Freely available global digital elevation models (DEMs) are important inputs for many research fields and applications. During the last decade, several global DEMs have been released based on satellite data. ASTER and SRTM are the most widely used DEMs, but the more recently released, AW3D30, TanDEM-X and MERIT, are being increasingly used. Many researchers have studied the quality of these DEM products in recent years. However, there has been no comprehensive and systematic evaluation of their quality over areas with variable topography and land cover conditions. To provide this comparison, we examined the accuracy of six freely available global DEMs (ASTER, AW3D30, MERIT, TanDEM-X, SRTM, and NASADEM) in four geographic regions with different topographic and land use conditions. We used local high-precision elevation models (Light Detection and Ranging (LiDAR), Pleiades-1A) as reference models and all global models were resampled to reference model resolution (1m). In total, 608 million 1x1 m pixels were analyzed. To estimate the accuracy, we generated error rasters by subtracting each reference model from the corresponding global DEM and calculated descriptive statistics for this difference (e.g., median, mean, root-mean-square error (RMSE)). We also assessed the vertical accuracy as a function of the slope, slope aspect, and land cover. We found that slope had the strongest effect on DEM accuracy, with no relationship for slope aspect. The AW3D30 was the most robust and had the most stable performance in most of the tests and is therefore the best choice for an analysis of multiple geographic regions. SRTM and NASADEM also performed well where available, whereas NASADEM, as a successor of SRTM, showed only slight improvement in comparison to SRTM. MERIT and TanDEM-X also performed well despite their lower spatial resolution.

Vertical Accuracy of Freely Available Global Digital Elevation Models (ASTER, AW3D30, MERIT, TanDEM-X, SRTM, and NASADEM)

Remote sensing and GIS techniques for prediction of land use land cover change effects on soil erosion in the high basin of the Oum Er Rbia River (Morocco)

This study sought to produce an accurate multi-hazard risk map for a mountainous region of Iran. The study area is in southwestern Iran. The region has experienced numerous extreme natural events in recent decades. This study models the probabilities of snow avalanches, landslides, wildfires, land subsidence, and floods using machine learning models that include support vector machine (SVM), boosted regression tree (BRT), and generalized linear model (GLM). Climatic, topographic, geological, social, and morphological factors were the main input variables used. The data were obtained from several sources. The accuracies of GLM, SVM, and functional discriminant analysis (FDA) models indicate that SVM is the most accurate for predicting landslides, land subsidence, and flood hazards in the study area. GLM is the best algorithm for wildfire mapping, and FDA is the most accurate model for predicting snow avalanche risk. The values of AUC (area under curve) for all five hazards using the best models are greater than 0.8, demonstrating that the model's predictive abilities are acceptable. A machine learning approach can prove to be very useful tool for hazard management and disaster mitigation, particularly for multi-hazard modeling. The predictive maps produce valuable baselines for risk management in the study area, providing evidence to manage future human interaction with hazards.

/pdf/a-machine-learning-framework-for-multi-hazards-modeling-and-36mqqqvsw1.pdf

A machine learning framework for multi-hazards modeling and mapping in a mountainous area.

Using machine learning models, remote sensing, and GIS to investigate the effects of changing climates and land uses on flood probability

Modelling the impacts of climate and land use changes on soil water erosion: Model applications, limitations and future challenges.

Mountainous areas are highly prone to a variety of nature-triggered disasters, which often cause disabling harm, death, destruction, and damage. In this work, an attempt was made to develop an accurate multi-hazard exposure map for a mountainous area (Asara watershed, Iran), based on state-of-the art machine learning techniques. Hazard modeling for avalanches, rockfalls, and floods was performed using three state-of-the-art models—support vector machine (SVM), boosted regression tree (BRT), and generalized additive model (GAM). Topo-hydrological and geo-environmental factors were used as predictors in the models. A flood dataset (n = 133 flood events) was applied, which had been prepared using Sentinel-1-based processing and ground-based information. In addition, snow avalanche (n = 58) and rockfall (n = 101) data sets were used. The data set of each hazard type was randomly divided to two groups: Training (70%) and validation (30%). Model performance was evaluated by the true skill score (TSS) and the area under receiver operating characteristic curve (AUC) criteria. Using an exposure map, the multi-hazard map was converted into a multi-hazard exposure map. According to both validation methods, the SVM model showed the highest accuracy for avalanches (AUC = 92.4%, TSS = 0.72) and rockfalls (AUC = 93.7%, TSS = 0.81), while BRT demonstrated the best performance for flood hazards (AUC = 94.2%, TSS = 0.80). Overall, multi-hazard exposure modeling revealed that valleys and areas close to the Chalous Road, one of the most important roads in Iran, were associated with high and very high levels of risk. The proposed multi-hazard exposure framework can be helpful in supporting decision making on mountain social-ecological systems facing multiple hazards.

