A GPU-based Parallelization Approach to conduct Spatially-Explicit Uncertainty and Sensitivity Analysis in the Application Domain of Landscape Assessment

Erlacher, Christoph; Jankowski, Piotr; Blaschke, Thomas; Paulus, Gernot; Anders, Karl–Heinrich

doi:10.1553/giscience2017_01_s44

Cited by 8 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a variety of different application domains that addresses S-MCDM, such as landscape assessment, environmental protection, utility management, sustainable and regional development, water resource management, land use planning, site planning, natural hazard risk assessment, waste management and network infrastructure planning [74][75][76][77][78][79][80][81][82][83][84]. Those application domains incorporate various mathematical models such as weighted linear combination [17], ordered weighted averaging [85][86][87], ideal point [60,88] or analytic hierarchy process [19] to compute the performance of the alternatives (e.g., cities or districts of a city). Additionally, this research project pointed out that there is a recognizable uncertainty in respect to the expert's preferences.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Can ISO-Defined Urban Sustainability Indicators Be Derived from Remote Sensing: An Expert Weighting Approach

et al. 2018

Self Cite

View full text Add to dashboard Cite

Abstract:In the context of the United Nations' "Agenda 2030 for Sustainable Development" and the presented Sustainable Development Goals (SDGs), the process of developing and agreeing on indicators to monitor the SDGs implementation becomes fundamental. In this paper, we identify indicators for the sustainable development of cities that have the greatest potential for their underlying data to be measured by means of remote sensing. We first identified existing indicators, which are derived from the International Standard ISO 37120, "Indicators for city services and quality of life", as being partly or fully measured by the use of remote sensing, and then presented these indicators to remote sensing experts in an assessment procedure. We then investigated Multi-Criteria Decision-Making (MCDM) weighting methods to identify the most relevant quality of life indicators that can be captured by means of remote sensing techniques. We assess the remote sensing experts' knowledge in the context of Decision Support Systems (DSS), and by means of both a questionnaire-based approach and a pairwise comparison approach. The approaches are compared with each other regarding their complexity, their potentials and limitations, and the respectively identified remote sensing based indicators. We identified three indicators related to surface characteristics as having the highest remote sensing potential. When contrasted to the results of the pairwise comparison, the questionnaire-based approach revealed high usability and confirmability. In the end, this approach enables cities' administrations to decide which indicators they want to cover by means of remote sensing, depending on the capacities of their departments.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Those differences can be expressed in weight ranges, which indicate uncertainties concerning the expert preferences [77]. Examples of spatial uncertainty and sensitivity analysis can be found in [88][89][90][91].…”

Section: Discussionmentioning

confidence: 99%

Can ISO-Defined Urban Sustainability Indicators Be Derived from Remote Sensing: An Expert Weighting Approach

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…It has also some advantages compared to other susceptibility mapping methods such as expert-knowledge-based GIS-MCDA. GIS-MCDA is sometimes criticized for the expert knowledge to be a major source of uncertainty among the results (Ş alap-Ayça and Jankowski 2016; Feizizadeh and Kienberger 2017;Erlacher et al 2017;Feizizadeh and Ghorbanzadeh 2017;Cabrera-Barona and Ghorbanzadeh 2018) or ordinary neural networks because they use if-then rules (Bardestani et al 2017). The proposed method does not apply expert opinions at any stage.…”

