Spatial prediction of soil organic carbon from data on large and variable spatial supports. II. Mapping temporal change

2012 ◽  
Vol 23 (2) ◽  
pp. 148-161 ◽  
Author(s):  
T.G. Orton ◽  
N.P.A. Saby ◽  
D. Arrouays ◽  
C. Walter ◽  
B. Lemercier ◽  
...  
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Temporal Change ◽  
Spatial Prediction

Soil Organic Carbon Prediction at National Scale (Germany)

2020 ◽  
Author(s):  
Ali Sakhaee ◽  
Anika Gebauer ◽  
Mareike Ließ ◽  
Axel Don
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Agricultural Soils ◽  
Model Performance ◽  
Spatial Prediction ◽  
Spatial Modelling ◽  
Agricultural Landscapes ◽  
Boosted Regression Trees ◽  
Environmental Drivers ◽  
National Scale

<p>Soil Organic Carbon (SOC) plays a crucial role in agricultural ecosystems. However, its abundance is spatially variable at different scales. In recent years, machine learning (ML) algorithms have become an important tool in the spatial prediction of SOC at regional to continental scales. Particularly in agricultural landscapes, the prediction of SOC is a challenging task.</p><p>In this study, our aim is to evaluate the capability of two ML algorithms (Random Forest and Boosted Regression Trees) for topsoil (0 to 30 cm) SOC prediction in soils under agricultural use at national scale for Germany. In order to build the models, 50 environmental covariates representing topography, climate factors, land use as well as soil properties were selected. The SOC data we used was from the German Agricultural Soil inventory (2947 sampling points). A nested 5-fold cross-validation was used for model tuning and evaluation. Hyperparameter tuning for both ML algorithms was done by differential evolution optimization. </p><p>This approach allows exploring an extensive set of field data in combination with state of the art pedometric tools. With a strict validation scheme, the geospatial-model performance was assessed. Current results indicate that the spatial SOC variation is to a minor extent predictable with the considered covariate data (<30% explained variance). This may partly be explained by a non-steady state of SOC content in agricultural soils with environmental drivers. We discuss the challenges of geo-spatial modelling and the value of ML algorithms in pedometrics.</p>

scholarly journals Improving the spatial prediction of soil organic carbon using environmental covariates selection: A comparison of a group of environmental covariates

CATENA ◽  
2022 ◽  
Vol 208 ◽  
pp. 105723
Author(s):  
Mojtaba Zeraatpisheh ◽  
Younes Garosi ◽  
Hamid Reza Owliaie ◽  
Shamsollah Ayoubi ◽  
Ruhollah Taghizadeh-Mehrjardi ◽  
...  
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Spatial Prediction ◽  
Environmental Covariates

A review of sampling designs for the measurement of soil organic carbon in Australian grazing lands

2010 ◽  
Vol 32 (2) ◽  
pp. 227 ◽  
Author(s):  
D. E. Allen ◽  
M. J. Pringle ◽  
K. L. Page ◽  
R. C. Dalal
Keyword(s):  
Microbial Biomass ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Plant Growth ◽  
Temporal Change ◽  
Organic C ◽  
Soil C ◽  
Efficient Sampling ◽  
Soc Stock ◽  
Grazing Lands

