Slope Stability - Science topic

Yes, there are several databases available that provide images and data related to landslides and slope stability, often used for geotechnical analysis and image processing research. Here are some notable options:

1. Landslide Inventory Maps – The US Geological Survey (USGS) and the European Space Agency (ESA) provide comprehensive landslide inventories with georeferenced images, which are valuable for analyzing landslide occurrences and patterns.

2. Global Landslide Catalog (GLC) – Managed by NASA, this catalog contains landslide data with images and geolocations, primarily associated with rainfall-triggered landslides, but it also includes a variety of slope stability scenarios.

3. Japanese Landslide Inventory – Available through the National Research Institute for Earth Science and Disaster Resilience (NIED) in Japan, this database focuses on earthquake-triggered landslides and offers high-resolution images that are highly relevant for seismic studies.

4. SLID: Landslide Image Dataset – This dataset is curated for machine learning purposes and includes labeled images of landslides, making it suitable for image processing and classification tasks.

These databases are widely used in geotechnical research and offer credible, high-quality resources for data-driven analyses of slope stability and landslide risks.

Dear Doctor

Go To

"Q-slope is one of the most recent empirical geomechanical classification systems and the least studied in South America. This study aims to expand the knowledge base regarding the Q-slope geomechanical method and demonstrate its applicability and reliability in rock slopes of Andean countries, such as Ecuador. To this end, thirty rocky slopes have been characterized considering (1) the physical visual approach—geographic location, climate, lithology, alteration, and stability (to obtain values of Jr, Ja, Jwice, and SRFa)—and (2) geomechanical stations and kinematic analysis (for the determination of the type of failure, Jn, O-factor, and SRFc for Q-slope). Field data were collected in contrasting environments (coastal, mountain, and forest), and different failure modes were considered (planar, wedge, block, and flexural topplings) to better understand the method. The results and main contributions of this research are (i) verifying the applicability of the Jwice parameters in different climatic settings and (ii) validating the Q-slope method by applying a confusion matrix to evaluate its reliability for slope stability assessment. The overall accuracy obtained is 80%, placing the Q-slope geomechanical method in the highest evaluation quartile and thus classifying it as very good for slope characterization.

Rock mass classifications have been successfully used worldwide for rock slope characterization for multiple reasons: effectiveness due to their connection with empirical methods and dissemination and communication across scientists, engineers, and the general public. In other words, rock mass classifications “put numbers to geology” [35]. The Q-slope method was applied herein in three natural regions of Ecuador—coast, mountains, and jungle—where igneous, sedimentary, and metamorphic rocks exhibiting different weathering conditions were found.

The result of the stability analysis using the Q-slope method determined that of the 30 slopes analyzed, 25 are in unstable conditions, 1 is almost stable, and 4 slopes are in stable conditions. The results demonstrated that instability processes occur for slopes starting at 61 degrees of inclination and 6 m high.

One of the main modifications implemented in the Q-method for its application to slopes is the shear strength, which, in our specific case, is obtained by multiplying the Jr/Ja ratio by the new O-factor. Nevertheless, when slopes that present toppling failures are studied, the method does not clearly establish the values to be considered for the O-factor (differently from the cases of planar and wedge failures). Therefore, future investigation is advisable to determine the O-factor values rigorously and accurately, especially for the toppling cases. The parameter could depend on the difference in strikes and dips between slope and joints, following the determination of the F1, F2, and F3 factors of the SMR correction.

Considering the values obtained and the metrics calculated for each class of statistical case a, it can be concluded that as sub-class 1 presents high values for precision and recall, the method can perfectly classify this sub-class. For sub-class 2, a high precision value is obtained with a low recall value; in this case, the method does not classify this class very well—however, when it does, it is highly reliable. For sub-class 3, the model provides a low precision value and a high recall value, which suggests that the method classifies the sub-class well but can also confuse the individuals of other sub-classes. The F1 score values obtained for each sub-class in the different statistical cases analyzed present values that range from 0.62 to 1, indicating that the Q-slope method is a balanced method that can confuse some cases as false but is also capable of correctly classifying all positive true cases, such as those of sub-class 1 of statistical case a. Only sub-class 2 of statistical case a returned an F1 score value of 0.25, which means that the model can confuse values as false for this specific case. Sub-classes 2 for statistical cases b and c present null values because the calculated FoS is a fixed value that only defines if the slope is stable or unstable. In these cases, a direct association could not be made between the quasi-stability obtained in situ and that predicted by the empirical method and FoS.

In general, considering that overall accuracy can be divided into quartiles, classifying quartile C1 as bad, C2 as intermediate, C3 as good, and C4 as very good, the value obtained for OA herein occupies the highest quartile, ranking the method as very good."

That is a very general question. any geotechnical book has the basic principles. Check, Soil Strength and Slope Stability book by J. Michael Duncan, Stephen G. Wright Thomas L. Brandon.

