Types Of Slope Failures Research Articles

Q-Slope System for Assessing the Stability of Rock Slopes in Selected Area, Mergasur Town, Erbil, Kurdistan Region, NE Iraq

Rock slope, slope height, rock discontinuity orientations, and undesigned excavated slopes are the primary contributing factors to the instability of the road in the mountain area. The eight rock slopes in Mergasur town, NE-Iraq, were chosen to be assessed for stability using the kinematic approach with DIPS v6.008 software to determine the type of slope failure and the Q-slope system applied to determine the stability condition. This is an efficient approach for classifying rock slope engineering. According to the kinematic results, stations 1–5 and 7 may have planar sliding, whereas stations 4–8 may experience wedge sliding, stations 1, 2, and 7-8 may experience flexural toppling, and station 3 may have direct toppling. In accordance with the Q-slope system results, stability conditions are determined by projecting the Q-slope and slope angle values on the Q-slope chart.

Field Investigation and Finite Element Analysis of Landslide-Triggering Factors of a Cut Slope Composed of Granite Residual Soil: A Case Study of Chongtou Town, Lishui City, China

Landslides caused by excavations and precipitation events are widespread types of slope failures in southwest Zhejiang, China, in areas with granite residual soil. Investigations of the effect of high precipitation on the hydrological response, stability, and evolutionary mechanism of cut slopes in granite soil areas are lacking. The characteristics of historical landslides in Chongtou Town in southwestern Zhejiang were summarized, and a typical slope was selected for analysis. The hydraulic and mechanical properties of the residual soil and fully weathered granite were tested, and the surface displacements on the slope were monitored. Geo-studio was utilized to establish a coupled seepage-deformation model to validate the numerical method and investigate the landslide-triggering factors of the cut slope. The results showed nearly all historical landslides in Chongtou Town were triggered by precipitation events, and the slide bodies consisted of residual soil and fully weathered granite with similar geotechnical properties. The simulated and measured horizontal displacements were in good agreement, indicating the reliability of the established model and parameters. The stability coefficient decreased with an increase in the gradient or height of the cut slope. The critical height values were 5.3 m, 5.5 m, 5.7 m, 6.0 m, and 6.3 m at slopes of 60°, 65°, 70°, 75°, and 80°, respectively. Long-term torrential rain and short-term high-intensity precipitation events are likely to trigger landslides when the precipitation event lasts longer than 26 h and 78 h, respectively. The landslide formation includes four stages: slope evolution, formation of unloading zone at slope foot, migration and loss of soil particles, and instability of the cut slope. The findings can be used to prevent and manage landslides on cut slopes in areas with granite residual soil.

Infiltration and Failure Behavior of an Unsaturated Soil Slope under Artificial Rainfall Model Experiments

Slope disasters often include soil erosion and shallow landslides. These types of slope failure can occur in unsaturated soil. In this study, artificial rainfall is applied to a compacted soil slope in a laboratory to investigate the effects of rainfall intensity, initial moisture content and relative compaction on infiltration and failure behavior of an unsaturated soil slope subjected to rainfall infiltration. Soil moisture probes installed in the soil slope were used to monitor soil moisture content during the experiment. Test results show that the soil saturation at the toe of the slope was observed to be higher than other areas of the slope following the onset of rainfall. Gradually, the saturation advanced towards the crest, resulting in the formation of a wetting band along the slope surface. With increasing rainfall duration, the wetting band progressed further downwards along the slope. The failure of the slope began at the crest and junction of the slope, and the primary cause was soil erosion resulting from high-intensity rainfall. The most significant variable affecting infiltration behavior is relative compaction, followed by the initial moisture content of the compacted slope. During the experiment, the low hydraulic conductivity of the saturated soil caused most of the rainfall on the slope to become surface runoff, which minimized the impact of rainfall intensity on infiltration behavior. Specifically, the hydraulic conductivity of soil compacted at optimal moisture content and 90 R.C. is only 7.041 × 10-5 cm/sec or 2.53 mm/h, which is much lower than rainfall intensities of 80 mm/h and 160 mm/h. In addition, soil saturation contours facilitated visualization and quantification of the infiltration behavior of slopes, enabling a more detailed analysis of experimental results. These results help understand the behavior of unsaturated soil slopes under artificial rainfall conditions and aid in designing effective slope stabilization measures to prevent slope failure and minimize the risk of landslides.

