Slope Degree Research Articles

Site Location and Construction of Ski Resorts Using Geographical Information System (GIS) in Isfahan Province

Considering the dry and hot climate governing Isfahan province, development of winter tourism (tourism development and providing the conditions for tourism) can bring in a different attraction for this province adding to its tourism potentialities i.e. the countless historical and cultural tourism attractions. The availability of high mountainous regions appropriately covered with snow can provide a susceptible field for winter tourism. This research is applied-developmental in nature aimed to locate and identify the appropriate areas and points for the construction of ski resorts in Isfahan province. For positioning and identifying the susceptible areas for the construction of ski resorts, the Isfahan’s high areas over than 2300 m were taken into account which were identified by applying analytic functions technique and satellite images. For locating, 7 measures including height, slope degree, temperature, snow depth, distance from the residential areas, infrastructure facilities and accessibility to communication roads were used. Besides, the statistical data obtained from 21 synoptic stations including that of Isfahan as well as nearby stations of Borujen, Saman, Si Sakht and Yasuj were also used. As per the obtained maps, Fereydunshahr, Semirom and a part of Chadegan were of high capability for the construction of ski resorts and winter tourism, respectively. In addition, the near distance between several villages and towns located close to these regions not only can play an effective role in the economic variety and development of these regions but also can significantly assist the management and maintenance of the ski resorts which should be deemed as a very important issue for the survival of such ski resorts.

Gully erosion susceptibility mapping using GIS-based multi-criteria decision analysis techniques

This research introduces a scientific methodology for gully erosion susceptibility mapping (GESM) that employs geography information system (GIS)-based multi-criteria decision analysis. The model was tested in Semnan Province, Iran, which has an arid and semi-arid climate with high susceptibility to gully erosion. The technique for order of preference by similarity to ideal solution (TOPSIS) and the analytic hierarchy process (AHP) multi-criteria decision-making (MCDM) models were integrated. The important aspect of this research is that it did not require gully erosion inventory maps for GESM. Therefore, the proposed methodology could be useful in areas with missing or incomplete data. Fifteen variables reflecting topographic, hydrologic, geologic, environmental and soil characteristics were selected as proxies for gully erosion conditioning factors (GECFs). The experiment was conducted using 200 sample points that were selected randomly in the study area, and the weights of criteria (GECFs) were obtained using the AHP model. In the next step, the TOPSIS model was applied, and the weight of each alternative (sample points) was obtained. Kriging and inverse distance-weighted (IDW) methods were used for interpolation and GESM. Natural break method was used for classifying gully erosion susceptibility into five classes, from very low to very high. The area under the ROC curve (AUC) was used for validation. AHP results showed that distance to stream (0.14), slope degree (0.13) and distance to road (0.12) played major roles in controlling gully erosion in the study area. The values of points obtained by using the TOPSIS model ranged from 0.321 to 0.808. Verification results showed that kriging had higher prediction accuracy than IDW. The GESM results obtained by this methodology can be used by decision makers and managers to plan preventive measures and reduce damages due to gully erosion.

Phytodiversity and medicinal plant distribution in pasturelands of North Western Himalaya in relation to environmental gradients

This study aimed at elucidating phytodiversity of pasturelands of North-western Kashmir Himalayan biotic province in relation to various environmental gradients, with added focus on assessing distribution of important threatened medicinal plant taxa across surveyed pasturelands. A total of 16 sites that spanned across a broad altitudinal gradient (2502–4120 m) were selected. Phytosociological data like density, cover, frequency and abundance of vascular flora were collected and processed using gradient analysis. Soil moisture, nitrogen, organic carbon, acidity and electrical conductivity, altitude, degree of slope and human disturbance were recorded from each site. Analysis of species composition showed a total of 293 species of vascular plants, belonging to 192 genera and 64 families recorded from surveyed sites. Rank abundance exhibited that majority of species are locally rare and patchily distributed, with over 60% of species recording frequencies between 0%–20% and none showing frequencies more than 80%. Species richness showed significant variations and ranged from 20 (Parihasmaidan) to 114 (Nagbarren) for macro and 3.53±2.11 (Thajwas) to 8.76± 1.01 (Marsar) for micro-scale of measurement. The Shannon-Wiener (H′) and Simpson’s diversity (Ds) indices also varied greatly and were recorded highest (H′= 2.76 & Ds= 0.36) for Marsar and lowest (0.87 & 0.62) for Parihasmaidan. The diversity attributes suggested that pasturelands with lower species richness and diversity on macro-scale were not always species poor and less diverse on micro- measurement scale. The life form groupings highlighted the hemicryptophytic character of vegetation and species with highest importance value index were Sibbaldia cuneata (5.71), Rumex nepalensis (2.89), Juniperus wallichiana (2.88), Cynodon dactylon (2.83), Poa annua (2.49) and Sambucus wightiana (2.41). The results of canonical correspondence analysis showed that effect of altitude and anthropogenic disturbance was overriding and among various environmental factors, species distribution was mainly correlated with altitude along first canonical axis, while to second axis anthropogenic disturbances were important. Using generalized additive model, these variables also appeared as significant predictors for distribution of various threatened taxa. The findings of this study may thus help in evolving an appropriate strategy and an ecological management tool for long term conservation and management of these mountain ecosystems.

