PERFORMANCE OF MACHINE LEARNING ALGORITHMS FOR MAPPING AND FORECASTING OF FLASH FLOOD SUSCEPTIBILITY IN TETOUAN, MOROCCO

Since the industrial revolution, the world is experiencing a huge change in its climate, which causes many imbalances such as flash floods (FF). The aim of this study is to propose a new approach for detection and forecasting of flash flood susceptibility in the city of Tetouan, Morocco. For this regard, support vector machine (SVM), logistic regression (LR), random forest (RF), Naïve Bayes (NB) and Artificial neural network (ANN) are used based on 1101 points (680 flood points and 421 non-flood points) and 9 flash-flood predictors (Elevation , Slope , Aspect , LU/LC , Stream Power Index , Plan curvature , Profile Curvature , Topographic Position Index and Topographic Wetness Index ) that were extracted from the DEM (10m resolution) and satellite imagery (Sentinel 2B) of the study area . Models were trained on 70% and tested on 30% of this dataset also they were evaluated using several metrics such as the Receiver Operating Characteristic (ROC) Curve, precision, recall, score and kappa index. The result demonstrated that RF (AUC = 0.99, Accuracy = 96%, Kappa statistics = 0.92) has the highest performance, followed by ANN (AUC = 0.98, Accuracy = 95%, Kappa statistics = 0.89) and SVM (AUC = 0.96, Accuracy = 92%, Kappa statistics = 0.80). The proposed approach is an effective tool for forecasting and predicting FF that can help reduce the severity of this disaster.

Sustainability at Auburn University: Assessing Rooftop Solar Energy Potential for Electricity Generation with Remote Sensing and GIS in a Southern US Campus

Achieving sustainability through solar energy has become an increasingly accessible option in the United States (US). Nationwide, universities are at the forefront of energy efficiency and renewable generation goals. The aim of this study was to determine the suitability for the installation of photovoltaic (PV) systems based on their solar potential and corresponding electricity generation potential on a southern US university campus. Using Auburn University located in the southern US as a case study, freely available geospatial data were utilized, and geographic information system (GIS) approaches were applied to characterize solar potential across the 1875-acre campus. Airborne light detection and ranging (lidar) point clouds were processed to extract a digital surface model (DSM), from which slope and aspect were derived. The area and total solar radiation of campus buildings were calculated, and suitable buildings were then determined based on slope, aspect, and total solar radiation. Results highlighted that of 443 buildings, 323 were fit for solar arrays, and these selected rooftops can produce 27,068,555 kWh annually. This study demonstrated that Auburn University could benefit from rooftop solar arrays, and the proposed arrays would account for approximately 21.07% of annual electricity requirement by buildings, equivalent to 14.43% of total campus electricity for all operations. Given increasing open and free access to high-resolution lidar data across the US, methods from this study are adaptable to institutions nationwide, for the development of a comprehensive assessment of solar potential, toward meeting campus energy goals.

Satellite–Derived Topography and Morphometry for VHR Coastal Habitat Mapping: The Pleiades–1 Tri–Stereo Enhancement

The evolution of the coastal fringe is closely linked to the impact of climate change, specifically increases in sea level and storm intensity. The anthropic pressure that is inflicted on these fragile environments strengthens the risk. Therefore, numerous research projects look into the possibility of monitoring and understanding the coastal environment in order to better identify its dynamics and adaptation to the major changes that are currently taking place in the landscape. This new study aims to improve the habitat mapping/classification at Very High Resolution (VHR) using Pleiades–1–derived topography, its morphometric by–products, and Pleiades–1–derived imageries. A tri–stereo dataset was acquired and processed by image pairing to obtain nine digital surface models (DSM) that were 0.50 m pixel size using the free software RSP (RPC Stereo Processor) and that were calibrated and validated with the 2018–LiDAR dataset that was available for the study area: the Emerald Coast in Brittany (France). Four morphometric predictors that were derived from the best of the nine generated DSMs were calculated via a freely available software (SAGA GIS): slope, aspect, topographic position index (TPI), and TPI–based landform classification (TPILC). A maximum likelihood classification of the area was calculated using nine classes: the salt marsh, dune, rock, urban, field, forest, beach, road, and seawater classes. With an RMSE of 4 m, the DSM#2–3_1 (from images #2 and #3 with one ground control point) outperformed the other DSMs. The classification results that were computed from the DSM#2–3_1 demonstrate the importance of the contribution of the morphometric predictors that were added to the reference Red–Green–Blue (RGB, 76.37% in overall accuracy, OA). The best combination of TPILC that was added to the RGB + DSM provided a gain of 13% in the OA, reaching 89.37%. These findings will help scientists and managers who are tasked with coastal risks at VHR.