Potensi longsor berdasarkan analisis kinematik pada area low wall PT. Bukit Asam Tbk, site Tanjung Enim, Sumatera Selatan

PT. Bukit Asam Tbk is an open-pit coal mining company in Muara Enim, Soutgh Sumatra. In open-pit mining activities, slope stability analysis is carried out to evaluate the mine in order to create a safe mining process. Several types of slope failure are associated with geological structures. This research was conducted to identify the type of landslides in the low wall area of Pit X PT. Bukit Asam Tbk and determine the slope stability factor based on discontinuity data using the scanline method at 8 observation points that represent the lithology of the low wall area. Methods used in this research is kinematic analysis, slope stability analysis on plane slide types and wedge. Based on the kinematic analysis, it was identified that the Pit X low wall area has the potential for plane and wedge type landslides with a relatively stable slopes.

Mass transport deposits in reflection seismic data offshore Oregon, USA

AbstractSubmarine landslides associated with the Cascadia subduction zone offshore of the Pacific northwest United States and Canada represent significant natural geohazards. Mapping past submarine landslide deposits is critical for understanding present and future slope failure and tsunami hazard potential. We focus on the portion of Cascadia offshore Oregon to map the occurrences of submarine landslide deposits (mass transport deposits [MTDs]) in the subsurface using recent high‐resolution reflection seismic data. We identified 133 MTDs and categorized them based on their present morphology inferred from their acoustic characteristics as disintegrative or blocky. Interestingly, nearly 76% of the MTDs are located in the northern Oregon margin and many of these are non‐cohesive disintegrative deposits. MTDs are less common in the southern Oregon margin, however, they were also much larger and more cohesive than those found in the north. The differences are not likely to be related to differences in earthquake intensity but rather sedimentation rates and basin structures. Specifically, the northern Oregon margin is proximal to the sediment‐delivery systems of the Columbia River and has landward verging fold‐and‐thrust structures, whereas the southern Oregon margin is relatively sediment starved and has seaward verging structures resulting in fewer steep ridges. Because of the higher sedimentation rates, the northern Oregon margin may be prone to more frequent and disintegrative types of slope failures. In contrast, the southern margin may have enhanced slope stability due to seismic strengthening and lower sedimentation rates. However, when slope failures do occur in the southern Oregon margin, they tend to be more cohesive and blocky. Therefore, even though there are fewer slope failures in the southern Oregon margin, there is still hazard potential because fast‐moving cohesive slope failures can generate tsunami.

Stability assessment of obliquely-bedded rock cuts using multi-prong procedures – case study

The stability of vertical cuts in rocky strata, associated with the provision of the transportation infrastructure through a mountainous terrain, is always a challenge for the geotechnical engineers. The problem becomes further complex if the cuts are parallel or near parallel to the bedding planes. Such a scenario results in all sorts of slope instability scenarios, including planar, wedge, rockfall, and toppling failure. A linear project was planned to pass through the mountainous stretches of western Saudi Arabia. The rock slopes exposed at the site after the excavations constitute igneous origin Granite/Granodiorite rock present in a moderately to highly weathered state and consist of two sets of discontinuities; one running almost parallel to slope faces and another nearly orthogonal to the major set of discontinuities. Based on the orientation of the discontinuities along the cuts on both the sides of the excavation, there is a high probability of all types of slope failures, including planar, wedge, toppling, or boulder/rockfall. This paper presents details of geologic field mapping, field and laboratory testing, and the software analysis of several modes of the possible slope failure modes. The study was carried out considering all the potential triggering factors, including rainfall, under both static and dynamic/seismic conditions. The paper also discusses the slope failure prevention measures recommended based on the interpretation of the field and laboratory data, software analysis, and the construction sequence.

Characteristics and susceptibility zonation of landslides in Wabe Shebelle Gorge, south eastern Ethiopia