Thanks, it really helps.

There is some data on 1-2 m deep, rainfall-induced landslides, on soil-mantled slopes, in this paper: https://www.sciencedirect.com/science/article/abs/pii/S0169555X1930251X

Road safety, car safety and factors influencing the reduction of road accidents

Hi Amir,

I checked your input file and it seems that you are using MC material def. for your soil. So, my guess was that the strain concentration is caused by discontinuity in the material behavior. Your soil block is pulling the infinite region and since it is less deformable, you get the stress concentration and plasticity in the interface region. But I tried to run your input file and in fact, the plasticity already occurred during the static step.

So, there are 2 concerns here from my pov:

1. The way you create the model. First, there is no infinite elements in the bottom of the soil. I understand what you are trying to simulate but by modelling it this way, you have no representation of the static and dynamic behavior in the vertical direction.

2. The geostatic state is missing. As you know, the soil behavior is governed by its confining stress. And it is paramount in nonlinear soil simulation. In your static step, you apply the gravity loading to the soil but there is no predefined stress in the soil. This yields incorrect nonlinear behavior because the soil strength is underestimated. Any deformation beyond this point would be considered invalid. If you are unfamiliar with this, please check the abaqus manual regarding geostatic step.

So, for your model, I recommend to apply the infinite elements surrounding the main study area. You can imagine the interface to be like a half-ellipsoid. The interface here is the line between regular and infinite elements.

And then apply the correct geostatic step. I know it can be a challenge to implement a geostatic step on a model with irregular surface. How I usually solve it is by having a preliminary geostatic computation. In this preliminary model, I apply the geostatic computation while applying fixed boundary condition to all soil (finite) region and record the reaction forces. These reactions are then used as input in the true geostatic step in the main model to stabilize the result. I don't know whether you want to go this far, so I'll stop with the details.

Cheers and good luck with the model.

High-speed landslides can generate air waves, which are also known as air blasts, due to the rapid movement of the landslide mass. The mechanical mechanism behind the generation of air waves by high-speed landslides is complex and involves several factors.

One of the primary factors is the sudden release of energy that occurs during the landslide. As the landslide mass moves downhill, it displaces a large volume of air in front of it. This displaced air creates a high-pressure zone, which propagates outward from the landslide as a shock wave or air blast.

Another factor that contributes to the generation of air waves by high-speed landslides is the fragmentation of the landslide mass. As the mass moves downslope, it can break apart into smaller pieces due to the forces acting on it. This fragmentation creates additional air pockets that are rapidly compressed and decompressed as the landslide moves, generating additional air waves.

The speed and size of the landslide also play a role in the generation of air waves. Larger and faster-moving landslides can generate more powerful air waves than smaller or slower-moving landslides.

Overall, the mechanical mechanism of air wave generation by high-speed landslides is complex and depends on several factors. However, the primary mechanism involves the rapid displacement of air by the landslide mass, which creates high-pressure zones that propagate outward as shock waves or air blasts.

It is true that some ML use statistical techniques for learning, but the statistical approaches that I mentioned comprise much simpler calculations for specifying weights to the sub-classes of landslide conditioning factors. For instance frequency ratio uses a simple division. You can refer to some of my works to see details.

Dear Followers of the Question,

I asked my question to ChatGPT. Here is the answer:

To calculate the intersection angle between two joint sets using dip and dip direction data, we can use the following formula:

cos(θ) = cos(α1)*cos(α2) + sin(α1)*sin(α2)*cos(δ1-δ2)

where:

- θ is the intersection angle between the two joint sets

- α1 and α2 are the dips of the two joint sets

- δ1 and δ2 are the dip directions of the two joint sets

Once we have calculated the value of cos(θ), we can use the inverse cosine function (usually denoted as cos^-1 or acos) to obtain the value of θ.

Note that dip direction data is typically given in degrees clockwise from north, so we may need to convert this to azimuth (degrees clockwise from east) before using the formula. This can be done using the following formula:

azimuth = (450 - δ) mod 360

where:

- δ is the dip direction in degrees clockwise from north

- the "mod 360" ensures that the value of azimuth is always between 0 and 360 degrees.

A high-speed remote landslide, also known as a "rock avalanche", can be triggered by a number of mechanisms, including earthquakes, heavy rainfall, snowmelt, and human activities such as mining and construction. These triggers can cause instability in the slope, leading to the failure of rocks and soil to slide down the slope at high speeds. The exact triggering mechanism can vary depending on the specific slope and conditions, and it is an active area of research in geology and engineering.

Lightweight soil roadbeds, like those made of organic matter, coal ash, slag, etc. tend to deform and fail over time under repeated traffic loads through several mechanisms:

To prevent excessive deformation and failure of lightweight roadbeds, techniques include: using reinforcing geosynthetics, limiting heavy loads, increasing thickness, improving moisture management, using cement or lime stabilization, and vegetation cover on slopes and shoulders. Periodic maintenance and regrading also help extend the service life.