Integration of Information Theory, Fractal Theory and Statistical Analyses for Landslide Susceptibility Mapping at Regional Scales

A new model, integrating information theory, fractal theory and statistical model for accurate landslide susceptibility mapping (LSM) at regional scales, has been proposed. In this model, landslide conditional factors are firstly classified with an optimal number of classes, which is determined by maximizing their information coefficients estimated from Shannon’s entropy model. The spatial association between influencing factors and induced landslides has been measured by introducing the variable fractal dimension method (VFDM). The VFDM approach fully considers the characteristics of landslide fractal distribution. Then the fractal dimensions (\(D\)) are calculated to provide multiple factors with various numerical weights. The proposed model eventually combines the landslide frequency ratio (\(fr\)) of each factor with corresponding weight to achieve spatial prediction of landslides, illustrated by an example area in China. In the study area, 500 landslides have been identified by aerial photograph interpretation, extensive field investigations, historical and bibliographical landslide data. In the model, these landslides are randomly split into a training dataset (70 %)and a validating dataset (30 %) Seven factors are recognized and analyzed by frequency ratio (FR) method, including lithology, distance to fault, altitude, slope, aspect, distance to stream and distance to the road. The receiver operating characteristic curve (AUROC) has been adopted to compare and validate the model results. Results show that the proposed landslide model achieved a more accurate prediction with AUROC equal to 0.8467, over-performing than the conventional frequency ratio method (AUROC=0.8088). According to the final prognostic landslide susceptibility map, 16.37 % f the study area shows very high and high susceptibility, accounting for 63.55 % f the entire landslides. Evaluation of relative factor importance based on a one-by-one factor removal test indicates that the lithology factor contributes unique information for landslides. In conclusion, the example demonstrates that the proposed framework is promising for further improvement of LSM.

Inventory and Distribution Characteristics of Large-Scale Landslides in Baoji City, Shaanxi Province, China

Inventories of historical landslides play an important role in the assessment of natural hazards. In this study, we used high-resolution satellite imagery from Google Earth to interpret large landslides in Baoji city, Shaanxi Province on the southwestern edge of the Loess Plateau. Then, a comprehensive and detailed map of the landslide distribution in this area was prepared in conjunction with the historical literature, which includes 3440 landslides. On this basis, eight variables, including elevation, slope, aspect, slope position, distance to the fault, land cover, lithology and distance to the stream were selected to examine their influence on the landslides in the study area. Landslide number density (LND) and landslide area percentage (LAP) were used as evaluation indicators to analyze the spatial distribution characteristics of the landslides. The results show that most of the landslides are situated at elevations from 500 to 1400 m. The LND and LAP reach their peaks at slopes of 10–20°. Slopes facing WNW and NW directions, and middle and lower slopes are more prone to sliding with higher LND and LAP. LND and LAP show a decreasing trend as the distance to the fault or stream increases, followed by a slow rise. Landslides occur primarily in the areas covered by crops. Regarding lithology, the regions covered by the Quaternary loess and Cretaceous gravels are the main areas where landslides occur. The results would be helpful for further understanding the developmental characteristics and spatial distribution of landslides on the Loess Plateau, and also provide a support to subsequent landslide susceptibility mapping in this region.

Relationships Between Soil Microbial Communities and Plant Communities on Different Slope Aspects in a Subalpine Coniferous Forest

Purpose The local microclimate of different slope aspects in the same area can not only impact soil environment and plant community but also affect soil microbial community. However, the relationship between aboveground plant communities and belowground soil microbial communities on various slope aspects has not been well understood.Methods We investigated the above- and belowground relationship on different slope aspects and explored how soil properties influence this relationship. Plant community attributes were evaluated by plant species richness and plant total basal area. Soil microbial community was assessed based on both 16S rRNA and ITS rRNA, using High-throughput Illumina sequencing. Results There was no significant correlation between plant richness and soil bacterial community composition on the north slope, but there was a positive correlation on the south slope and a significantly negative correlation on the flat site. There was a significantly negative correlation between soil fungal community composition and plant total basal area, which did not change with the slope aspect. In addition, there was no significant correlation between plant community species richness and soil microbial species richness.Conclusions In subalpine coniferous forests, the relationship between plant-soil bacteria varies with slope aspect, but the plant-soil fungi relationship is relatively consistent across different slope aspects. These results can improve our understanding of the relationship between plant and soil microorganisms in forest ecosystems under microtopographic changes and have important implications for the conservation of biodiversity and forest management in subalpine coniferous forests.

