Spatial Assessment of Soil Organic Carbon Density Through Random Forests Based Imputation

Sreenivas, K.; Sujatha, G.; Sudhir, K.; Kiran, D. Vamsi; Fyzee, M. A.; Ravisankar, T.; Dadhwal, V. K.

doi:10.1007/s12524-013-0332-x

Cited by 40 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RF models are a type of multidecision tree model whose advantages include the ability to model numerical and categorical factors without considering the multicollinearity among factors (Breiman, ; Crookston & Finley, ). Sreenivas et al () used an RF model to map SOC density in the states of Andhra Pradesh and Karnataka (India) at a spatial resolution of 1 km, and the model performed well. Therefore, it is feasible to employ this model to predict the SOC contents of grasslands on the Loess Plateau, combined with the use of RS images and an RF model.…”

Section: Introductionmentioning

confidence: 99%

Large‐scale soil organic carbon mapping based on multivariate modelling: The case of grasslands on the Loess Plateau

Wang

Deng

et al. 2017

Land Degrad Dev

View full text Add to dashboard Cite

The Loess Plateau is considered one of the world's regions with severe soil erosion. Grasslands are widely distributed on the Loess Plateau, accounting for approximately 40% of the total area.Soil organic carbon (SOC) plays an important role in the terrestrial carbon cycle in this region.We compiled more than 1,000 measurements of plant biomass and SOC content derived from 223 field studies of grasslands on the Loess Plateau. Combined with meteorological factors (precipitation and air temperature) and the photosynthetically active radiation factor, the topsoil SOC contents of grasslands were predicted using the random forest (RF) regression algorithm. biomass and temperature should receive more attention due to increasing C sequestration.

show abstract

Section: Introductionmentioning

confidence: 99%

Large‐scale soil organic carbon mapping based on multivariate modelling: The case of grasslands on the Loess Plateau

Wang

Deng

et al. 2017

Land Degrad Dev

View full text Add to dashboard Cite

show abstract

“…The random forests model is a classification and regression method based on decision trees [ 47 ]. It is one of the most efficient algorithms in machine learning, and has been widely used in many domains, including environment [ 48 , 49 ], ecology [ 50 ], bioinformatics [ 51 , 52 ] and remote sensing [ 53 , 54 ]. The random forests model has also been used in physical time-activity classification in previous studies.…”

Section: Methodsmentioning

confidence: 99%

Refining Time-Activity Classification of Human Subjects Using the Global Positioning System

Liu

et al. 2016

PLoS ONE

View full text Add to dashboard Cite

BackgroundDetailed spatial location information is important in accurately estimating personal exposure to air pollution. Global Position System (GPS) has been widely used in tracking personal paths and activities. Previous researchers have developed time-activity classification models based on GPS data, most of them were developed for specific regions. An adaptive model for time-location classification can be widely applied to air pollution studies that use GPS to track individual level time-activity patterns.MethodsTime-activity data were collected for seven days using GPS loggers and accelerometers from thirteen adult participants from Southern California under free living conditions. We developed an automated model based on random forests to classify major time-activity patterns (i.e. indoor, outdoor-static, outdoor-walking, and in-vehicle travel). Sensitivity analysis was conducted to examine the contribution of the accelerometer data and the supplemental spatial data (i.e. roadway and tax parcel data) to the accuracy of time-activity classification. Our model was evaluated using both leave-one-fold-out and leave-one-subject-out methods.ResultsMaximum speeds in averaging time intervals of 7 and 5 minutes, and distance to primary highways with limited access were found to be the three most important variables in the classification model. Leave-one-fold-out cross-validation showed an overall accuracy of 99.71%. Sensitivities varied from 84.62% (outdoor walking) to 99.90% (indoor). Specificities varied from 96.33% (indoor) to 99.98% (outdoor static). The exclusion of accelerometer and ambient light sensor variables caused a slight loss in sensitivity for outdoor walking, but little loss in overall accuracy. However, leave-one-subject-out cross-validation showed considerable loss in sensitivity for outdoor static and outdoor walking conditions.ConclusionsThe random forests classification model can achieve high accuracy for the four major time-activity categories. The model also performed well with just GPS, road and tax parcel data. However, caution is warranted when generalizing the model developed from a small number of subjects to other populations.

show abstract

“…RF models have been widely applied in various scientific fields, including remote sensing [16], [17], ecological modeling [18], [19], [20], environmental science [21], [22], [23], [24], [25], [26], [27].…”

Section: Introductionmentioning

confidence: 99%

Comparison of artificial neural network, random forest and random perceptron forest for forecasting the spatial impurity distribution

Shichkin

Buevich

Sergeev

2018

AIP Conference Proceedings

View full text Add to dashboard Cite

show abstract

Spatial Assessment of Soil Organic Carbon Density Through Random Forests Based Imputation

Cited by 40 publications

References 18 publications

Large‐scale soil organic carbon mapping based on multivariate modelling: The case of grasslands on the Loess Plateau

Large‐scale soil organic carbon mapping based on multivariate modelling: The case of grasslands on the Loess Plateau

Refining Time-Activity Classification of Human Subjects Using the Global Positioning System

Comparison of artificial neural network, random forest and random perceptron forest for forecasting the spatial impurity distribution

Contact Info

Product

Resources

About