The final models included soil depth, L*, and a* as independent variables (dry soils R2 = 0.7978 and MSPE = 0.0819, moist soils R2 = 0.7254 and MSPE = 0.1536).
This model includes soil surface heat exchange with the greenhouse air which was found to give a more accurate prediction of the internal temperatures.
At 200 m resolution, soil and groundwater factors yileld the best model (R2 = 0.42) while at 500 m resolution a model including soil, groundwater and historical land use performs best (R2 = 0.75).
The inputs to the neural network model included soil moisture, electrical conductivity of the soil solution, height and diameter of plant shoot, potential evapotranspiration, atmospheric humidity and air temperature.
Each terron is characterised by landscape variables (derived from a digital elevation model) and soil variables which include soil pH, clay percentage, soil mineralogy (clay types and presence of iron oxides), continuous soil classes, and presence or absence of marl.
Current models need to be improved to include soil structure as an influencing factor to better predict C fluxes between pedosphere and atmosphere and to estimate carbon sequestration potentials.
To effectively model these fluxes, complex functions that include soil and vegetation properties are often required.
We modeled the sequences and magnitudes of changes in the interpreted air photo data in a multi-level panel model that included soil quality and slope of sample areas and agricultural activities and employment reported in the U.S. Censuses of Agriculture and Population.
With various degrees of complexity, the models include consideration of soil moisture and litter volumes and composition.
Several hydrological models including the Soil and Water Assessment Tool (SWAT) and Hydrologic Index Tool were integrated and the results were used to develop a stream health model.