Delineation of Groundwater Potential Zones of Semi-Arid Region of YSR Kadapa District Andhra Pradesh India using RS GIS and Analytic Hierarchy Process

Water scarcity due to increasing urbanization and population in urban and rural areas makes necessary planning for artificial groundwater recharge. Remote Sensing (RS), Geographic Information System (GIS) and Analytical Hierarchy Process (AHP) are advantageous tools to delineate the Groundwater Potential Zones (GWPZ) in arid and semi-arid areas of India. An aggregate of eight thematic layers affecting groundwater potential of the area were assigned appropriate weights dependent on the Saaty’s 9 point scale. These weights were normalized using AHP technique to delineate the GWPZ. About 2.30km2 shows very good groundwater potential (GWP), 162.10km2 shows good GWP, whereas 127.78km2 and 1.45km2 are under moderate and poor GWP, correspondingly. The structural hilly terrain located in the Eastern and Southern parts has a poor groundwater potential due to higher degree of slope and low permeability of clayey soils. This study can be helpful to identify the GWPZ of drought-prone zones useful for planning and development with integrated water resources management.

Estimation of Above Ground Biomass Using Support Vector Machines and ALOS/PALSAR data

L-band Synthetic aperture radar (SAR) data has been extensively used for forest aboveground biomass (AGB) estimation due to its higher saturation level. However, SAR backscatter is highly influenced by the topography characteristics along with the bio-geophysical properties of vegetation and underneath soil characteristics. This has limited the accuracy of directly relating the SAR backscatter with above ground biomass in highly undulated terrain. In this study, it has been observed that terrain degree of slope and aspect plays a vital role in influencing the SAR backscatter in addition with AGB. Because of this, the degree of slope and aspect along with SAR backscatter in HH (transmit and receive polarizations are horizontal) and HV (transmit horizontal and receive vertical) polarizations have been considered as inputs for Support Vector Machine (SVM) to improve the biomass retrieval accuracy. Our results demonstrate that the accuracy of AGB estimation over hilly terrain can be significantly improved by considering topographical characteristics in addition to L-band backscatter.

Evaluating connected and autonomous vehicles using a hardware-in-the-loop testbed and a living lab

Connected and autonomous vehicle (CAV) applications focusing on energy optimization have attracted a lot of attention recently. However, it is challenging to evaluate various optimizations and controls in real-world traffic scenarios due to safety and technical concerns. In light of this, our previous work has developed a hardware-in-the-loop (HIL) testbed with a laboratory powertrain research platform to evaluate CAV applications. An actual engine is loaded by a hydrostatic dynamometer whose loading torque is controlled in real-time by the simulated vehicle dynamics. The HIL testbed mimics the performance of a target vehicle and the dynamometer generates the same load as the target vehicle. In this work, the HIL testbed is further enhanced to match the performance of actual testing vehicles at the Federal Highway Administration (FHWA) and a living lab is developed to incorporate real traffic information. The same engine as the actual testing vehicles at the FHWA was installed and the vehicle models were calibrated using testing data from actual vehicles. The same roadway conditions (speed limit, the degree of road slope, etc.) were input into the testbed and the dynamometer generates the same load as an actual vehicle’s engine is getting. The HIL testbed emulates the performance of an actual vehicle and both fuel consumption and emissions are measured by precise instruments in the lab. In eight testing scenarios, the results have shown that the performance of the HIL testbed matches very well with the actual testing vehicles with about 1% error. In addition, the living lab has enabled the HIL testbed to interact with real traffic and extended the testing capabilities of the HIL testbed. Two new testing capabilities have been demonstrated through two CAV applications. This is an exciting result since the HIL testbed could provide an effective and economical way for the testing of fuel consumption and emissions on various roadway conditions for CAVs and other types of vehicles.

