Machine-learning algorithms have gained popularity in recent years in the field of ecological modeling due to their promising results in predictive performance of classification problems. While the application of such algorithms has been highly predictors.Results show that GAM and Random Forest (RF) (mean AUROC estimates 0.708 and 0.699) outperform all other methods in predictive accuracy. The effect of hyperparameter tuning saturates at around 50 iterations for this data set. The AUROC differences between the bias-reduced (spatial cross-validation) and overoptimistic (non-spatial cross-validation) performance estimates of the GAM and RF are 0.167 (24%) and 0.213 (30%), respectively. It is recommended to also use spatial partitioning for cross-validation hyperparameter tuning of spatial data. The models developed in this study enhance the detection of Diplodia sapinea in the Basque Country compared to previous studies.
The fusion of microwave and optical data sets is expected to provide great potential for the derivation of forest cover around the globe. As Sentinel-1 and Sentinel-2 are now both operating in twin mode, they can provide an unprecedented data source to build dense spatial and temporal high-resolution time series across a variety of wavelengths. This study investigates (i) the ability of the individual sensors and (ii) their joint potential to delineate forest cover for study sites in two highly varied landscapes located in Germany (temperate dense mixed forests) and South Africa (open savanna woody vegetation and forest plantations). We used multi-temporal Sentinel-1 and single time steps of Sentinel-2 data in combination to derive accurate forest/non-forest (FNF) information via machine-learning classifiers. The forest classification accuracies were 90.9% and 93.2% for South Africa and Thuringia, respectively, estimated while using autocorrelation corrected spatial cross-validation (CV) for the fused data set. Sentinel-1 only classifications provided the lowest overall accuracy of 87.5%, while Sentinel-2 based classifications led to higher accuracies of 91.9%. Sentinel-2 short-wave infrared (SWIR) channels, biophysical parameters (Leaf Area Index (LAI), and Fraction of Absorbed Photosynthetically Active Radiation (FAPAR)) and the lower spectrum of the Sentinel-1 synthetic aperture radar (SAR) time series were found to be most distinctive in the detection of forest cover. In contrast to homogenous forests sites, Sentinel-1 time series information improved forest cover predictions in open savanna-like environments with heterogeneous regional features. The presented approach proved to be robust and it displayed the benefit of fusing optical and SAR data at high spatial resolution.
Considering the critical importance of the quality of input data for landslide susceptibility, we investigate the performance improvements that can be achieved by different globally available digital elevation models (DEMs) using different state-of-the-art statistical and machine-learning models. For this purpose we compare the predictive performances achieved using terrain attributes derived from TanDEM-X DEM (12 m resolution and resampled to 30 m), ASTER DEM (30 m), SRTM DEM (30 m), and a DEM (25 m) interpolated from contour lines (1:25.000 map scale), exploiting the capabilities of logistic regression, generalized additive models, random forests and support vector machines. The study was conducted in the Buz au Sector of the Curvature Subcarpathians of Romania, a region highly susceptible to landslides. While the performances varied little among modelling techniques, the use of different DEMs strongly influenced the cross-validation accuracy of landslide susceptibility models. TanDEM-X (12 m) based susceptibility models outperformed models based on the other DEMs (median Area Under the Receiver Operating Characteristics Curve (AUROC) values 0.708-0.730). Models using ASTER-derived terrain attributes showed the poorest predictive capabilities (median AUROC 0.568-0.595). We conclude that the quality of DEMs is of critical importance in landslide susceptibility modelling, and greater efforts should be made to obtain suitable DEM products.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.