Synergetic Use of Bare Soil Composite Imagery and Multitemporal Vegetation Remote Sensing for Soil Mapping (A Case Study from Samara Region’s Upland) DOI Creative Commons
А. В. Чинилин, Nikolai Lozbenev, P. M. Shilov

и другие.

Land, Год журнала: 2024, Номер 13(12), С. 2229 - 2229

Опубликована: Дек. 20, 2024

This study presents an approach for predicting soil class probabilities by integrating synthetic composite imagery of bare with long-term vegetation remote sensing data and survey data. The goal is to develop detailed maps the agro-innovation center “Orlovka-AIC” (Samara Region), a focus on lithological heterogeneity. Satellite were sourced from cloud-filtered collection Landsat 4–5 7 images (April–May, 1988–2010) 8–9 (June–August, 2012–2023). Bare surfaces identified using threshold values NDVI (<0.06), NBR2 (<0.05), BSI (>0.10). Synthetic generated calculating median reflectance across available spectral bands. Following adoption no-till technology in 2012, average additionally calculated assess condition agricultural lands. Seventy-one sampling points within classified both Russian WRB classification systems. Logistic regression was applied pixel-based prediction. model achieved overall accuracy 0.85 Cohen’s Kappa coefficient 0.67, demonstrating its reliability distinguishing two main classes: agrochernozems agrozems. resulting map provides robust foundation sustainable land management practices, including erosion prevention use optimization.

Язык: Английский

Satellite images reveal soil color changes in typical black soil region of China: brighter, redder, and yellower DOI
Wang Xiang, Sijia Li, Chaosheng Zhang

и другие.

CATENA, Год журнала: 2025, Номер 254, С. 108958 - 108958

Опубликована: Март 19, 2025

Язык: Английский

Процитировано

0
Enhanced Surface Soil Moisture Prediction Through Dual-Satellite Spectral Fusion DOI
Kamal Khosravi Aqdam, Amin Nouri, Naser Miran

и другие.

Earth Systems and Environment, Год журнала: 2025, Номер unknown

Опубликована: Апрель 28, 2025

Язык: Английский

Процитировано

0
Challenges of earth remote sensing data during geological exploration DOI
Andrey Samsonov,

Yu. A. Churikov,

A. R. Ibragimov

и другие.

International Journal of Environmental Science and Technology, Год журнала: 2025, Номер unknown

Опубликована: Май 10, 2025

Язык: Английский

Процитировано

0
A global numerical classification of the soil surface layer DOI Creative Commons
Alexandre M.J.‐C. Wadoux, Alex B. McBratney

Geoderma, Год журнала: 2024, Номер 447, С. 116915 - 116915

Опубликована: Май 25, 2024

The quest for a global soil classification system has been long-standing challenge in science. There currently exist two, seemingly disjoint, systems, the USDA Soil Taxonomy and World Reference Base Resources, many regional national systems. While both systems are acknowledged as international, there remain various examples of their shortcoming accounting topsoil features, local applications communication with established This calls numerical that addresses these discrepancies achieves harmonization existing In this paper, we report on development natural layer — opposed to profile entities, first step towards achieving comprehensive not based priori defined classes. We implemented modelling approach set predicted key properties available globally surface same depth range 0–5 cm. was partitioned into number homogeneous disjoint classes using k-means clustering algorithm. Next, investigated pattern variation clusters association property map principal component analysis. A three-component nomenclature is derived transformed space class-specific centroids account uneven distribution space. show it possible build data-based objective taxonomic layers, sets properties, separately, coalesce identifiable or manifest discernible spatial and/or pedological patterns. grouping logical categories better define diagnostic horizon features suggest new ones. general-purpose world also potential assessing change designing monitoring surveys.

Язык: Английский

Процитировано

3
Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement DOI Creative Commons
José Lucas Safanelli, Tomislav Hengl, Leandro Parente

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Дек. 17, 2023

Abstract Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, bottleneck its more widespread adoption the need establishing large reference datasets training machine learning (ML) models, which called spectral libraries (SSLs). Similarly, prediction capacity of new samples also subject number diversity types conditions represented in SSLs. To help bridge this gap enable hundreds stakeholders collect affordable data by leveraging centralized open resource, Spectroscopy Global Good has created Open Spectral Library (OSSL). In paper, we describe procedures collecting harmonizing several SSLs incorporated into OSSL, followed exploratory analysis predictive modeling. The results 10-fold cross-validation with refitting show that, general, mid-infrared (MIR)-based models significantly accurate than visible near-infrared (VisNIR) or (NIR) models. From independent model evaluation, found Cubist comes out as best-performing ML algorithm calibration delivery reliable outputs (prediction uncertainty representation flag). Although many well predicted, total sulfur, extractable sodium, electrical conductivity performed poorly all regions, some other nutrients physical performing one two regions (VisNIR Neospectra NIR). Hence, use based solely on variations limitations. This study presents discusses resources were developed from aspects opening data, current limitations, future development. With genuinely science project, hope OSSL becomes driver community accelerate pace scientific discovery innovation.

