Soil depth modelling using terrain analysis and satellite imagery: the case study of Qeshlaq mountainous watershed (Kurdistan, Iran)

  • Salahudin Zahedi | zahedi51@gmail.com Kurdistan Agricultural and Natural Resources Research and Education Centre, AREEO, Sanandaj, Iran, Islamic Republic of.
  • Kaka Shahedi Watershed Management Department, Sari University of Agricultural Sciences and Natural Resources, Sari, Iran, Islamic Republic of.
  • Mahmod Habibnejad Rawshan Watershed Management Department, Sari University of Agricultural Sciences and Natural Resources, Sari, Iran, Islamic Republic of.
  • Karim Solimani Watershed Management Department, Sari University of Agricultural Sciences and Natural Resources, Sari, Iran, Islamic Republic of.
  • Kourosh Dadkhah Department of Statistics, Faculty of Sciences, University of Kurdistan, Sanandaj, Iran, Islamic Republic of.

Abstract

Soil depth is a major soil characteristic, which is commonly used in distributed hydrological modelling in order to present watershed subsurface attributes. This study aims at developing a statistical model for predicting the spatial pattern of soil depth over the mountainous watershed from environmental variables derived from a digital elevation model (DEM) and remote sensing data. Among the explanatory variables used in the models, seven are derived from a 10 m resolution DEM, namely specific catchment area, wetness index, aspect, slope, plan curvature, elevation and sediment transport index. Three variables landuse, NDVI and pca1 are derived from Landsat8 imagery, and are used for predicting soil depth by the models. Soil attributes, soil moisture, topographic curvature, training samples for each landuse and major vegetation types are considered at 429 profiles within four subwatersheds. Random forests (RF), support vector machine (SVM) and artificial neural network (ANN) are used to predict soil depth using the explanatory variables. The models are run using 336 data points in the calibration dataset with all 31 explanatory variables, and soil depth as the response of the models. Mean decrease permutation accuracy is performed on Variable selection. Testing dataset is done with the model soil depth values at testing locations (93 points) using different efficiency criteria. Prediction error is computed for both the calibration and testing datasets. Results show that the variables landuse, specific surface area, slope, pca1, NDVI and aspect are the most important explanatory variables in predicting soil depth. RF and SVM models are appropriate for the mountainous watershed areas that have been limited in the depth of the soil and ANN model is more suitable for watershed with the fields of agricultural and deep soil depth.

Downloads

Download data is not yet available.
Published
2017-09-14
Section
Original Articles
Keywords:
Explanatory variable, digital elevation model, statistical prediction models, terrain attributes.
Statistics
Abstract views: 956

PDF: 291
HTML: 591
Share it

PlumX Metrics

PlumX Metrics provide insights into the ways people interact with individual pieces of research output (articles, conference proceedings, book chapters, and many more) in the online environment. Examples include, when research is mentioned in the news or is tweeted about. Collectively known as PlumX Metrics, these metrics are divided into five categories to help make sense of the huge amounts of data involved and to enable analysis by comparing like with like.

How to Cite
Zahedi, S., Shahedi, K., Habibnejad Rawshan, M., Solimani, K., & Dadkhah, K. (2017). Soil depth modelling using terrain analysis and satellite imagery: the case study of Qeshlaq mountainous watershed (Kurdistan, Iran). Journal of Agricultural Engineering, 48(3), 167-174. https://doi.org/10.4081/jae.2017.595