4.7 Article

Soil organic matter mapping using INLA-SPDE with remote sensing based soil moisture indices and Fourier transforms decomposed variables

Related references

Note: Only part of the references are listed.
Article Agronomy

Responses of soil carbon dynamics to precipitation and land use in an Inner Mongolian grassland

Wenkuan Qin et al.

Summary: This study investigated the responses and mechanisms of soil organic carbon (SOC) decomposition and accumulation to precipitation and land-use in an Inner Mongolian grassland. The results showed that increased precipitation led to higher SOC accumulation, while decreased precipitation resulted in increased SOC decomposition. Compared to land-use regimes, precipitation treatments had a more significant impact on SOC dynamics.

PLANT AND SOIL (2023)

Article Environmental Sciences

Mapping soil erodibility in southeast China at 250 m resolution: Using environmental variables and random forest regression with limited samples

Zhiyuan Tian et al.

Summary: The study mapped soil erodibility (K factor) using a random forest (RF) model and environmental variables, identifying relief, climate, land surface temperature, and vegetation indexes as important predictors. By optimizing the model and generating a digital map, the spatial resolution of the K factor was significantly improved, demonstrating the effectiveness of the mapping approach.

INTERNATIONAL SOIL AND WATER CONSERVATION RESEARCH (2022)

Article Soil Science

The effectiveness of digital soil mapping with temporal variables in modeling soil organic carbon changes

Ren-Min Yang et al.

Summary: The study found that incorporating temporal variables into soil organic carbon prediction models can improve their accuracy. Utilizing temporal changes in environmental factors can better explain the spatiotemporal variability of soil organic carbon, which is crucial for future predictions of soil organic carbon changes.

GEODERMA (2022)

Article Soil Science

A multiple soil properties oriented representative sampling strategy for digital soil mapping

Lei Zhang et al.

Summary: The study introduced a representative sampling strategy for multiple soil properties by considering the environmental influences for each property, leading to more accurate predictions and mapping of soil properties.

GEODERMA (2022)

Article Soil Science

Prediction of soil organic matter using VNIR spectral parameters extracted from shape characteristics

Xiang Wang et al.

Summary: In this study, the effectiveness of spectral feature parameters (SFPs) in predicting soil organic matter (SOM) was tested for different regions, showing high correlation between RSFPs and characteristics of sandy soils and SOM. The importance of curve length (Lc) relative to area (Ac) in SOM prediction was highlighted. The feasibility of using RSFPs for SOM prediction and its spatial transferability were confirmed, with potential applications in predicting other soil properties in Northeast China.

SOIL & TILLAGE RESEARCH (2022)

Article Geosciences, Multidisciplinary

Spatial statistics and soil mapping: A blossoming partnership under pressure

Gerard B. M. Heuvelink et al.

Summary: Pedologists traditionally mapped soil by drawing boundaries, but the introduction of geostatistics and ordinary kriging in the 1980s revolutionized soil mapping. Machine learning techniques have also been adopted, but they lack transparency and spatial correlation considerations. Spatial statisticians and pedometricians have important roles in incorporating uncertainty and communicating it to end users.

SPATIAL STATISTICS (2022)

Article Agriculture, Multidisciplinary

Digital mapping of soil biological properties and wheat yield using remotely sensed, soil chemical data and machine learning approaches

Vahid Alah Jahandideh Mahjenabadi et al.

Summary: Predicting soil properties and wheat yield in the Southwest of Iran using machine learning algorithms and environmental covariates showed high accuracy in predicting wheat yield, with urease and alkaline phosphatase as major factors affecting yield and spatial variability.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

Article Geochemistry & Geophysics

Soil organic carbon accrual due to more efficient microbial utilization of plant inputs at greater long-term soil moisture

Itamar A. Shabtai et al.

Summary: High long-term soil moisture promotes the accumulation of soil organic carbon by enhancing the conversion of plant inputs into microbial biomass and influencing the mineral and chemical composition of the soil.

GEOCHIMICA ET COSMOCHIMICA ACTA (2022)

Article Soil Science

Temperature and moisture alter organic matter composition across soil fractions

Anna M. Cates et al.

