.png){kind=icon}
.png){kind=icon}
Return
Off-road trafficability using multicriteria decision analysis: development and validation of vehicle trafficability maps
.png){kind=icon}
PRE
AI
R
C
R
DOI：10.1080/15230406.2026.2653182.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study presents an original methodological contribution by developing and validating a replicable framework for the generation of vehicle trafficability maps through refined spatial modeling techniques, relying on biophysical, infrastructure, and meteorological variables. By integrating remote sensing data, Geographic Object-Based Image Analysis (GEOBIA), Machine Learning classification (Random Forest), and Multicriteria Decision Analysis (MCDA) operationalized via the Analytic Hierarchy Process (AHP), we designed a robust spatial model within the Dinamica EGO platform. This methodological innovation enables the systematic integration of heterogeneous spatial layers (e.g. relief, land use and land cover, soil, wind speed, precipitation, temperature) and non-spatial data (e.g. vehicle tire type), producing a continuous Trafficability Index and its subsequent categorical mapping using Jenks natural breaks approach. The model’s validity was demonstrated through comprehensive field surveys and accuracy assessment via statistical metrics, achieving an overall accuracy of 84.7% and a Kappa index of 0.81. This work advances cartographic modeling by formalizing a generalizable procedure that can support decision-making in diverse applications, such as transportation planning, environmental management, and military operations. It contributes as well to the methodological repertoire of GIScience for terrain analysis and cartographic modeling.
Keywords:
Analytic hierarchy process
Dinamica EGO
GIS
Machine Learning
spatial modeling
Journal
IF:
2.4
Papers:
103
Citations:
1.5K
Organization
Cited Papers