The accurate measurement of the soil organic carbon (SOC) stock in Australian grazing lands is important due to the major role that SOC plays in soil productivity and the potential influence of soil C cycling on Australia’s greenhouse gas emissions. However, the current sampling methodologies for SOC stock are varied and potentially conflicting. It was the objective of this paper to review the nature of, and reasons for, SOC variability; the sampling methodologies commonly used; and to identify knowledge gaps for SOC measurement in grazing lands. Soil C consists of a range of biological materials, in various SOC pools such as dissolved organic C, micro- and meso-fauna (microbial biomass), fungal hyphae and fresh plant residues in or on the soil (particulate organic C, light-fraction C), the products of decomposition (humus, slow pool C) and complexed organic C, and char and phytoliths (inert, passive or resistant C); and soil inorganic C (carbonates and bicarbonates). Microbial biomass and particulate or light-fraction organic C are most sensitive to management or land-use change; resistant organic C and soil carbonates are least sensitive. The SOC present at any location is influenced by a series of complex interactions between plant growth, climate, soil type or parent material, topography and site management. Because of this, SOC stock and SOC pools are highly variable on both spatial and temporal scales. This creates a challenge for efficient sampling. Sampling methods are predominantly based on design-based (classical) statistical techniques, crucial to which is a randomised sampling pattern that negates bias. Alternatively a model-based (geostatistical) analysis can be used, which does not require randomisation. Each approach is equally valid to characterise SOC in the rangelands. However, given that SOC reporting in the rangelands will almost certainly rely on average values for some aggregated scale (such as a paddock or property), we contend that the design-based approach might be preferred. We also challenge soil surveyors and their sponsors to realise that: (i) paired sites are the most efficient way of detecting a temporal change in SOC stock, but destructive sampling and cumulative measurement errors decrease our ability to detect change; (ii) due to (i), an efficient sampling scheme to estimate baseline status is not likely to be an efficient sampling scheme to estimate temporal change; (iii) samples should be collected as widely as possible within the area of interest; (iv) replicate of laboratory analyses is a critical step in being able to characterise temporal change. Sampling requirements for SOC stock in Australian grazing lands are yet to be explicitly quantified and an examination of a range of these ecosystems is required in order to assess the sampling densities and techniques necessary to detect specified changes in SOC stock and SOC pools. An examination of techniques that can help reduce sampling requirements (such as measurement of the SOC fractions that are most sensitive to management changes and/or measurement at specific times of the year – preferably before rapid plant growth – to decrease temporal variability), and new technologies for in situ SOC measurement is also required.

scholarly journals Nonstationary spatial prediction of soil organic carbon: Implications for stock assessment decision making

2019 ◽  
Vol 13 (1) ◽  
pp. 165-188 ◽  
Author(s):  
Mark D. Risser ◽  
Catherine A. Calder ◽  
Veronica J. Berrocal ◽  
Candace Berrett
Keyword(s):  
Decision Making ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Stock Assessment ◽  
Spatial Prediction

Spatial prediction of soil organic carbon from data on large and variable spatial supports. I. Inventory and mapping

2012 ◽  
Vol 23 (2) ◽  
pp. 129-147 ◽  
Author(s):  
T. G. Orton ◽  
N. P. A. Saby ◽  
D. Arrouays ◽  
C. Walter ◽  
B. Lemercier ◽  
...  
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Spatial Prediction

Spatial-temporal change of soil organic carbon in Anhui Province of East China

2021 ◽  
pp. e00415
Author(s):  
Ming-Song Zhao ◽  
Shi-Qi Qiu ◽  
Shi-Hang Wang ◽  
De-Cheng Li ◽  
Gan-Lin Zhang
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Temporal Change ◽  
Anhui Province ◽  
East China

Soil organic-carbon dynamics after 80 years of cropping a Dark Brown Chernozem

1993 ◽  
Vol 73 (1) ◽  
pp. 133-136 ◽  
Author(s):  
C. M. Monreal ◽  
H. H. Janzen
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Temporal Change ◽  
Soil Samples ◽  
Crop Rotations ◽  
Surface Samples ◽  
Soil Organic Carbon Dynamics ◽  
Over Time ◽  
Dry Combustion

The temporal change of soil organic-carbon (Corg) was studied in soil samples taken from long-term crop rotations at Lethbridge. Between 1910 and 1990, net Corg losses for the 0–15 cm depth varied between 23% under fallow–wheat (FW) and 21% under fallow–wheat–wheat (FWW) and 17% under continuous wheat (W). Analysis of variance and an LSD test indicated that in 1990 the surface Corg concentrations were similar among all crop rotations. Corg in the 15–30 cm depth decreased over time and was significantly lower than in surface samples. Key words: Organic carbon, dry combustion, cold-wet dichromate digestion

Sign in / Sign up

Export Citation Format

Share Document