Wildfire Probability Mapping: Bivariate vs. Multivariate Statistics

Wildfires are one of the most common natural hazards worldwide. Here, we compared the capability of bivariate and multivariate models for the prediction of spatially explicit wildfire probability across a fire-prone landscape in the Zagros ecoregion, Iran. Dempster–Shafer-based evidential belief function (EBF) and the multivariate logistic regression (LR) were applied to a spatial dataset that represents 132 fire events from the period of 2007–2014 and twelve explanatory variables (altitude, aspect, slope degree, topographic wetness index (TWI), annual temperature, and rainfall, wind effect, land use, normalized difference vegetation index (NDVI), and distance to roads, rivers, and residential areas). While the EBF model successfully characterized each variable class by four probability mass functions in terms of wildfire probabilities, the LR model identified the variables that have a major impact on the probability of fire occurrence. Two distribution maps of wildfire probability were developed based upon the results of each model. In an ensemble modeling perspective, we combined the two probability maps. The results were verified and compared by the receiver operating characteristic (ROC) and the Wilcoxon Signed-Rank Test. The results showed that although an improved predictive accuracy (AUC = 0.864) can be achieved via an ensemble modeling of bivariate and multivariate statistics, the models fail to individually provide a satisfactory prediction of wildfire probability (EBFAUC = 0.701; LRAUC = 0.728). From these results, we recommend the employment of ensemble modeling approaches for different wildfire-prone landscapes.

Sustainable Urban Regeneration for Shrinking Cities: A Case from Japan

Population decline is leading to a shrinking city size in industrialized countries. In some developing countries, because majority of the population is concentrated in big cities, the population in undeveloped cities has begun to decline. Japan experienced rapid urban expansion surrounding industrial districts, including steeply sloped areas, between the 1950s and 1970s. In the past forty years, Japan’s population has decreased, and the average age of the population is increasing. The reduction in the size of cities, following population decreases is becoming an important issue, and the study of sustainable, concentrated urban planning to cope with shrinking city size is, therefore, necessary. We have conducted a case study using Yahatahigashi-ku to determine its redevelopment potential, based on a combination of urban geographic data. This paper (1) presents a typical case study using Geographic Information System (GIS) data to evaluate an aging and shrinking society; (2) explores the GIS design approaches configured for an aging society; and (3) evaluates the optimization of environmental performance for an urban regeneration plan. The primary factors related to this urban design case study included, a declining population, mixed urban land use, and the placement of public facilities. We developed a method involving the slope degree to evaluate land-use to model the importance of informational evaluation in the urban planning process. This method could contribute to the urban regeneration for an aging society and could also be applied to other aging and shrinking cities, in mountainous regions.

Rainwater harvesting capacity of soils subjected to reservoir tillage during rainfall on the Loess Plateau of China

Soil rainwater harvesting (SRWH) is an important process in rainfed farming areas. Improving the capacity for SRWH via tillage is essential in many parts of the world. In recent years, reservoir tillage (RT) has attracted attention because it was said that RT contributes to SRWH. The objectives of this study were to measure the cumulative soil-harvested rainwater (SHR) of slopes subjected to RT and to evaluate the contribution of RT to SRWH under different rainfall conditions. A smooth surface (SS) served as a control surface. Three slope degrees (5°, 15° and 25°) were subjected to low and heavy (60 and 120 mm/h) and long-term rainfall (90 min). The results showed that the cumulative SHR decreased to different extents under different rainfall intensities as the slope degree increased. On the gentle slope (5°) and under low rainfall intensity (60 mm/h), no significant differences in cumulative SHR were detected between the RT and SS treatments, whereas significant differences in cumulative SHR were detected between them on the steep slopes (15° and 25°) and under high rainfall intensity (120 mm/h). The differences in cumulative SHR among the different conditions occurred because the contribution of RT to SRWH varied as the soil surface properties changed (especially as surface depression storage decreased due to sediment deposition) under the conditions of long-term rainfall. For example, on the 5° slope at a rainfall intensity of 120 mm/h, the contribution of RT to SRWH was 18.58% during the 0-30-min rainfall stage but -14.84% during the 60–90-min stage, resulting in nearly equal cumulative SHR values between the RT slope and the SS slope. Our results suggest that RT is not necessary contribute to SRWH in all cases.