Geohazards like landslides are widely spread in Ethiopia, especially in the steep and hilly areas of the highlands and Rift escarpments. One of the areas which are highly affected by landslides and associated problems is the Wabe Shebelle gorge in Southeastern Ethiopia. Such hazards have caused damage to roads, farmlands, and dwelling houses and othee engineering infrastructures. Therefore the purpose of this study was to evaluate the characteristics of landslides, define the major factors causing slope failures, and develop landslide susceptibility zonation which could be used for development planning. The research involved: (a) comprehensive field survey/inventory of failed or potentially unstable slopes, (b) evaluation of the geological and geotechnical properties of the soils and rocks, (c) assessment of the hydrogeological conditions of the area, (d) identifying the major factors controlling slope instability, and (e) landslide susceptibility zonation using the Analytical Hierarchy Process (AHP) and Frequency Ratio (FR) methods. The results of the study show that the major types of slope failures in the area include rockfalls, debris/earth slides, and rockslides. The main parameters influencing slope failures include slope angle, aspect, lithology, slope curvature, elevation, distance to road, distance to streams/rivers, and land use/cover. Results of the GIS-based landslide susceptibility mapping show that the most susceptible areas are those which are characterized by the following crucial conditions: (a) underlain by basalt and limestone formations, (b) slope gradients higher than 30°, and (c) with slope facing to east and northeast. A combination of both triggering, and conditional factors is believed to have contributed to the initiations of landslides, including road excavations and uncontrolled runoff. Based on the result, the following mitigations measures are recommended: (1) design of proper drainage structure on the roadside, (2) design of proper slope cuts along the road corridor and select planned dumping areas of road cut materials, (3) provision of retaining structures which resists the loads imposed by the slide material and integrated with sufficient drainage systems. In addition, it is advisable to promote bio-engineering as it could help to increase the stability of slopes and enhance the sustainability of roads and other infrastructures.

Geotechnical Investigation and Numerical Analysis of Slope Failure: A Case Study of Landslide Vulnerability Zone in Kolli Hills, Tamil Nadu

Abstract Landslides are the downward movement of materials under the influence of gravity when shear stress exceeds the shear strength of the material. It includes various movements resulting in complex type of slope failures which commonly occurred on cut slopes of Ghat roads in mountaneous region. The study area chosen for the geotechnical investigation is Kolli hills situated in the tail end of the Eastern Ghats in Namakkal district of Tamil Nadu, India. The ghat road section of 20 km stretch along with 70 hairpin bends, connects the foothills at Karavallikkombai to Sholaikkadu at the top is selected for the present study. The hill is situated at a fault zone which is extended from Mettur dam, Salem district, Tamil Nadu. In this study, undisturbed soil samples were collected from 10 landslide locations and tested for its index and engineering properties. Based on the test results, static slope stability analysis using Modified Bishop method and dynamic slope stability analysis using Simplified Newmark method were carried out to find out factor of safety of the slopes which is used to derive the slope stability assessment of the study area. The landslide hazard zone assessment was carried out to identify the landslide prone areas.

Retrogressive Failure of Reservoir Rim Sandy Slopes Induced by Steady-State Seepage Condition

Reservoir rim slopes often experience seepage-induced slope instability during rainfall season. The predominant phenomenon observed during monsoons is the establishment of continuous seeping conditions, either steady or unsteady in nature. The infiltrated rainwater seeping toward the drainage basin may induce instability in the slope. This paper presents results from an experimental study conducted to investigate the failure mechanism of a cohesionless soil slope under a steady-state seepage condition. Retrogressive multiple rotational slide type of slope failure occurred during experimentation. It was observed that the failure didn’t occur in one go; instead, it was progressive with time. In usual practice by engineers, while performing numerical simulations for a field problem, the focus is on the formation of failure surface and deformations observed. But, the limitation with such studies is that the movement of the slope surface over a period of time cannot be investigated. It is, therefore, suggested that emphasis should be laid upon the time-dependent analysis as well.

A laboratory and field-monitoring experiment on the ability of anti-slide piles to prevent buckling failures in bedding slopes

Buckling failure is a special form of a landslide, and it has been little debated in the literature so far. There have been few studies conducted on this type of slope failure, and the corresponding reinforcement measure research has also been rarely conducted. Therefore, it is nearly impossible to provide systematic guidance for the reinforcement and monitoring of such a slope. In this study, a new type of slope test system is developed, and the reinforcement effect of double-row piles was studied using simplified laboratory tests. Under the conditions of no pile and piles, load tests on the sliding body were carried out, and the ultimate loads that can be borne by the slope sliding body under these two conditions were analyzed. The multivariate information evolution of stress, displacement, and pile deformation under these two conditions were studied using multiple monitoring methods. The results showed that anti-slide piles can significantly improve the ability of the sliding body to withstand external loads. For the condition of no piles, 4 kN/m (20.55 kPa) was the critical value and the critical load the slope could bear reached 10 kN/m (51.38 kPa) after the installation of piles. The first row of piles withstood more load than the second row of piles, and double-row pile reinforcement can effectively improve the anti-slip safety reserve. In addition, monitoring of the deformation of the slope and anti-sliding piles should focus on the position of the sliding body and the slip face. Based on the results of laboratory tests, on-site field monitoring was then conducted on the target slope, including displacement monitoring at different positions on the slope before and after anti-slide pile construction, deformation monitoring of anti-slide piles, and rock stress monitoring around anti-slide piles. Monitoring results showed that the slope deformation and rock mass stress tended to be stable after anti-sliding pile construction, and the anti-slide piles were conducive to a safe state. The results of this study provide a useful reference for the reinforcement and monitoring of buckling failure in an actual slope.