Section: Introductionmentioning

confidence: 99%

A new GIS-based data mining technique using an adaptive neuro-fuzzy inference system (ANFIS) and k-fold cross-validation approach for land subsidence susceptibility mapping

et al. 2018

Self Cite

View full text Add to dashboard Cite

In this paper, we evaluate the predictive performance of an adaptive neuro-fuzzy inference system (ANFIS) using six different membership functions (MF). In combination with a geographic information system (GIS), ANFIS was used for land subsidence susceptibility mapping (LSSM) in the Marand plain, northwest Iran. This area is prone to droughts and low groundwater levels and subsequent land subsidence damages. Therefore, a land subsidence inventory database was created from an extensive field survey. Areas of land subsidence or areas showing initial signs of subsidence were used for training, while onethird of inventory database were reserved for testing and validation. The inventory database randomly divided into three different folds of the same size. One of the folds was chosen for testing and validation. Other two folds was used for training. This process repeated for every fold in the inventory dataset. Thereafter, land subsidence related factors, such as hydrological and topographical factors, were prepared as GIS layers. Areas susceptible to land subsidence were then analyzed using the ANFIS approach, and land subsidence susceptibility maps were created, whereby six different MFs were applied. Lastly, the results derived from each MF were validated with those areas of the land subsidence database that were not used for training. Receiver operating characteristics (ROC) curves were drawn for all LSSMs, and the areas under the curves were calculated. The ROC analyses for the six LSSMs yielded very high prediction values for two out of the six methods, namely the difference of DsigMF (0.958) and GaussMF (0.951). The integration of ANFIS and GIS generally led to high LSSM prediction accuracies. This study demonstrated that the choice of training dataset and the MF significantly affects the results.

show abstract

“…In response to this need, concepts of sensitivity and uncertainty have been developed that aim to determine the sources of error in GIS-MCDA in order that they can then be minimized. An uncertainty analysis is not the same as a sensitivity analysis and a number of researchers have integrated the two into GIS-MCDA (Crosetto et al 2000;Ligmann-Zielinska and Jankowski 2012;Feizizadeh et al 2014b;Norton 2015;Erlacher et al 2017). The two terms (uncertainty and sensitivity) refer to different concepts: an uncertainty analysis attempts to describe the entire set of possible outcomes and their associated probabilities of occurrence, while a sensitivity analysis attempts to determine the magnitude of change in model output that results from a minor change in model input.…”

Section: Introductionmentioning

confidence: 99%

Multi-criteria risk evaluation by integrating an analytical network process approach into GIS-based sensitivity and uncertainty analyses

Ghorbanzadeh

Feizizadeh

Blaschke

2017

Geomatics, Natural Hazards and Risk

Self Cite

103

View full text Add to dashboard Cite

Geographic information system (GIS)-based multi-criteria decision analysis (MCDA) is commonly used to solve a range of complex spatial problems. We have incorporated an analytical network process (ANP) as a central part of MCDA and used this approach for land subsidence susceptibility mapping (LSSM). We used an ANP approach in combination with the concepts of global sensitivity and uncertainty analyses, in order to minimize any associated errors. This approach was tested for a LSSM application in northwestern Iran, using a methodology that consisted of three distinct phases. An ANP approach was used in the first phase to derive criteria weightings by analysing relevant criteria, which included topographic, hydrologic, climatologic, geological, and anthropological indicators. The second phase involved evaluating the uncertainty and sensitivity of areas susceptible to subsidence as a function of the derived weightings, using Monte Carlo simulations. The third phase then used a land subsidence inventory database to validate the results and to measure any improvement in accuracy following sensitivity analysis. Results indicated a 6% improvement in the accuracy of the ANP method as a result of using an integrated global sensitivity analysis.

show abstract

A GPU-based Parallelization Approach to conduct Spatially-Explicit Uncertainty and Sensitivity Analysis in the Application Domain of Landscape Assessment

Cited by 8 publications

References 18 publications

Can ISO-Defined Urban Sustainability Indicators Be Derived from Remote Sensing: An Expert Weighting Approach

Can ISO-Defined Urban Sustainability Indicators Be Derived from Remote Sensing: An Expert Weighting Approach

A new GIS-based data mining technique using an adaptive neuro-fuzzy inference system (ANFIS) and k-fold cross-validation approach for land subsidence susceptibility mapping

Multi-criteria risk evaluation by integrating an analytical network process approach into GIS-based sensitivity and uncertainty analyses

Contact Info

Product

Resources

About