Summary: Understanding the effects of temperature and moisture treatments on the composition of soil organic carbon is important for C and climate change modeling. This study analyzed the chemical composition of different aggregate fractions under different temperature and moisture treatments. The results showed that the composition of organic matter varied among different fractions, and both temperature and moisture had significant effects on the abundance of different carbon compounds. Moisture had the most pronounced effect on the composition of carbon within aggregates, while temperature had a stronger influence on carbon content in the silt and clay fractions.

GEODERMA (2022)

Article Soil Science

Soil texture controls added organic matter mineralization by regulating soil moisture-evidence from a field experiment in a maritime climate

Haichao Li et al.

Summary: Soil texture strongly influences the levels of soil organic carbon (SOC) and soil moisture, which in turn affects the decomposition of added organic matter (OM). This study found that silt loam soils have lower SOC levels compared to sandy soils in Western Europe. However, during periods of prolonged drought, silt loam soils with higher moisture availability favored OM mineralization more than sandy soils. The study also showed that capillary rise did not significantly increase OM decomposition in sandy soils. These findings highlight the importance of soil texture in regulating moisture and OM decomposition, and suggest that finer textured soils may experience greater SOC depletion under future climate scenarios.

GEODERMA (2022)

Review Soil Science

Digital mapping of GlobalSoilMap soil properties at a broad scale: A review

Songchao Chen et al.

Summary: Digital soil mapping (DSM) is increasingly used to deliver soil information efficiently. Research shows that while the number of DSM publications continues to grow exponentially, the majority focus on applications rather than methodology, with a particular emphasis on the mandatory soil properties for global soil mapping.

GEODERMA (2022)

Article Soil Science

Incorporating spatial uncertainty maps into soil sampling improves digital soil mapping classification accuracy in Ontario, Canada

Christopher Blackford et al.

Summary: Digital soil mapping combines soil plot data with environmental datasets to model variation in soil properties across a landscape. Optimizing site selection and sampling intensity can improve the accuracy of digital soil maps and reduce field costs. Generating preliminary uncertainty maps can guide subsequent field soil sample collections to significantly improve model performance. This study demonstrates the effectiveness of uncertainty maps in guiding sampling by simulating a multiyear soil sampling campaign and testing different uncertainty metrics and sampling intensity levels.

GEODERMA REGIONAL (2022)

Article Biodiversity Conservation

Response of soil moisture to vegetation and trade-off analysis in the hilly area of the Loess Plateau, China

Lei Han et al.

Summary: This study innovatively applied the piecewise linear regression (PLR) and nonparametric conditional quantile regression (NCQR) models to analyze vegetation survey data and soil moisture data. The results show a trade-off relationship between soil moisture and various vegetation parameters (VPs). The study also found that some irrational vegetation planting practices led to a decrease in soil moisture benefits. The findings have important implications for evaluating the trade-off relationship between soil moisture and vegetation.

ECOLOGICAL INDICATORS (2022)

Article Ecology

Comparison of the use of Landsat 8, Sentinel-2, and Gaofen-2 images for mapping soil pH in Dehui, northeastern China

Chenzhen Xia et al.

Summary: This study evaluates the effect of spatial resolution on soil pH mapping using different satellite images in the black soil region of northeastern China. The results show that the high spatial resolution GF-2 image performs slightly better in soil pH prediction compared to the Landsat 8 and Sentinel-2 images. However, the use of high-resolution remote sensing images may not significantly improve the accuracy of soil pH mapping compared to medium-resolution images.

ECOLOGICAL INFORMATICS (2022)

Article Soil Science

Comparing the prediction performance, uncertainty quantification and extrapolation potential of regression kriging and random forest while accounting for soil measurement errors

Bertin Takoutsing et al.

Summary: Geostatistics and machine learning have been widely used for modeling and predicting the spatial distribution of continuous soil variables. This study compared regression kriging and random forest in their ability to provide accurate predictions and quantify prediction uncertainties while considering measurement errors in the soil data. The results showed that regression kriging outperformed random forest in terms of accuracy, prediction uncertainties, and spatial extrapolation potential.

