Prediction of Soil Organic Carbon across Different Land‐use Patterns

Abstract

Mathematical modeling has widely been used to predict soil organic ingful in creating a real picture of spatial distribution carbon (SOC). However, there are characteristics of the models such as over simplification, ignorance of complex nonlinear interactions of SOC. Attempts have been made to estimate global etc., which limit their use in accurately assessing the distribution of the SOC using the pedon database and extrapolating them C across the landscapes. Artificial neural network (ANN) modeling to soil units of the world soil map (Bohn, 1976, 1982; approach that provides a tool to solve complex problems related to Batjes, 1996; Buringh, 1984; Kimble et al., 1990). The larger data sets was therefore used here to predict SOC contents pedon database of the USDA Soil Conservation Service across different land use patterns in a study conducted in Sri Lanka. and related organizations has been used to estimate the Selection of variables was made using a priori knowledge of the regional distribution of organic C in the USA (Kern, relationships between the variables. Thus, soils of the sites were sam-1994). However, previous studies indicated that there pled and analyzed for organic C by internal heat of dilution (Ci) and are uncertainties associated with such SOC estimates external heat of dilution (Ce), and the results were presented as grams and often related to variations in soil map scales and per kilogram (g kg Ϫ1). In addition, some landscape attributes and environmental parameters of the sites were also collected. The pre-series. As a whole the uncertainties associated with meadictive performance of ANN was compared with multi-linear regres-suring and detecting changes in soil C pools remain sion (MLR) models. The best ANN model predicted the measured high, both at individual sites and extrapolating site-level Ci content with R 2 of 0.92. However, comparison of the two types of data to regional, national, or global scales (Vance, 2003). models indicated less bias and high accuracy of the ANN compared Accurate and precise approaches yet to be available for with MLR in predicting Ci, but the reverse for Ce. In order to better assessing the effect of management practices and land predict Ce, it is recommended to use other architectures of neural use change on the soil C for the purpose of incorporation networks and training algorithms for improving predictive accuracy. of this important pool into future C accounting systems. The predictive capability of the ANN developed with easily available The Kyoto Protocol, for instance, limits reporting of C climatic and terrain data are of importance in predicting SOC with sequestration activities to "measurable and verifiable" minimum cost, labor, and time. pools (Vance, 2003). Mathematical modeling has been used to predict soil C evolution (Jenkinson and Rayner, 1977; Parton et al.

Detection of the effects of management and physical factors on forest soil carbon stock variability in semiarid conditions using parametric and nonparametric methods

“…On the other hand, ANNs showed a higher ability to simulate management effects on SOC variability. This ability is in contract with Somaratne et al (2005) findings. The ANN models could contribute 45% of SOC variability to physical variables (Fig.…”

Spatial upscaling using thematic maps: An analysis of uncertainties in permafrost soil carbon estimates

“…Upscaling or "bottom up" approaches to quantifying ecosystem C storage or gas-fluxes in remote arctic areas often use an approach were point measurements are upscaled to areal coverage using thematic maps or remote sensing products [e.g., Tarnocai and Lacelle, 1996;Heikkinen et al, 2004;Ping et al, 2008;Schuur et al, 2009;Tarnocai et al, 2009;Hugelius et al, 2011;Johnson et al, 2011]. For studies of more accessible areas, such as agricultural landscapes, researchers have successfully employed more sophisticated means of assessing e.g., soil organic carbon (SOC) stocks [e.g., Somaratne et al, 2005;Simbahan and Dobermann, 2006;Panda et al, 2008;Goidts et al, 2009]. However, for large and remote areas of periglacial terrain, the applications of data intensive approaches remain elusive.…”

Using artificial neural network models to produce soil organic carbon content distribution maps across landscapes

“…From a land management perspective, SOC plays important roles in reducing soil erosion and improving crop productivity. For this reason, SOC content has been used as a required input variable for a number of hydrological simulation models (Somaratne et al 2005) and many landscape level models for estimating soil water retention (Koekkoek and Booltink 1999), cation exchange capacity (Amini et al 2005), and soil bulk density (Tranter et al 2007). Field soil survey has been the primary method for determining soil properties including SOC.…”

“…Statistical models with predictive powers could potentially overcome the problem of interpolation methods (Chaplot et al 2001;Cerri et al 2004;Chen 2000Chen , 2005Sumfleth and Duttmann 2008). But empirical models derived from traditional statistical methods may hinder the real relationships between the SOC and independent data because the relationships are rarely linear in nature (Somaratne et al 2005).…”