Assessment of Rock Slope Stability along Sulaimaniyah -Qaradagh Main Road, Near Dararash Village, Sulaimaniyah, NE-Iraq

The road network in the Baranan mountain, near Dararash village, connecting Sulaymaniyah city with Qaradagh town, plays a major role in socio- economic activities of Qaradagh town and its surrounding villages. Any type of slope failure in the area may cause breaking up in traffic, loss of lives, and injuries.
 For assessing the stability of rock slopes in the area, seven stations (rock-cut slopes) were selected along the road and evaluated by kinematic analysis, using DIPS v6.008 software and slope mass rating system (SMRTool - v205 software).
 The kinematic analysis revealed that planar and wedge sliding may occur in stations no.2, 5, 6, and 7, flexural toppling may occur in station no.1, direct toppling may occur in station no.2, and oblique toppling may occur in station no.3.
 SMR- Tool software for discrete-SMR and continuous-SMR (CSMR) revealed that stations no.2, 5, 6 and 7 are unstable slopes (class IV of a bad slope type) with failure probability of 0.6, with an exception for station no.7 which is a partially stable slope (class III of a normal slope type) with failure probability of 0.4. Station no.1 is partially stable slope (class III of a normal slope type) with failure probability of 0.4 and station no.3 is stable slope (class II of a good slope type) with failure probability of 0.2.
 Due to the lack of structural and failure surface data (attitude of discontinuities and slumping surface) in station no.4, stability analysis was interpreted by using the general conventional method, depending on the field criterion and vision. The station can be interpreted as a rotational failure, the upper part of which consists of slump motion and the lower part of flow motion.

A two-dimensional limit equilibrium computer code for analysis of complex toppling slope failures

Evaluation of blocky or layered rock slopes against toppling failures has remained of great concern for engineers in various rock mechanics projects. Several step-by-step analytical solutions have been developed for analyzing these types of slope failures. However, manual application of these analytical solutions for real case studies can be time-consuming, complicated, and in certain cases even impossible. This study will first examine existing methods for toppling failure analyses that are reviewed, modified and generalized to consider the effects of a wide range of external and dead loads on slope stability. Next, based on the generalized presented formulae, a Windows form computer code is programmed using Visual C# for analysis of common types of toppling failures. Input parameters, including slope geometry, joint sets parameters, rock and soil properties, ground water level, dynamic loads, support anchor loads as well as magnitudes and forms of external forces, are first loaded into the code. The input data are then saved and used to graphically draw the slope model. This is followed by automatic identification of the toppling failure mode and a deterministic analysis of the slope stability against this failure mode. The results are presented using a graphical approach. The developed code allows probabilistic introduction of the input parameters via probability distribution functions (PDFs) and thus a probabilistic analysis of the toppling failure modes using Monte-Carlo simulation technique. This allows calculation of the probability of slope failure. Finally, several published case studies and typical examples are analyzed with the developed code. The outcomes are compared with those of the main references to assess the performance and robustness of the developed computer code. The comparisons demonstrate good agreement between the results.

Assessment of the physical vulnerability of buildings affected by slow-moving landslides

Abstract. Physical vulnerability is a challenging and fundamental issue in landslide risk assessment. Previous studies mostly focus on generalized vulnerability assessment from landslides or other types of slope failures, such as debris flow and rockfall, while the long-term damage induced by slow-moving landslides is usually ignored. In this study, a method was proposed to construct physical vulnerability curves for masonry buildings by taking the Manjiapo landslide as an example. The landslide's force acting on the buildings' foundation is calculated by applying the landslide residual-thrust calculation method. Considering four rainfall scenarios, the buildings' physical responses to the thrust are simulated in terms of potential inclination by using Timoshenko's deep-beam theory. By assuming the landslide safety factor to be landslide intensity and inclination ratio to be vulnerability, a physical vulnerability curve is fitted and the relative function is constructed by applying a Weibull distribution function. To investigate the effects of buildings' parameters that influence vulnerabilities, the length, width, height, and foundation depth and Young's modulus of the foundation are analysed. The validation results on the case building show that the physical vulnerability function can give a good result in accordance with the investigation in the field. The results demonstrate that the building length, width, and foundation depth are the three most critical factors that affect the physical vulnerability value. Also, the result shows that the higher the ratio of length to width of the building, the more serious the damage to the building. Similarly, the shallower the foundation depth is, the more serious the damage will be. We hope that the established physical vulnerability curves can serve as tools for the quantitative risk assessment of slow-moving landslides.