GEODERMA (2022)

Article Soil Science

National-scale maps for soil aggregate size distribution parameters using pedotransfer functions and digital soil mapping data products

Naveen K. Purushothaman et al.

Summary: This study comprehensively evaluated 26 ASD models and parameterized them using 1373 soil ASD datasets from a large region in India. The lognormal distribution-based Buchan model was found to best describe the majority of the datasets. PTFs were developed using random forest and extreme gradient boosting models, and the feasibility of using soil properties estimated through digital soil mapping was validated. National digital soil maps for ASD parameters were successfully created based on DSM-derived soil properties for the first time.

GEODERMA (2022)

Article Environmental Sciences

A CNN-LSTM Model for Soil Organic Carbon Content Prediction with Long Time Series of MODIS-Based Phenological Variables

Lei Zhang et al.

Summary: The spatial distribution of soil organic carbon (SOC) is crucial for assessing ecosystem services, climate change mitigation, and agricultural management. This study developed a CNN-LSTM model to predict SOC using static and dynamic environmental variables, including long-term vegetation phenology information. The results showed that adding phenological variables improved the accuracy of SOC prediction, demonstrating the potential effectiveness of the CNN-LSTM model for regional-scale SOC prediction.

REMOTE SENSING (2022)

Article Geosciences, Multidisciplinary

Daily soil moisture mapping at 1 km resolution based on SIVIAP data for desertification areas in northern China

Pinzeng Rao et al.

Summary: This study utilized multiple machine learning methods to downscale the coarse spatial resolution SMAP SM products and produce higher-spatial-resolution soil moisture data. The downscaled data showed good performance in assessing soil drought and reversing desertification, indicating its potential for application.

EARTH SYSTEM SCIENCE DATA (2022)

Article Computer Science, Information Systems

Extracting knowledge from legacy maps to delineate eco-geographical regions

Lin Yang et al.

Summary: This study proposes a method to extract knowledge from legacy area-class maps to formulate fuzzy membership functions for regionalization. The buffer zone approach effectively reduces uncertainties of boundaries between eco-region units on area-class maps, recommending a buffer distance of 10-15 km. The climatic zone map generated based on extracted fuzzy membership functions shows higher spatial stratification heterogeneity compared to the original map.

INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE (2021)

Article Geosciences, Multidisciplinary

Soil organic carbon prediction using phenological parameters and remote sensing variables generated from Sentinel-2 images

Xianglin He et al.

Summary: This study verified the effectiveness of phenological parameters and remote sensing predictors extracted from the Sentinel-2 EVI time series for DSM in farmland.

CATENA (2021)

Article Geosciences, Multidisciplinary

Combining laboratory measurements and proximal soil sensing data in digital soil mapping approaches

Sanaz Zare et al.

Summary: This study fills the gap in comparing and developing methods for integrating new sources of soil data for DSM by mapping electrical conductivities using real measurements and EM38MK2 measurements. The results show the utility of EM38MK2 data as surrogate input data for mapping soil salinity, with regression co-kriging identified as the best integration method. The impact of EM38MK2 data on performance gains increases as the sizes of real soil salinity measurements decrease, indicating a promising way to tackle constraints of DSM in areas where soil sensing as alternative data is accessible.

CATENA (2021)

Article Geosciences, Multidisciplinary

Digital mapping of the soil thickness of loess deposits over a calcareous bedrock in central France

Songchao Chen et al.

Summary: The study tested the prediction of loess thickness (TOL) by coupling a large soil dataset and environmental covariates. Using recursive feature elimination for variable selection and quantile regression forests for spatial modeling, the models showed good performance with reasonable prediction uncertainty. Airborne gamma-ray radiometric data and Sentinel 2 products were identified as important variables for the prediction of TOL.

CATENA (2021)

Article Soil Science

Spatiotemporal modelling of soil organic matter changes in Jiangsu, China between 1980 and 2006 using INLA-SPDE

Xiao-Lin Sun et al.

