Search

Featured Application: This research deals with a very relevant topic in the framework of landslide susceptibility mapping, highlighting some very critical drawbacks in using a weak landslide inventory for regional-scale assessment. Tools and strategies for recognizing and approaching such limits are given. This research is focused on the evaluation of the reliability of regional landslide susceptibility models obtained by exploiting inhomogeneous (for quality, resolution and/or triggering related type and intensity) collected inventories for calibration. At a large-scale glance, merging more inventories can result in well-performing models hiding potential strong predictive deficiencies. An example of the limits that such kinds of models can display is given by a landslide susceptibility study, which was carried out for a large sector of the coastal area of El Salvador, where an apparently well-performing regional model (AUC = 0.87) was obtained by regressing a dataset through multivariate adaptive regression splines (MARS), including five landslide inventories from volcanic areas (Ilopango and Coatepeque caldera; San Salvador, San Miguel, and San Vicente Volcanoes). A multiscale validation strategy was applied to verify its actual predictive skill on a local base, bringing to light the loss in the predictive power of the regional model, with a lowering of AUC (20% on average) and strong effects in terms of sensitivity and specificity. [ABSTRACT FROM AUTHOR]

Long-term changes in precipitation and temperature indirectly impact aquifers through groundwater recharge (GWR). Although estimates of future GWR are needed for water resource management, they are uncertain in cold and humid climates due to the wide range in possible future climatic conditions. This work aims to (1) simulate the impacts of climate change on regional GWR for a cold and humid climate and (2) identify precipitation and temperature changes leading to significant long-term changes in GWR. Spatially distributed GWR is simulated in a case study for the southern Province of Quebec (Canada, 36,000 km2) using a water budget model. Climate scenarios from global climate models indicate warming temperatures and wetter conditions (RCP4.5 and RCP8.5; 1951–2100). The results show that annual precipitation increases of >+150 mm/yr or winter precipitation increases of >+25 mm will lead to significantly higher GWR. GWR is expected to decrease if the precipitation changes are lower than these thresholds. Significant GWR changes are produced only when the temperature change exceeds +2 °C. Temperature changes of >+4.5 °C limit the GWR increase to +30 mm/yr. This work provides useful insights into the regional assessment of future GWR in cold and humid climates, thus helping in planning decisions as climate change unfolds. The results are expected to be comparable to those in other regions with similar climates in post-glacial geological environments and future climate change conditions. [ABSTRACT FROM AUTHOR]

In this paper, for the first time, a regional-scale 1:100,000 landslide-susceptibility map (LSM) is presented for Sisak-Moslavina County in Croatia. The spatial relationship between landslide occurrence and landslide predictive factors (engineering geological units, relief, roughness, and distance to streams) is assessed using the integration of a statistically based frequency ratio (FR) into the analytical hierarchy process (AHP). Due to the lack of landslide inventory for the county, LiDAR-based inventories are completed for an area of 132 km2. From 1238 landslides, 549 are chosen to calculate the LSM and 689 for its verification. Additionally, landslides digitized from available geological maps and reported via the web portal "Report a landslide" are used for verification. The county is classified into four susceptibility classes, covering 36% with very-high and high and 64% with moderate and low susceptibility zones. The presented approach, using limited LiDAR data and the extrapolation of the correlation results to the entire county, is encouraging for primary regional-level studies, justifying the cost-benefit ratio. Still, the positioning of LiDAR polygons prerequires a basic statistical analysis of predictive factors. [ABSTRACT FROM AUTHOR]

Satellite-borne multispectral data are suitable for regional-scale grassland community classification owing to comprehensive coverage. However, the spectral similarity of different communities makes it challenging to distinguish them based on a single multispectral data. To address this issue, we proposed a support vector machine (SVM)–based method integrating multispectral data, two-band enhanced vegetation index (EVI2) time-series, and phenological features extracted from Chinese GaoFen (GF)-1/6 satellite with (16 m) spatial and (2 d) temporal resolution. To obtain cloud-free images, the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) algorithm was employed in this study. By using the algorithm on the coarse cloudless images at the same or similar time as the fine images with cloud cover, the cloudless fine images were obtained, and the cloudless EVI2 time-series and phenological features were generated. The developed method was applied to identify grassland communities in Ordos, China. The results show that the Caragana pumila Pojark, Caragana davazamcii Sanchir and Salix schwerinii E. L. Wolf grassland, the Potaninia mongolica Maxim, Ammopiptanthus mongolicus S. H. Cheng and Tetraena mongolica Maxim grassland, the Caryopteris mongholica Bunge and Artemisia ordosica Krasch grassland, the Calligonum mongolicum Turcz grassland, and the Stipa breviflora Griseb and Stipa bungeana Trin grassland are distinguished with an overall accuracy of 87.25%. The results highlight that, compared to multispectral data only, the addition of EVI2 time-series and phenological features improves the classification accuracy by 9.63% and 14.7%, respectively, and even by 27.36% when these two features are combined together, and indicate the advantage of the fine images in this study, compared to 500 m moderate-resolution imaging spectroradiometer (MODIS) data, which are commonly used for grassland classification at regional scale, while using 16 m GF data suggests a 23.96% increase in classification accuracy with the same extracted features. This study indicates that the proposed method is suitable for regional-scale grassland community classification. [ABSTRACT FROM AUTHOR]

High spatial resolution (1–5 m) remotely sensed datasets are increasingly being used to map land covers over large geographic areas using supervised machine learning algorithms. Although many studies have compared machine learning classification methods, sample selection methods for acquiring training and validation data for machine learning, and cross-validation techniques for tuning classifier parameters are rarely investigated, particularly on large, high spatial resolution datasets. This work, therefore, examines four sample selection methods—simple random, proportional stratified random, disproportional stratified random, and deliberative sampling—as well as three cross-validation tuning approaches—k-fold, leave-one-out, and Monte Carlo methods. In addition, the effect on the accuracy of localizing sample selections to a small geographic subset of the entire area, an approach that is sometimes used to reduce costs associated with training data collection, is investigated. These methods are investigated in the context of support vector machines (SVM) classification and geographic object-based image analysis (GEOBIA), using high spatial resolution National Agricultural Imagery Program (NAIP) orthoimagery and LIDAR-derived rasters, covering a 2,609 km2 regional-scale area in northeastern West Virginia, USA. Stratified-statistical-based sampling methods were found to generate the highest classification accuracy. Using a small number of training samples collected from only a subset of the study area provided a similar level of overall accuracy to a sample of equivalent size collected in a dispersed manner across the entire regional-scale dataset. There were minimal differences in accuracy for the different cross-validation tuning methods. The processing time for Monte Carlo and leave-one-out cross-validation were high, especially with large training sets. For this reason, k-fold cross-validation appears to be a good choice. Classifications trained with samples collected deliberately (i.e., not randomly) were less accurate than classifiers trained from statistical-based samples. This may be due to the high positive spatial autocorrelation in the deliberative training set. Thus, if possible, samples for training should be selected randomly; deliberative samples should be avoided. [ABSTRACT FROM AUTHOR]