Язык: Английский

Процитировано

7
Time-series of Landsat-based spectral indices for continental Europe for 2000--2022 to support soil health monitoring DOI Creative Commons
Xuemeng Tian, Tomislav Hengl, Davide Consoli

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Апрель 12, 2024

Abstract As the importance of soil health in supporting European ecosystems and agriculture becomes increasingly critical, effective monitoring is essential for its protection restoration. This paper describes production quality assessment a data cube (17TB size) derived from Landsat Analysis Ready Data version 2 (ARD V2) dataset tailored monitoring, featuring multiple spectral indices, long time span, high resolution, analysis readiness. The focus was on indices health: Normalized Difference Vegetation Index (NDVI), Soil Adjusted (SAVI), Fraction Absorbed Photosynthetically Active Radiation (FAPAR), Snow (NDSI), Water (NDWI), Tillage (NDTI), minimum (minNDTI), Bare (BSF), Number Seasons (NOS) Crop Duration Ratio (CDR). set available with resolution 30~m, bimonthly (i.e. one image per two months), annual, long-term throughout continental Europe, including Ukraine, UK, Turkey, covering 2000 to 2022. results assessment, both visual examination plausibility check ground survey data, show that these can effectively capture environmental processes offer insight into through aspects such as vegetation, crop status, tillage practices, exposure directly or serve covariates digital mapping. In particular, BSF shows strong negative correlation -0.73 coverage 2006 2017, suggesting an detection exposure. minNDTI moderate positive 0.57 Eurostat practices indicating it provides valuable information intensity, although not definitively. analysis-ready cloud-optimized, making suitable applications property mapping development comprehensive approaches Europe.

Язык: Английский

Процитировано

2
Digital Mapping of Agricultural Soils Texture of the Brazilian Cerrado Biome DOI

Marcelo Procópio Pelegrino,

Luiz Roberto Guimarães Guilherme,

Geraldo Jânio Lima

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0
Recognizing and reducing effects of moisture-salt coexistence on soil organic matter spectral prediction：From laboratory to satellite DOI
Danyang Wang,

Yayi Tan,

Cheng Li

и другие.

Soil and Tillage Research, Год журнала: 2024, Номер 248, С. 106397 - 106397

Опубликована: Дек. 5, 2024

Язык: Английский

Процитировано

0
Utilization of Sentinel-2 satellite imagery for correlation analysis of shoreline variation and incident waves: Application to Wonpyeong-Chogok Beach, Korea DOI Creative Commons
Euihyun Kim, Changbin Lim, Jung Lyul Lee

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 136, С. 104316 - 104316

Опубликована: Дек. 12, 2024

Язык: Английский

Процитировано

0
Prediction of Soil Colour using Vis-NIR Spectroscopy and Machine Learning Models DOI Open Access

Devid Kumar Sahu,

Y. M. Sharma,

G. S. Tagore

и другие.

Asian Journal of Soil Science and Plant Nutrition, Год журнала: 2024, Номер 10(4), С. 657 - 676

Опубликована: Дек. 17, 2024

Soil colour is a critical indicator of soil properties and conditions, influencing various agronomic environmental factors. A total 2216 surface samples (0-15 cm) were collected from the Kymore Plateau Satpura Hill zone Madhya Pradesh, using Global Positioning System (GPS) for precise location. parameters measured in field Munsell chart, while chemical analysis was conducted laboratory following standard procedures. Additionally, spectra recorded spectroradiometer under conditions. The results showed that hues ranged 10R, 10YR, 2.5Y, 2.5YR, 5Y, 5R, 5YR, to 7.5YR, Values Chroma varied 2 7 1 8, respectively. Correlation revealed negative correlations between RGB components organic carbon, with r values -0.114**, -0.071**, -0.101* R, G, B, Polynomial models best fit relationship value chroma carbon (SOC), equations Y = 0.086x² - 0.860x + 7.528 (R² 0.982) 0.018x² 0.249x 6.126 0.948), linear observed available phosphorus (P), equation -0.873 13.92 0.922). In addition, machine learning models, including PLSR, SVM, Random Forest, ANN, XGBoost, LightGBM, CatBoost, ELM algorithms, used predict parameters. Among these, Forest XGBoost demonstrated performance predicting (L*, a*, b*, B), model accuracies 83.6%, 80.9%, 83.0%, 84.3%, 83.7%, 83.4%, variation depicted maps generated GIS can also serve as covariates mapping, offering comprehensive insights into soil's properties.

Язык: Английский

Процитировано

0