Summary: The study highlights the importance of understanding spatiotemporal changes in soil conditions for food production, environmental sustainability, and climate change adaptation. The INLA-SPDE model shows promise in accurately predicting soil properties and accounting for uncertainties in spatiotemporal soil modeling. The study recommends the use of INLA-SPDE within a hierarchical model as an effective method in studying spatiotemporal soil change.

GEODERMA (2021)

Article Soil Science

A self-training semi-supervised machine learning method for predictive mapping of soil classes with limited sample data

Lei Zhang et al.

Summary: This study introduced a self-training semi-supervised learning method for soil prediction in digital soil mapping, and conducted an empirical study in Heilongjiang Province, China. Results showed that the SSL method outperformed the SL method in terms of prediction accuracy when applying machine learning models, especially with limited sample data.

GEODERMA (2021)

Article Soil Science

Multi-algorithm comparison to predict soil organic matter and soil moisture content from cell phone images

Perry Taneja et al.

Summary: An accurate assessment of soil organic matter and soil moisture content is crucial for various applications. This study explores the use of computer vision and machine learning algorithms to predict these soil properties from cell phone images, with promising results indicating the potential for efficient proximal soil sensors.

GEODERMA (2021)

Article Environmental Sciences

Topographic Wetness Index calculation guidelines based on measured soil moisture and plant species composition

Martin Kopecky et al.

Summary: Different algorithms used in Topographic Wetness Index (TWI) calculation can impact the relationship between soil moisture and plant species composition. A study in temperate forests found that the method used to calculate TWI affects study conclusions.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

Article Public, Environmental & Occupational Health

Bayesian spatial modelling of geostatistical data using INLA and SPDE methods: A case study predicting malaria risk in Mozambique

Paula Moraga et al.

Summary: Bayesian spatial models are commonly used for data analysis in scientific fields such as health, ecology, and the environment. Traditional MCMC methods can be computationally intensive and may not be feasible for big data problems, while the INLA method offers a less-intensive alternative for fitting latent Gaussian models.

SPATIAL AND SPATIO-TEMPORAL EPIDEMIOLOGY (2021)

Article Computer Science, Interdisciplinary Applications

Spatial modelling of hydrothermal mineralization-related geochemical patterns using INLA plus SPDE and local singularity analysis*

Jian Wang et al.

Summary: The paper discusses the complexity of geochemical patterns in surficial media, and introduces a hybrid method (INLA + SPDE) to simulate the spatial distribution of geochemical variables and evaluate geochemical anomalies. The case study demonstrates the effectiveness of combining INLA + SPDE and LSA in identifying geochemical anomalies, thereby enriching tools for mineral exploration.

COMPUTERS & GEOSCIENCES (2021)

Article Public, Environmental & Occupational Health

Estimating ambient air pollutant levels in Suzhou through the SPDE approach with R-INLA

Neil Wright et al.

Summary: Spatio-temporal models can predict ambient air pollution levels, with Integrated nested Laplace approximations aiding Bayesian inference and facilitating SPDE spatial modelling. Meteorological variables can be useful predictors, but covariate misalignment must be addressed for accuracy. This method is used to estimate pollutant levels in a city with dispersed monitors, utilizing a two-stage approach to handle weather covariate misalignment.

INTERNATIONAL JOURNAL OF HYGIENE AND ENVIRONMENTAL HEALTH (2021)

Article Soil Science

Soil property mapping by combining spatial distance information into the Soil Land Inference Model (SoLIM)

Chengzhi Qin et al.

Summary: The Soil Land Inference Model (SoLIM), based on the Third Law of Geography, estimates soil property values by considering similarities in environmental conditions and spatial distances. Introducing a new method, SoLIM-IDW, incorporating spatial distance information, was shown to yield lower prediction errors than other modeling methods. Future work will focus on optimizing parameter values for different application contexts.

PEDOSPHERE (2021)

Article Environmental Sciences

Soil moisture content estimate with drying process segmentation using shortwave infrared bands

Jia Tian et al.

Summary: Soil moisture content (SMC) has been widely studied in various fields. Although many indices and models have been proposed to estimate SMC from reflectance data, there is an issue with accuracy for lower SMC levels. A segmentation method is introduced in this study to improve SMC estimation accuracy, which shows promising results compared to current methods.