GIS-based landslide susceptibility mapping using numerical risk factor bivariate model and its ensemble with linear multivariate regression and boosted regression tree algorithms

In this study, a novel approach of the landslide numerical risk factor (LNRF) bivariate model was used in ensemble with linear multivariate regression (LMR) and boosted regression tree (BRT) models, coupled with radar remote sensing data and geographic information system (GIS), for landslide susceptibility mapping (LSM) in the Gorganroud watershed, Iran. Fifteen topographic, hydrological, geological and environmental conditioning factors and a landslide inventory (70%, or 298 landslides) were used in mapping. Phased array-type L-band synthetic aperture radar data were used to extract topographic parameters. Coefficients of tolerance and variance inflation factor were used to determine the coherence among conditioning factors. Data for the landslide inventory map were obtained from various resources, such as Iranian Landslide Working Party (ILWP), Forestry, Rangeland and Watershed Organisation (FRWO), extensive field surveys, interpretation of aerial photos and satellite images, and radar data. Of the total data, 30% were used to validate LSMs, using area under the curve (AUC), frequency ratio (FR) and seed cell area index (SCAI). Normalised difference vegetation index, land use/ land cover and slope degree in BRT model elevation, rainfall and distance from stream were found to be important factors and were given the highest weightage in modelling. Validation results using AUC showed that the ensemble LNRF-BRT and LNRFLMR models (AUC = 0.912 (91.2%) and 0.907 (90.7%), respectively) had high predictive accuracy than the LNRF model alone (AUC = 0.855 (85.5%)). The FR and SCAI analyses showed that all models divided the parameter classes with high precision. Overall, our novel approach of combining multivariate and machine learning methods with bivariate models, radar remote sensing data and GIS proved to be a powerful tool for landslide susceptibility mapping.

Ecological analysis of Kashin-Beck osteoarthropathy risk factors in Tibet\u2019s Qamdo City, China

We studied Tibet’s Qamdo City, which currently hosts the most serious prevalence of Kashin-Beck osteoarthropathy (KB) in China. This study utilizes the geographical detector (GeoDetector) algorithm to measure the individual and interactive influences of risk factors on KB and to quantify the highest potential risk subzones of each principal factor. With a comprehensive consideration of 13 possible related factors, namely, the tectonic division, stratum, moisture index, gross domestic product, mean annual precipitation, soil type, groundwater type, elevation, mean annual temperature, vegetation type, geomorphic type, slope degree and slope aspect, our results indicate that the main exposure factors for KB in Qamdo City are geological factors (tectonic division and stratum), wetting factors (moisture index and mean annual precipitation), and an economic factor (gross domestic product). In contrast, other factors have little effect on the prevalence of KB in Qamdo City. All 13 factors either nonlinearly or bivariately enhance each other, and the interactions between these factors can increase the prevalence of KB. Consequently, it can be inferred that KB in Qamdo City is caused primarily by a set of multiple and interrelated disease risk factors.

Flood Susceptibility Mapping on a National Scale in Slovakia Using the Analytical Hierarchy Process

Flood susceptibility mapping and assessment is an important element of flood prevention and mitigation strategies because it identifies the most vulnerable areas based on physical characteristics that determine the propensity for flooding. This study aims to define the flood susceptibility zones for the territory of Slovakia using a multi-criteria approach, particularly the analytical hierarchy process (AHP) technique, and geographic information systems (GIS). Seven flood conditioning factors were chosen: hydrography—distance from rivers, river network density; hydrology—flow accumulation; morphometry—elevation, slope; and permeability—curve numbers, lithology. All factors were defined as raster datasets with the resolution of 50 x 50 m. The AHP technique was used to calculate the factor weights. The relative importance of the selected factors prioritized slope degree as the most important factor followed by river network density, distance from rivers, flow accumulation, elevation, curve number, and lithology. It was found that 33.1% of the territory of Slovakia is characterized by very high to high flood susceptibility. The flood susceptibility map was validated against 1513 flood historical points showing very good agreement between the computed susceptibility zones and historical flood events of which 70.9% were coincident with high and very high susceptibility levels, thus confirming the effectiveness of the methodology adopted.

