scholarly journals Study on Method of Building a Regional Digital Elevation Model Based on Accuracy Evaluation by Cross Validation

2018 ◽  
Keyword(s):  
Digital Elevation Model ◽  
Cross Validation ◽  
Accuracy Evaluation ◽  
Model Based ◽  
Digital Elevation ◽  
Elevation Model

scholarly journals A Case Study of Digital Elevation Model-Based Slope Stability Assessment on Managed Forestland in the Oregon Coast Range

2006 ◽  
Vol 21 (4) ◽  
pp. 195-202
Author(s):  
Marvin R. Pyles ◽  
Mari Kramer
Keyword(s):  
Slope Stability ◽  
Digital Elevation Model ◽  
Low Risk ◽  
Correct Prediction ◽  
Stability Assessment ◽  
Forest Management Planning ◽  
Model Based ◽  
The North ◽  
Digital Elevation ◽  
Elevation Model

Abstract An aerial photo-based inventory of landslides on recently harvested and reforested land after a significant landslide-producing storm in February 1996, was compared with a digital elevation model-based assessment of slope stability (shallow landsliding stability model [SHALSTAB]) for Confederated Tribes of Siletz Indians (CTSI) and surrounding forestland. The SHALSTAB predictions of landslide locations did not correlate well with the locations of observed landslides. Eighty-nine percent of the landslides on the more stable landform in the southern portion of the CTSI ownership occurred on land that SHALSTAB indicated to be at a low risk of landsliding. Seventy-two percent of the landslides on the less stable landform to the north occurred on land that SHALSTAB indicated to be at a low risk of landsliding. Conversely, only 11 and 28%, respectively, of the observed landslides occurred on lands predicted to be “chronically unstable” or at “high risk” by SHALSTAB. This level of correct prediction of landsliding was judged to be unacceptable for SHALSTAB to be used for slope stability assessment as a part of forest management planning. West. J. Appl. For. 21(4):195–202.

Impacts of coarse-resolution soil maps and high-resolution digital-elevation-model-generated attributes on modelling forest soil zinc and copper

2021 ◽  
pp. 1-16
Author(s):  
Zhengyong Zhao ◽  
Qi Yang ◽  
Xiaogang Ding ◽  
Zisheng Xing
Keyword(s):  
High Resolution ◽  
Forest Soil ◽  
Digital Elevation Model ◽  
Cross Validation ◽  
Large Area ◽  
Coarse Resolution ◽  
Digital Elevation ◽  
Ann Models ◽  
Elevation Model ◽  
Fold Cross Validation

The depth-specific zinc (Zn) and copper (Cu) maps with high resolution (i.e., ≤10 m) are important for soil and forest management and conservation. The objective of this study was to assess the effects of easily accessible model inputs, i.e., existing coarse-resolution parent material, pH, and soil texture maps with 1:1 800 000–2 800 000 scale and nine digital elevation model (DEM)-generated terrain attributes with 10 m resolution, on modelling Zn and Cu distributions of forest soil over a large area (e.g., thousands of km2). A total of 511 artificial neural network (ANN) models for each depth (20 cm increments to 100 cm) were built and evaluated by a 10-fold cross-validation with 385 soil profiles from the Yunfu forest, South China, about 4915 km2 areas. The results indicated that the optimal models for five depths engaged five to seven DEM-generated attributes together with three coarse-resolution soil attributes as inputs, respectively, and accuracies for estimating Zn and Cu varied with R2 of 0.76–0.85 and relative overall accuracy ±10% of 74%–86%. The produced maps showed that DEM-generated sediment delivery ratio, topographic position index (TPI), and aspect were the most important attributes for predicting Cu, but flow length, TPI, and slope were for Zn, which heavily affected Zn and Cu distributions in detail. Boundaries of three coarse-resolution maps were still visible in the generated maps indicated that the maps affected the distributions of Zn and Cu in large scales. Thus, the modelling method, i.e., developing ANN models with k-fold cross-validation, can be used to map high-resolution Zn and Cu over a large area.

Sign in / Sign up

Export Citation Format

Share Document