Paraglacial slope failures in the Aran valley (Central Pyrenees)

Slope failures are widespread phenomena in mid-latitude mountain environments that were glaciated during the Last Glacial Cycle. This is the case of the Aran valley, in the Upper Garonne catchment, Central Pyrenees, that included glaciers several hundred meters thick. Following postglacial warming and ice thinning, the recently deglaciated slopes were subject to intense stress readjustments - the so-called paraglacial dynamics. We have identified up to 135 major slope failures in the Aran valley, with only 10 units occurring outside the glaciated domain of the maximum ice extent of the Last Glacial. The presence of polished bedrock surfaces, till and moraine ridges next to some of these features evidence a close connection between glacial and slope processes. We have detected different types of slope failures affecting both bedrock (12 large catastrophic rock slope failures, 16 rock-slope deformation, 34 rockfalls, and 49 rockslides) and unconsolidated glacial sediments (14 slope readjustments on drift-mantled slopes). The average altitude of rock slope failures oscillates between 1551 and 1991 m, with a mean length ranging from 147 to 905 m and a width between 247 and 513 m. The affected surface is also highly variable, oscillating between 0.02 and 126.2 ha. Slope failures occur in different lithological settings, but they are most frequent in slate, lutite and limestone bedrocks. We conclude that most of the failures show a paraglacial origin, though other factors (i.e. lithology and topography) promoted slope instability.

A Preliminary Assessment of Rock Slope Stability in Tropical Climates: A Case Study at Lafarge Quarry, Perak, Malaysia

The stability analysis of rock slopes is a complex task for the geotechnical engineers due to the complex nature of the rock mass in a tropical climate that often has discontinuities in several forms, and consequently, in several types of slope failures. In this work, a rock mass classification scheme is followed in a tropical environment using the Rock Mass Rating (RMR) and Geological Strength Index (GSI) combined with the kinematic investigation using the Rocscience Software Dips 6.0. The Lafarge quarry is divided into ten windows. In the RMR system, the five parameters uniaxial compressive strength (UCS), rock quality designation (RQD), discontinuity spacing, discontinuity condition, and groundwater conditions are investigated. The RMR values range from 51 to 70 (fair to good rock mass), and the GSI values range from 62 to 65 (good to fair rock mass). There is a good and positive correlation between RMR and GSI. The kinematic analysis reveals that window A is prone to critical toppling, window H to critical wedge-planar failure, and window G to critical wedge failure. From the results obtained, it can be concluded that the kinematic analysis combined with the rock mass classification system provides a better understanding to analyze the rock slope stability in a tropical climate compared with considering the rock mass classification system individually.

Digital Surface Model-aided Quantitative Geologic Rockfall Rating System (QG-RRS)

ABSTRACTRockfalls are one of the most common types of slope failures that affect cut slopes along roadways in mountainous regions. The Rockfall Hazard Rating System (RHRS), started in Oregon and adopted by various U.S. states, is used to rate cut slopes with respect to their likelihood of releasing rockfalls. Existing rating systems use semi-quantitative approaches to rate geological and non-geological factors. The main geologic factors are favorability/unfavorability of orientation of discontinuities with respect to the orientation of slope faces and likelihood of differential weathering leading to undercutting of strong rock units. Digital surface models (DSMs) derived from light detection and ranging (LiDAR) and photogrammetry have been used to remotely characterize rock mass. This research introduces an expanded application of DSMs to quantify geologic factors that contribute to the likelihood of rockfall events. The method is hence referred to as the Quantitative Geologic Rockfall Rating System (QG-RRS). Four DSM-based parameters, A, B, C, and D, have been identified to evaluate geologic factors. These parameters quantify the likelihood of discontinuity orientation-controlled failures (parameter A), the degree of undercutting (parameter B), rockfall activity based on rockfall release surfaces (parameter C), and rockfall volume from rockfall voids (parameter D). This rating system, although not inclusive of other non-geological factors, appears to provide reproducible quantitative estimation of geologic factors that control rockfall generation.

