A one-step approach for modelling and mapping soil properties based on profile data sampled over varying depth intervals

Orton, Thomas G.; Pringle, M. J.; Bishop, Thomas

doi:10.1016/j.geoderma.2015.08.013

Cited by 51 publications

(19 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This would remove the need for using splines to create the finely spaced vertical dataset. Adopting the approach by Orton et al [37] also bypasses the uncertainty introduced by the splining process, although, as discussed, the results in the current study suggested that this was relatively small ( Table 3). The uncertainty in imputed values is commonly ignored in DSM studies that use splined soil data.…”

Section: Modelling/mapping Approach and Validationmentioning

confidence: 63%

“…This cross-validation procedure was performed in two ways: (1) at 1-cm vertical resolution (the splined observed pH data vs. the independently predicted pH data) and (2) at the original sampling depths of the observed data (observed pH data vs. predicted pH data at a 1-cm resolution aggregated to the original sampling depths). The rationale for this was that the splining procedure introduces some amount of uncertainty to the data [37] and validating by the second approach avoids this limitation as the predicted data are compared to the original, un-splined soil pH data. To test the importance of different predictor variables in the model, the mean decrease in accuracy was used, which is based on the mean square error (MSE).…”

Section: Model Quality and Validationmentioning

confidence: 99%

“…This would still be at a fine enough vertical resolution to inform management decisions for land managers but would significantly reduce the dataset size. An alternative would be to use the approach of Orton et al [37] who presented a geostatistical approach to predict in 3D at any vertical resolution using observations from different vertical supports (e.g., soil horizons). This would remove the need for using splines to create the finely spaced vertical dataset.…”

Section: Modelling/mapping Approach and Validationmentioning

confidence: 99%

See 2 more Smart Citations

Mapping the Depth-to-Soil pH Constraint, and the Relationship with Cotton and Grain Yield at the Within-Field Scale

et al. 2019

View full text Add to dashboard Cite

Subsoil alkalinity is a common issue in the alluvial cotton-growing valleys of northern New South Wales (NSW), Australia. Soil alkalinity can cause nutrient deficiencies and toxic effects, and inhibit rooting depth, which can have a detrimental impact on crop production. The depth at which a soil constraint is reached is important information for land managers, but it is difficult to measure or predict spatially. This study predicted the depth in which a pH (H2O) constraint (>9) was reached to a 1-cm vertical resolution to a 100-cm depth, on a 1070-hectare dryland cropping farm. Equal-area quadratic smoothing splines were used to resample vertical soil profile data, and a random forest (RF) model was used to produce the depth-to-soil pH constraint map. The RF model was accurate, with a Lin’s Concordance Correlation Coefficient (LCCC) of 0.63–0.66, and a Root Mean Square Error (RMSE) of 0.47–0.51 when testing with leave-one-site-out cross-validation. Approximately 77% of the farm was found to be constrained by a strongly alkaline pH greater than 9 (H2O) somewhere within the top 100 cm of the soil profile. The relationship between the predicted depth-to-soil pH constraint map and cotton and grain (wheat, canola, and chickpea) yield monitor data was analyzed for individual fields. Results showed that yield increased when a soil pH constraint was deeper in the profile, with a good relationship for wheat, canola, and chickpea, and a weaker relationship for cotton. The overall results from this study suggest that the modelling approach is valuable in identifying the depth-to-soil pH constraint, and could be adopted for other important subsoil constraints, such as sodicity. The outputs are also a promising opportunity to understand crop yield variability, which could lead to improvements in management practices.

show abstract

Section: Modelling/mapping Approach and Validationmentioning

confidence: 63%

Section: Model Quality and Validationmentioning

confidence: 99%

Section: Modelling/mapping Approach and Validationmentioning

confidence: 99%

See 1 more Smart Citation

Mapping the Depth-to-Soil pH Constraint, and the Relationship with Cotton and Grain Yield at the Within-Field Scale

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In "stratified" cross-validation, training and test sets have the same spatial and price value distribution as the full dataset [31]. In addition, "stratified" is a variant of the k-fold within training data and also ensures that each fold has the right proportion of samples in regard to spatial location and price values.…”

Section: The Comparison Of Ols and Rf Performancementioning

confidence: 99%

Estimating the Performance of Random Forest versus Multiple Regression for Predicting Prices of the Apartments

Čeh

Kilibarda

Lisec

et al. 2018

IJGI

146

View full text Add to dashboard Cite

Abstract:The goal of this study is to analyse the predictive performance of the random forest machine learning technique in comparison to commonly used hedonic models based on multiple regression for the prediction of apartment prices. A data set that includes 7407 records of apartment transactions referring to real estate sales from 2008-2013 in the city of Ljubljana, the capital of Slovenia, was used in order to test and compare the predictive performances of both models. Apparent challenges faced during modelling included (1) the non-linear nature of the prediction assignment task; (2) input data being based on transactions occurring over a period of great price changes in Ljubljana whereby a 28% decline was noted in six consecutive testing years; and (3) the complex urban form of the case study area. Available explanatory variables, organised as a Geographic Information Systems (GIS) ready dataset, including the structural and age characteristics of the apartments as well as environmental and neighbourhood information were considered in the modelling procedure. All performance measures (R 2 values, sales ratios, mean average percentage error (MAPE), coefficient of dispersion (COD)) revealed significantly better results for predictions obtained by the random forest method, which confirms the prospective of this machine learning technique on apartment price prediction.

show abstract

“…Geostatistical tools are usually applied to data with apparent spatial continuity, e.g. temperature, rainfall and land composition, in the fields of geology (Lee, Carle, & Fogg, 2007;Orton, Pringle, & Bishop, 2016;Tamayo-Mas, Mustapha, & Dimitrakopoulos, 2016), hydrology (Guven & Kitanidis, 1988;Goovaerts, 2000) and mining (Coburn, 2012), for example. However, over the last decades, its implementation on spatially discrete data (Goovaerts, 2006;Goovaerts, 2008) has proven to be a potential alternative when adapted to such spatial continuity problems.…”

Section: Spatial Statistics Methods On Crash Predictionmentioning

confidence: 99%

Spatial crash prediction models: an evaluation of the impacts of enriched information on model performance and the suitability of different spatial modeling approaches

Gomes¹

View full text Add to dashboard Cite

A one-step approach for modelling and mapping soil properties based on profile data sampled over varying depth intervals

Cited by 51 publications

References 40 publications

Mapping the Depth-to-Soil pH Constraint, and the Relationship with Cotton and Grain Yield at the Within-Field Scale

Mapping the Depth-to-Soil pH Constraint, and the Relationship with Cotton and Grain Yield at the Within-Field Scale

Estimating the Performance of Random Forest versus Multiple Regression for Predicting Prices of the Apartments

Spatial crash prediction models: an evaluation of the impacts of enriched information on model performance and the suitability of different spatial modeling approaches

Contact Info

Product

Resources

About