Research on Dynamic Evaluation Model of Slope Risk Based on Improved VW-UM

There are many accidents of slope failure due to rainfall at home and abroad, which have caused heavy casualties and property losses. Stability analysis and evaluation of slope have become a research hotspot. Aiming at the slope stability under different rainfall, this paper takes Yuebao Open-pit Mine slope as an example, has constructed a dynamic variable weight (VW) model of influencing factors on slope stability, and has analyzed the dynamic change and correlation of the slope indexes weights under different monthly maximum rainfall. On this basis, the dynamic evaluation model of slope stability has been established based on uncertainty measurement (UM), and the risk importance (RI) q which is proposed has quantitatively evaluated the risk degree of slope. The results show that under different monthly maximum rainfall the weight of each index is no longer a fixed value but a nonlinear and dynamic change law, and there is a strong correlation among the monthly maximum rainfall, internal friction angle, and cohesion. In addition, the q increases gradually with the increase of the monthly maximum rainfall, and the stability evaluation results are highly consistent with the HP1 slope, which have verified the reliability of the dynamic evaluation model. So, it can provide technical support for the safety production and management of open-pit slope and can also provide reference for related research.

Influencia de la cobertura, pendiente y profundidad, sobre el carbono y nitrógeno del suelo

El estudio conjunto del carbono orgánico del suelo (COS) y el nitrógeno total del suelo (Nt) es importante debido a que sus ciclos interaccionan, además de que son considerados parámetros de fertilidad, calidad e impacto. Sus contenidos en el suelo inciden en la productividad de los bosques y tienen relación con la mitigación del cambio climático cuando el suelo se conserva. Se realizó un muestreo de suelos en la Estación Forestal Experimental de Zoquiapan, con el objetivo de obtener y analizar el contenido de COS y Nt del suelo a las profundidades de 0 a 10, 10 a 20 y 20 a 30 cm, con tres grados de pendiente donde se desarrollan bosques de oyamel, pino y pino-aile. Los mayores almacenes de COS y Nt se ubicaron en los primeros 10 cm. El suelo con la cobertura de oyamel, pendiente mayor y profundidad menor presentó el mayor contenido de COS y Nt (132.20 y 14.19 Mg ha-1 respectivamente). El suelo con cobertura de pino, pendiente y profundidad mayor tuvo los contenidos más bajos de COS y Nt (30.86 y 3.37 Mg ha-1, respectivamente). Se concluye que los contenidos de COS y Nt mostraron diferencias por tipo de cobertura, por pendiente y por profundidad. Aunque fue con relación a la profundidad que los contenidos de COS y Nt tuvieron un comportamiento más regular, que disminuye a medida que la profundidad se incrementó, independientemente de la cobertura y pendiente.

Decreased Posterior Tibial Slope Does Not Affect Postoperative Posterior Knee Laxity After Double-Bundle Posterior Cruciate Ligament Reconstruction

Background: Recent clinical studies identified sagittal plane posterior tibial slope as a risk factor for increased postoperative laxity after single-bundle posterior cruciate ligament reconstruction (PCLR). Purpose/Hypothesis: To retrospectively compare the degree of posterior tibial slope and its effect on posterior tibial translation (PTT) after double-bundle (DB) PCLR. Our null hypothesis was that preoperative tibial slope would not be associated with graft laxity. Study Design: Case series; Level of evidence, 4. Methods: Patients who underwent DB PCLR between 2010 and 2017 by a single surgeon were retrospectively analyzed. Measurements of posterior tibial slope were performed on lateral radiographs, and PTT was measured with pre- and postoperative kneeling stress radiographs. Simple and multiple linear regression was performed to estimate the unadjusted and adjusted effect of tibial slope on postoperative graft laxity, respectively. Results: A total of 103 patients with posterior cruciate ligament tears and subsequent reconstructions were included. There was a significant reduction of the mean ± SD side-to-side difference in PTT between stress radiographs (preoperative, 10.6 ± 2.7 mm; postoperative, 1.5 ± 2.6 mm; mean difference, 9.1 mm; 95% CI, 8.4-9.8; P < .001). Linear regression analysis revealed no significant correlation between preoperative posterior tibial slope and the amount of side-to-side difference in PTT on postoperative stress radiographs obtained at a mean 18.5 months (R = −0.115, P = .249). Combined ligament injury (beta = −1.01; 95% CI, −2.00 to −0.01; P = .047) was a significant independent predictor of decreased postoperative side-to-side difference in PTT. Conclusion: Graft laxity, determined by PTT in posterior kneeling stress radiographs, was not influenced by decreased posterior tibial slope after DB PCLRs. The observed results in the current study support the use of DB PCLR. Future studies should be conducted to compare the effect of tibial slope after SB PCLR and DB PCLR at long-term follow-up.

