Data supplement to "In-stream wetland suitability mapping using Analytic Hierarchy Process and machine learning"

This dataset provides the supplementary output products supporting the results and figures reported in Guamán-Pintado et al., “In-stream wetland suitability mapping using Analytic Hierarchy Process and machine learning.” The repository contains raster-based in-stream wetland suitability maps generated using two complementary approaches: an expert-based Analytic Hierarchy Process (AHP) and a Random Forest (RF) machine learning model. The outputs represent the final spatial predictions used to analyse and compare methodological performance. Suitability maps are provided for combinations of: modelling approach (AHP and RF), data origin (local and global datasets), and spatial resolution (10 m and 50 m). All raster files are delivered in GeoTIFF format and represent continuous suitability scores, where higher values indicate higher feasibility for in-stream wetland creation or restoration. This dataset includes only the final model outputs used to produce the results and figures reported in the article. The model implementation and training code are available at https://doi.org/10.5281/zenodo.18403086. Full methodological details, predictor variables, and validation procedures are described in the associated publication. This dataset is intended to support reproducibility, transparency, and reuse in research related to wetland restoration planning, suitability mapping, and spatial environmental modelling.