Geospatial Technology for Landslide Susceptibility Mapping along the Vathalmalai Ghat road section, South India

Landslides are among the most prevalent and harmful hazards. Assessment of landslide susceptibility zonation is an important task in reducing the losses of lifeand properties. The present study aims to demarcate the landslide prone areas along the Vathalmalai Ghat road section (VGR) using remote sensing and GIS techniques. In the first step, the landslide causative factors such as geology, geomorphology, slope, slope aspect, land use / land cover, drainage density, lineament density, road buffer and relative relief were assessed. All the factors were assigned to rank and weight based on the slope stability of the landslide susceptibility zones. Then the thematic maps were integrated using ArcGIS tool and landslide susceptibility zonation was obtained and classified into five categories ; very low, low, moderate, high and very high. The landslide susceptibility map is validated with R-index and landslide inventory data collected from the field using GPS measurement. The distribution of susceptibility zones is ; 16.5% located in very low, 28.70% in low, 24.70% in moderate, 19.90% in high and 10.20% in very high zones. The R-index indicated that about 64% landslide occurences correlated with high to very high landslide susceptiblity zones. The model validation indicated that the method adopted in this study is suitable for landslide disaster mapping and planning.

GIS-BASED OPTIMUM SITE SELECTION FOR SOLAR ELECTRIC VEHICLE CHARGING STATION: ANKARA-ISTANBUL HIGHWAY CASE

Energy sources are divided into renewable and non-renewable sources. It can be seen that non-renewable energy resources are not adequately meeting the increased demands of worldwide technological developments, increasing population, and global consumption. Therefore, the demand for renewable resources is increasing day by day. When it comes to the use of non-renewable carbon-based fossil fuels, one of the first areas that come to mind is undoubtedly the Automotive sector. Today, it is realized that one of the main reasons for the lack of electric motor cars compared to petroleum fuelled cars, is the scarcity of electric vehicle charging stations and the difficulty of their accessibility. In this study; an analysis of solar-powered electric charging stations site selection was carried out for electric vehicles. The Ankara-Istanbul highway, which has a high traffic density, was chosen as the sample route for the study. Within the scope of the study, the areas where stations can be installed on the highway were carried out using the Multi-Criteria Decision Making Method with the help of Geographic Information System. Solar radiation, slope, aspect, land use/land cover, traffic volume and proximity to the road, criteria of the route, and site selection analysis were determined as input data. The maps of the determined criteria were arranged according to the study area and prepared for analysis. The criteria maps obtained were reclassified according to the above-mentioned criteria and scoring system. After the reclassification process, the weighting of each criteria which affect the analysis was determined by the researched literature and an overlapping process was carried out. According to the results map produced as a result of the overlay analysis, the appropriate area has been determined for the electric charging stations working with solar energy. On the defined route within the scope of the study, a proposal has been made for a total of 13 stations, 8 in Ankara, 3 in Bolu, 1 in Kocaeli, and 1 in Istanbul. This study, it is aimed to encourage automobile users to make greater use of electric motor vehicles, which would be a more environmentally friendly and sustainable choice, and ultimately more economical.

Characterizing Groundwater Potential Using GIS-Based Machine Learning Model in Chihe River Basin, China

Mapping of groundwater potential over space, built by synergizing environmental variables and machine learning models, was of great significance for regional water resources management. Taking the Chihe River basin in Anhui province as an example, thirteen influence factors were used to predict the spatial distribution of groundwater, including elevation, slope, aspect, plan curvature, profile curvature, topographic wetness index (TWI), drainage density, distance to rivers, distance to faults, lithology, soil type, land use, and normalized difference vegetation index (NDVI). The potential of groundwater resource in this region was predicted using GIS-based machine learning models, including logistic regression (LR), deep neural networks (DNN), and random forest (RF) model. Then, the accuracy of prediction results was evaluated by calculating the RMSE, MAE and R evaluation index. The results show that there is no collinearity among the 13 environmental impact factors, which can provide corresponding environmental variables for the evaluation of regional groundwater potential. Machine learning models show that groundwater potential is concentrated in moderate to high potential areas. Among them, the moderate to the high potential of this area accounted for 81.14% in the LR model, 90.36% and 87.55% in the DNN model and the RF model, respectively. According to the result of these evaluation indexes, the three models all have high prediction accuracy, among which the LR model performs more prominently. The good prediction capabilities of these machine learning technologies can provide a reliable scientific basis for spatial prediction of groundwater potential and management of water resources.