Spatial modelling of gully headcuts using UAV data and four best-first decision classifier ensembles (BFTree, Bag-BFTree, RS-BFTree, and RF-BFTree)

Despite the importance of delineating spatial modelling of gully headcuts (GHs) in erosion-prone environments, assessments of the factors that control the occurrence of headcuts is lacking. To fill this gap in the research, we identified 129 GHS field surveys. These 129 cases were randomly divided into two groups: 90 GHs (70%) for model training and 39 GHs (30%) for model validation. Subsequently, new unmanned aerial vehicle (UAV) imagery is used to develop spatial modelling to predict the location of GHs at sites prone to soil erosion in Golestan Province, Iran. Mapping GHs enables evaluation of 4 machine-learning techniques (or ensembles) – best-first decision tree (BFTree), bagging best-first decision tree (Bag-BFTree), random-subspace best-first decision tree (RS-BFTree), and rotation-forest best-first decision tree (RF-BFTree) – for modelling GHs. We use the information-gain ratio method to analyze the relationships between GHS and 22 GH conditioning factors. The 4 ensemble outputs are validated using a receiver operating characteristic (ROC) curve. The areas under the curves (AUCs) for prediction rates of the ensemble methods applied to the training group are BFTree – 88.3%, Bag-BFTree – 92.7%, RS-BFTree – 95.7%, and RF-BFTree – 93.2%. The AUCs for the model-validation group cases, however, are 84.9%, 94.1%, 97.4%, and 9.18%, respectively. Therefore, RS-BFTree is, statistically, the most effective ensemble method for accurate modelling of GHs. Variable-importance analyses using information-gain ratio indicate that out of 22 GH-influential factors, land use, slope degree, and slope-length are of more importance in developing of GH occurrence. Finally, to address the need for detailed observations and highly accurate erosion data in the field, UAV image-acquisition technologies are demonstrated.

Assessment of the importance of gully erosion effective factors using Boruta algorithm and its spatial modeling and mapping using three machine learning algorithms

The Maharloo watershed has witnessed many gullies in the recent due to the specific topo-climatic conditions and man-made activities in that area. The present study is set out to address this issue by producing gully erosion prediction maps via three machine learning algorithms including RF, SVM and BRT in Maharloo watershed, Fars province, Iran. Also, this research attempted to consider the importance of effective factors in the occurrence of gully erosion using Boruta algorithm. To this end, gully erosion locations were identified by extensive field surveys as well as the use of already prepared gully raster map of Maharloo watershed. Then, sixteen causative factors of gully erosion such as elevation, slope degree, slope aspect, plan curvature, TWI, distance from rivers, distance from roads, drainage density, lithology, annual mean rainfall, NDVI, land use and some soil characteristics (pH, clay percent, electrical conductivity-EC, and silt percent) were identified and their maps were produced and classified in the GIS. In this study, the relationships among each agent and gully erosion were defined employing the evidential belief function (EBF) algorithm and the weight of each factor's classes was determined. On the other hand, the results of the collinearity test among the factors showed that sand percentage agent had a VIF > 5; therefore, this covariate was removed from the model. Also, the results of the importance of effective factors using Boruta algorithm indicated that three factors including land use, distance from river, and clay percent had the most noticeable importance in the occurrence of gully erosion in the study area. Finally, the gully erosion susceptibility maps were produced using the RF, BRT, and SVM models in the R statistical software. The results of machine learning techniques were evaluated employing 30% of unused locations in the modeling process as well as the receiver operating characteristic (ROC) curve. Also, in the current research, try to assess the fitting performance of models and their robustness using sensitivity rate, specificity rate, Cohen's Kappa, and 4-fold cross-validation measures. Results showed that the final gully erosion susceptibility maps had an excellent accuracy with AUC values of validation data sets by scenarios 7 and 9 independent factors on gully erosion, respectively (SVM = 0.957, 0.975, RF = 0.991, 0.986, BRT = 0.913, 0.913). The fitting performance measures and robustness technique (4-fold cross-validation) also confirmed the achieved validation results. In order to control and prevent this type of erosion in the Maharloo watershed, there should be protective actions and watershed management measures in place at the primary stages, especially at the beginning of the gully erosion, to control the development of the gully erosion.