/pdf/multi-hazard-exposure-mapping-using-machine-learning-26014224bm.pdf

Multi-Hazard Exposure Mapping Using Machine Learning Techniques: A Case Study from Iran

Although snow avalanches are among the most destructive natural disasters, and result in losses of life and economic damages in mountainous regions, far too little attention has been paid to the prediction of the snow avalanche hazard using advanced machine learning (ML) models. In this study, the applicability and efficiency of four ML models: support vector machine (SVM), random forest (RF), naive Bayes (NB) and generalized additive model (GAM), for snow avalanche hazard mapping, were evaluated. Fourteen geomorphometric, topographic and hydrologic factors were selected as predictor variables in the modeling. This study was conducted in the Darvan and Zarrinehroud watersheds of Iran. The goodness-of-fit and predictive performance of the models was evaluated using two statistical measures: the area under the receiver operating characteristic curve (AUROC) and the true skill statistic (TSS). Finally, an ensemble model was developed based upon the results of the individual models. Results show that, among individual models, RF was best, performing well in both the Darvan (AUROC = 0.964, TSS = 0.862) and Zarrinehroud (AUROC = 0.956, TSS = 0.881) watersheds. The accuracy of the ensemble model was slightly better than all individual models for generating the snow avalanche hazard map, as validation analyses showed an AUROC = 0.966 and a TSS = 0.865 in the Darvan watershed, and an AUROC value of 0.958 and a TSS value of 0.877 for the Zarrinehroud watershed. The results indicate that slope length, lithology and relative slope position (RSP) are the most important factors controlling snow avalanche distribution. The methodology developed in this study can improve risk-based decision making, increases the credibility and reliability of snow avalanche hazard predictions and can provide critical information for hazard managers.

Spatial Modeling of Snow Avalanche Using Machine Learning Models and Geo-Environmental Factors: Comparison of Effectiveness in Two Mountain Regions

Climate change is known as the long-term average changes of weather conditions in an area with significant effects on the ecosystem of the region Climate change is believed to have significant impacts on the water basin and region, such as in a runoff and hydrological system, erosion, environment as well as agriculture Climate change simulation and scenario design can serve as a useful tool in reducing the effects of this phenomenon The objective of this study is to simulate climate change and design different scenarios in order to evaluate the site-specific impacts of future climate change on soil erosion at the Kasilian watershed in the north of Iran employing seven downscaling scenarios Hence, the climate changes were downscaled based on A2 and B1 emission scenarios, using the Institut Pierre Simon Laplace (IPCM4) with Long Ashton Research Station Weather Generator model and three climate change scenarios, ie, 10% increase in rainfall, 10% reduction in rainfall and unchanged rainfall were employed by Statistical Downscaling Model for the periods of 2011–2030 and 2031–2050 Also, the Revised Universal Soil Loss Equation (RUSLE) model was used in order to estimate soil erosion in basis period (1991–2010) and in the simulated periods (2011–2030, 2031–2050) under effect of climate change scenarios The results showed that the rainfall erosivity factor in the RUSLE model is directly influenced by climate changes The mean of soil erosion was 2182 (tons ha−1 year−1) in basis period, and there was an increase of 10–35% for rainfall erosivity and 10–32% for soil loss during 2011–2030, compared with the present climate Simulated soil loss under the rainfall erosivity during 2031–2050 would be 4–28 and 2–26% for soil loss compared with those under seven downscaling scenarios in the present climate Thus, increase in soil erosion will be definite in four future decades

Teimur Teimurian

Papers

Multi-Hazard Exposure Mapping Using Machine Learning Techniques: A Case Study from Iran

Spatial Modeling of Snow Avalanche Using Machine Learning Models and Geo-Environmental Factors: Comparison of Effectiveness in Two Mountain Regions

Simulation of soil erosion under the influence of climate change scenarios