies insights into precise mapping GHGs, this aims advance research decision-making processes climate change.

Язык: Английский

Процитировано

0
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

и другие.

Land, Год журнала: 2025, Номер 14(4), С. 677 - 677

Опубликована: Март 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

Язык: Английский

Процитировано

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

и другие.

Geo-spatial Information Science, Год журнала: 2025, Номер unknown, С. 1 - 23

Опубликована: Апрель 4, 2025

Язык: Английский

Процитировано

0
Soil Organic Carbon Retrieval Using a Machine Learning Approach from Satellite and Environmental Covariates in the Lower Brazos River Watershed, Texas, USA DOI Creative Commons
Birhan Getachew Tikuye, Ram L. Ray

Applied Computing and Geosciences, Год журнала: 2025, Номер unknown, С. 100252 - 100252

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Enhancing soil organic carbon prediction in coastal farmlands using multi-source remote sensing data and machine learning DOI Creative Commons

Yongpeng Deng,

Xue Zhang, Yong Yang

и другие.

Smart Agricultural Technology, Год журнала: 2025, Номер unknown, С. 101059 - 101059

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0