A particle-based optimization of artificial neural network for earthquake-induced landslide assessment in Ludian county, China

The focal point of this study is to assess the efficacy of a state-of-the-art optimization technique namely, particle swarm optimization (PSO) for enhancing the performance of the artificial neural network (ANN) in modeling the seismic landslides at Ludian districts, China. Twelve geological and hydrological landslide-conditioning factors namely, elevation, lithology, slope degree, slope aspect, stream power index, peak ground acceleration, topographic wetness index, distance to river, distance to road, distance to fault, normalized difference vegetation index and plan curvature were considered within a geographic information system (GIS). After achieving the optimal structure of the multilayer perceptron neural network, the PSO algorithm was applied to improve its efficiency. The landslide susceptibility maps were generated in a GIS environment and area under the curve (AUC) criterion was used to assess the integrity of employed predictive models. The results showed that after applying the PSO algorithm, AUC experiences a significant increase from 0.765 to 0.825 in the validation phase. Moreover, respective AUCs of 0.812 and 0.828 obtained for the training phase of ANN and PSO-ANN reveal the efficiency of the proposed algorithm in improving the ANN accuracy.

Two novel neural-evolutionary predictive techniques of dragonfly algorithm (DA) and biogeography-based optimization (BBO) for landslide susceptibility analysis

Due to the wide application of evolutionary science in different engineering problems, the main aim of this paper is to present two novel optimizations of multi-layer perceptron (MLP) neural network, namely dragonfly algorithm (DA) and biogeography-based optimization (BBO) for landslide susceptibility assessment at a study area, West of Iran. Utilizing 14 landslide conditioning factors, namely elevation, slope aspect, plan curvature, profile curvature, soil type, lithology, distance to the river, distance to the road, distance to the fault, land cover, slope degree, stream power index (SPI), and topographic wetness index (TWI) and rainfall as the input variables, and 208 historical landslides as target variable, the required spatial database is created. Then, the MLP is synthesized with the mentioned algorithms to develop the proposed DA-MLP and BBO-MLP ensembles. Three accuracy criteria of mean square error, mean absolute error, and area under the receiving operating characteristic curve are used to evaluate the performance of the models and also to develop a score-based ranking system. As the first outcome, the application of the DA and BBO metaheuristic algorithms enhances the accuracy of the MLP. Moreover, referring to the calculated total ranking scores of 6, 14, and 16, it was revealed that the BBO performs more efficiently than DA in optimizing the MLP.

Novel hybrids of adaptive neuro-fuzzy inference system (ANFIS) with several metaheuristic algorithms for spatial susceptibility assessment of seismic-induced landslide

Strong ground motions usually trigger lots of slope failures in the affected area. In this work, we analyse the occurrence likelihood of earthquake-triggered landslide by employing the ensembles of adaptive neuro-fuzzy inference systems (ANFIS) with four well-known metaheuristics techniques, namely particle swarm optimization (PSO), genetic algorithm (GA), ant colony optimization (ACO), and differential evolution (DE) algorithms. Twelve landslide conditioning factors namely, elevation, slope degree, lithology, peak ground acceleration (PGA), stream power index (SPI), topographic wetness index (TWI), distance to road, distance to river, distance to fault, normalized difference vegetation index (NDVI), slope aspect, and plan curvature are considered within the geographic information system (GIS) to produce the required spatial database. In this paper, frequency ratio (FR) model is used to evaluate the spatial interaction between the landslides and conditioning factors. Meantime, among a total of 458 marked earthquake-induced landslides, 366 (80%) are specified to the learning process, and the remaining 92 (20%) landslides are used to evaluate the accuracy of applied models. The landslide susceptibility maps are generated in the GIS environment. Three accuracy criteria of mean square error (MSE), root mean square error (RMSE), and area under the receiving operating characteristic curve (AUROC) are used to develop a ranking system for comparing the integrity of the designed models. The total ranking scores (TRSs) of 15, 8, 10, and 18, respectively, obtained for PSO-ANFIS, GA-ANFIS, ACO-ANFIS, and DE-ANFIS revealed the superiority of the DE algorithm compared to other metaheuristics techniques. Also, the DE-ANFIS emerged as the fastest ensemble, due to the highest convergence speed obtained for this model.