Spatial distribution of soil carbon stocks in a semi-arid region of India

Mitran, Tarik; Mishra, Umakant; Lal, Rattan; Ravisankar, T.; Sreenivas, K.

doi:10.1016/j.geodrs.2018.e00192

Cited by 24 publications

(11 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regression residuals were then interpolated using ordinary kriging and added to the estimated Ln-transformed SOC stocks regression model surface ( Mishra et al, 2012 ). Several recent studies have also applied a variant of this technique using a geographically weighted regression approach to model the spatially varying regression relationships between the SOC stocks and its environmental controllers ( Zhang et al, 2011 ; Mishra and Riley, 2015 ; Mitran et al, 2018 ).…”

Section: Methodsmentioning

confidence: 99%

Ensemble Machine Learning Approach Improves Predicted Spatial Variation of Surface Soil Organic Carbon Stocks in Data-Limited Northern Circumpolar Region

et al. 2020

Self Cite

View full text Add to dashboard Cite

Various approaches of differing mathematical complexities are being applied for spatial prediction of soil properties. Regression kriging is a widely used hybrid approach of spatial variation that combines correlation between soil properties and environmental factors with spatial autocorrelation between soil observations. In this study, we compared four machine learning approaches (gradient boosting machine, multinarrative adaptive regression spline, random forest, and support vector machine) with regression kriging to predict the spatial variation of surface (0-30 cm) soil organic carbon (SOC) stocks at 250-m spatial resolution across the northern circumpolar permafrost region. We combined 2,374 soil profile observations (calibration datasets) with georeferenced datasets of environmental factors (climate, topography, land cover, bedrock geology, and soil types) to predict the spatial variation of surface SOC stocks. We evaluated the prediction accuracy at randomly selected sites (validation datasets) across the study area. We found that different techniques inferred different numbers of environmental factors and their relative importance for prediction of SOC stocks. Regression kriging produced lower prediction errors in comparison to multinarrative adaptive regression spline and support vector machine, and comparable prediction accuracy to gradient boosting machine and random forest. However, the ensemble median prediction of SOC stocks obtained from all four machine learning techniques showed highest prediction accuracy. Although the use of different approaches in spatial prediction of soil properties will depend on the availability of soil and environmental datasets and computational resources, we conclude that the ensemble median prediction obtained from multiple machine learning approaches provides greater spatial details and produces the highest prediction accuracy. Thus an ensemble prediction approach can be a better choice than any single prediction technique for predicting the spatial variation of SOC stocks.

show abstract

Section: Methodsmentioning

confidence: 99%

Ensemble Machine Learning Approach Improves Predicted Spatial Variation of Surface Soil Organic Carbon Stocks in Data-Limited Northern Circumpolar Region

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hence, there is need to explore more options for including geological covariates for DSM in India. Sreenivas et al (2016) and Mitran et al (2018) have used geological information obtained from Geological Survey of India as covariates for DSM. Bhukosh geoportal of Geological Survey of India (https://bhukosh.gsi.gov.in/) can be explored for geological information.…”

Section: Journal Pre-proofmentioning

confidence: 99%

Identifying opportunities to improve digital soil mapping in India: A systematic review

2022

View full text Add to dashboard Cite

“…Zhou et al, (2018) revealed that old SOC decomposition is more sensitive to temperature than younger components. Mitran et al,(2018) reported that the total carbon is stored in large amounts in Alfisols (0.49 Pg C) followed by Inceptisols (0.35 Pg C) and Entisols (0.27 Pg C) in the southern states of India. Guoet al, (2019) showed that soil structure is strongly influenced by the OC status in soil, so, any practice that leads to decline in OC will decrease in soil aggregate stability, infiltration rate and increase in susceptibility to compaction, runoff.…”

Section: Climate Change Impact On Soilmentioning

confidence: 99%

Study of Climate Change Impact on Crops and Soil Health in India: A Review

Manjeet¹,

Anurag²,

Niwas³

et al. 2022

View full text Add to dashboard Cite

Climate change such as rising temperature, atmospheric carbon dioxide levels, rainfall variability and altering soil physical, chemical and biological properties are observed all around the world. A review over impacts of clim ate change with relation to crops and soil health was done at Department of Agricultural Meteorology, CCS HAU Hisar. IPCC, 2021 provides new estimates of the chances of crossing the global warming level of 1.5°C in the next decades and finds that unless there are immediate, rapid and large-scale reductions in greenhouse gas emissions, limiting warming to close to 1.5°C or even 2°C will be beyond reach. Impacts of climate change on soil properties are long time process as weather elements induce Physio-chemical reaction with soil which happens slowly in relation to weather elements. Climate change is generally expectedto increase the crop yields due to CO2 fertilization, radiation use efficiency and longer growing season but on the other hand, beyond a critical limit it may develop stress conditions like water stress, sun burns, scorching, bark cracking, closure stomata, leaf senescence and abscission etc. that can decrease crop production. Acidification, sodicity and salinization problem can develop in soil due to increase in temperature and acidic rainfall. So it can be held that, climate change would have intensive impacts on cereal and horticulture crops health and production as well as on soil properties.

show abstract

Spatial distribution of soil carbon stocks in a semi-arid region of India

Cited by 24 publications

References 63 publications

Ensemble Machine Learning Approach Improves Predicted Spatial Variation of Surface Soil Organic Carbon Stocks in Data-Limited Northern Circumpolar Region

Ensemble Machine Learning Approach Improves Predicted Spatial Variation of Surface Soil Organic Carbon Stocks in Data-Limited Northern Circumpolar Region

Identifying opportunities to improve digital soil mapping in India: A systematic review

Study of Climate Change Impact on Crops and Soil Health in India: A Review

Contact Info

Product

Resources

About