Numerical analysis of slide-head-toppling failure

In layered and blocky rock slopes, toppling failure is a common mode of instability that may occur in mining engineering. If this type of slope failure occurs as a consequence of another type of failure, it is referred to as the secondary toppling failure. “Slide-head-toppling” is a type of secondary toppling failures, where the upper part of the slope is toppled as a consequence of a semi-circular sliding failure at the toe of the slope. In this research work, the slide-head-toppling failure is examined through a series of numerical modeling. Phase 2, as a software written based on the finite element method, is used in this work. Different types of slide-head-toppling failures including blocky, block-flexural, and flexural are simulated. A good agreement can be observed when the results of the numerical modeling are compared with those for the pre-existing physical modeling and analytical method.

Land Degeneration due to Water Infiltration and Sub-Erosion: A Case Study of Soil Slope Failure at the National Geological Park of Qian-an Mud Forest, China

Sustainable development of the natural landscape has received an increasing attention worldwide. Identifying the causes of land degradation is the primary condition for adopting appropriate methods to preserve degraded landscapes. The National Geological Park of Qian-an mud forest in China is facing widespread land degradation, which not only threatens landscape development but also endangers many households and farmlands. Using the park as a research object, we identified the types of slope failure and the factors that contribute to their occurrence. During June 2017, a detailed field survey conducted in a representative area of the studied region found two main types of slope failure: soil cave piping and vertical collapse. Physicochemical properties of the soil samples were measured in the laboratory. Results show that soil slope failure is controlled by three factors: (1) the typical geological structure of the mud forest area represented by an upper layer of thick loess sub-sandy soil and the near-vertical slope morphology; (2) particular soil properties, especially soil dispersibility; and (3) special climate conditions with distinct wet and dry seasons.

Engineering geological mapping of earthquake-induced landslides in South Lefkada Island, Greece: evaluation of the type and characteristics of the slope failures

A moderate, shallow depth, earthquake (Mw = 6.5) occurred onshore Lefkada island on November 17, 2015 with the focal depth estimated at 11 km. The seismic fault is a near-vertical strike-slip fault running along the western coast, part of the Cephalonia Transform Fault. Landslides and ground cracks were mainly reported at the western part of the island, inducing structural damages. High severity slope failures occurred at Egremnoi and Gialos areas that both are located at coastal regions. This study aims to investigate the engineering geological conditions at these areas, and assess the characteristics and physical quantities (e.g., type, area—m2, and volume—m3) of the instabilities. To achieve this, engineering geological mapping was implemented in Egremnoi and Gialos area aiming to; (a) classify the geological units mapped on the heavily damaged areas and (b) to correlate them with the type of slope failures. Furthermore, type and dimensions of slope failures were evaluated to estimate the total volume of the mass movement. All the data, originated from the engineering geological mapping, have been digitized and rasterized at 5 m grid spacing using the Arc/Info GIS software to perform a Newmark’s sliding block analysis. The outcome arisen by this analysis is that the generated by the earthquake peak ground acceleration at these areas should be at least 0.45 g to trigger these kinds of slope failures.

SPATIAL MODELING VARIOUS TYPES OF SLOPE FAILURE USING ARTIFICIAL NEURAL NETWORK (ANN) IN PULAU PINANG, MALAYSIA/PEMODELAN RUANGAN PELBAGAI JENIS KEGAGALAN CERUN MENGGUNAKAN RANGKAIAN SARAF BUATAN (ANN) DI PULAU PINANG, MALAYSIA

This paper discusses the modeling of various types of slope failure using the artificial neural network (ANN) in Penang. Slope failure areas identified by field trips. However, the existing models do not categorize the various types of slope failure, therefore the model to be developed will categorize a variety of types of slope failure has occurred The objective of the study is to model various types of slope failure using an artificial neural network (ANN). A total of 12 variables that influence the occurrence of slope failure is used to develop spatial model of slope failure. Among the factors are distant from slope failure to road, distant from slope failure to river, distant from slope failure to lineament, lithology, land use, soil series, average annual rainfall, slope aspect, slope steepness, topographic elevation (DEM), the curvature of the slope and vegetation index. The results of this study show a satisfactory performance in which the accuracy of the original model is 76.63%. The performance of the model is evaluated using independent data set of 20%, and the accuracy of 73.85%.