REMOTE SENSING OF ENVIRONMENT (2021)

Article Soil Science

Food security impacts of the 4 per Thousand initiative

Rattan Lal

GEODERMA (2020)

Article Geography

Spatial prediction and mapping of soil pH across a tropical afro-montane landscape

Brian Otieno Odhiambo et al.

APPLIED GEOGRAPHY (2020)

Article Geography, Physical

Mapping salt marsh soil properties using imaging spectroscopy

Caiyun Zhang et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2019)

Article Geography, Physical

Development of soil moisture indices from differences in water absorption between shortwave-infrared bands

Jibo Yue et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2019)

Article Environmental Sciences

Land use and climate change effects on soil organic carbon in North and Northeast China

Yin Zhou et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2019)

Article Geosciences, Multidisciplinary

Spatial variability of soil texture fractions and pH in a flood plain (case study from eastern Iran)

Mohammad Reza Pahlavan-Rad et al.

CATENA (2018)

Article Soil Science

Mapping Soil Cation-Exchange Capacity using Bayesian Modeling and Proximal Sensors at the Field Scale

Nan Li et al.

SOIL SCIENCE SOCIETY OF AMERICA JOURNAL (2018)

Article Environmental Sciences

Evaluating a Bayesian modelling approach (INLA-SPDE) for environmental mapping

Jingyi Huang et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2017)

Article Statistics & Probability

POINT PROCESS MODELS FOR SPATIO-TEMPORAL DISTANCE SAMPLING DATA FROM A LARGE-SCALE SURVEY OF BLUE WHALES

Yuan Yuan et al.

ANNALS OF APPLIED STATISTICS (2017)

Article Geosciences, Multidisciplinary

Uncertainty-guided sampling to improve digital soil maps

Felix Stumpf et al.

CATENA (2017)

Review Statistics & Probability

A Review of Modern Computational Algorithms for Bayesian Optimal Design

Elizabeth G. Ryan et al.

INTERNATIONAL STATISTICAL REVIEW (2016)

Article Soil Science

Digital soil mapping: A brief history and some lessons

Budiman Minasny et al.

GEODERMA (2016)

Review Chemistry, Analytical

Estimation of Soil Moisture from Optical and Thermal Remote Sensing: A Review

Dianjun Zhang et al.

SENSORS (2016)

Article Computer Science, Interdisciplinary Applications

Bayesian Spatial Modelling with R-INLA

Finn Lindgren et al.

JOURNAL OF STATISTICAL SOFTWARE (2015)

Article Soil Science

The dimensions of soil security

Alex McBratney et al.

GEODERMA (2014)

Article Computer Science, Interdisciplinary Applications

Bayesian computing with INLA: New features

Thiago G. Martins et al.

COMPUTATIONAL STATISTICS & DATA ANALYSIS (2013)

Article Computer Science, Information Systems

An integrative hierarchical stepwise sampling strategy for spatial sampling and its application in digital soil mapping

Lin Yang et al.

INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE (2013)

Article Statistics & Probability

An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach

Finn Lindgren et al.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY (2011)

Article Biology

Influence of spring and autumn phenological transitions on forest ecosystem productivity

Andrew D. Richardson et al.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES (2010)

Review Statistics & Probability

Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations

Havard Rue et al.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY (2009)

Article Soil Science

Spatial Prediction of Soil Organic Matter Content Using Cokriging with Remotely Sensed Data

Chunfa Wu et al.

SOIL SCIENCE SOCIETY OF AMERICA JOURNAL (2009)

Article Statistics & Probability

Stationary process approximation for the analysis of large spatial datasets

Sudipto Banerjee et al.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY (2008)

Article Soil Science

The Matern function as a general model for soil variograms

B Minasny et al.

GEODERMA (2005)

Review Soil Science

On digital soil mapping

AB McBratney et al.

GEODERMA (2003)

Article Statistics & Probability

Bayesian measures of model complexity and fit

DJ Spiegelhalter et al.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY (2002)

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)