Does this help explain the key mechanisms by which lightweight soil roadbeds deform and fail over time under repeated traffic loading? Let me know if you have any other questions!

Geostudio, Abaqus, FLAC, Plaxis, and so on. It's not difficult to learn how to use these software. But, how to choose the hydrological and mechanical parameters of slope materials in the numerical model is a key point.

1. Im not sure if its logical, but as it is doesnt effect the stability slope much. If you predict it higher and repeat calculation, you could get much different results (less stable slope). So if you dont have any data and you want to play it safe, take into account higher level of water.

Questions 2 and 3 were already answered by others.

Dear Thanks for the referred paper.

Regards,

Raj

Dear Klaus,

Hynes-Griffin & Franklin approach (kh=0.50 PGA) is a very common and well-known approach for numerical analysis. I can say that considering kv will not cause any significant difference in results.

However, considering topographical state of the section may help you to come up with a precise solution. NCHRP advices a factor called as "fill-height dependent reduction factor" for the determination of the proper kh value. The soil class of the area is also critical for this approach. Maybe you can check this solution for your analysis. See attached file: Section 7.5 for more detailed information.

Dear Tariq,

These articles might help:

Bests,

It sent By accident: https://www.fs.fed.us/rm/pubs_other/wo_em7170_13/wo_em7170_13_vol1.pdf

Dear Salome,

There are several in-situ tests can be used like in-situ direct-shear test and gallery direct-shear test.

Bests,

Dear Sangam,

you can focus on reinforced soil behavior during the failure or smart instrumentation can be interesting for soil nailing.

Best regards,

Dear Kandi sandeep Reddy

Set some topics that you interested

Read some new papers on the subject

Find a theoretical basis about the subject

Look for some aspects that you can make a difference

Don't limit yourself to special subjects

Try to find a subject related to new ideas ( Smart Mine, Robots and drones in mining, Sustainability and environmentalism, deep-sea mining)

Also, this paper will be useful:

GEO5 and/or FLAC3D can be used. Other reliable software can also be used, it depends only on the level of accuracy that you want to expect. Machine Learning Techniques, Analytical and Empirical methods can be taken into account. It is suggested to select and try two methods in order to compare results and get high precision, as rock density on slope stability is a hot topic.

Dear Kuldeep,

Nice to hear about your research work..your question is what type of triaxial test is to be conducted for soil samples collected from landslide. It is simple understanding that if you need to verify the short term stability of slope than you need to conduct CU test or if you want to verify the long term stability slope than use CD test results. As you know CU test is quick as compared to CD test..so depending upon your design requirements you have to use either CU or CD test..ok all the best..

Hi dear Kuldeep Dutta

Check out the following software:

This is a good question.

Check the stress level you used in RockLab. If the confining stresses in RockLab in the region of interest are different from the stresses in your Plaxis model, the distance from linear M-C shear strength envelope to curved H&B shear strength envelope may be significant, affecting plastification.

Dear Sohaib,

Probably this video would be helpful to some extent.

Watch "How to model the soil slope using Plaxis 2D" on YouTube

Sorry for being late to this discussion.

There are many thresholds for the forecasting of landslides and you can find a comprehensive overview here: http://rainfallthresholds.irpi.cnr.it/

Correct, the demo permits the cycling of a maximum of 1,000 balls or 1,000 clumps (not exceeding a total of 1,000 balls) and up to 10 discrete fractures. However, you would get a warning message if you exceed this; the program should not crash because of demo limits.

Otherwise, the only technical limit is the amount of RAM in your computer. You should be able to readily create and work with models with 100,000's or even a few million particles. Please contact Itasca's Technical Support team via https://www.itascacg.com/contact-itasca/sw-tech-support-pfc2d and they will be able to help you.

There are several reasons;

1. Your structure is highly stable.

2. You have assigned over estimated parameters.

Please revise your parameters, else provide the file for revision.

Hi Friend

You must get good parameters in input analysis.

After that you can use FLAc 2D and 3d.

Hi Tharshikka,

You just need to select a surface and apply the infiltration boundary condition to it. About the suction, you can select an option in the Project setting to put a cut off for the suction. Please email me if you have further questions: sina.javankhoshdel@rocscience.co, I will be happy to help.

Cheers,

Thank you very much for help..

I hope i can solve the problem and let you know the reason and solution.

Best regards

Dragi Vikram,

Za podatke o vodonosnicima i litoloških karakteristika - opšte stanje na tlu, možete naći na Googlu i predlog gospodina Abdelrazek Elnashar, koji predlaže sledeće izvore na programu Google Earth Engine, Podaci o tlu: https://developers.google.com/s/results/earth-engine/datasets?q=OpenLandMap; LULC: https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_Landcover_100m_Proba-V-C3_Global

Takođe je dobra i https://bhuvan-app1.nrsc.gov.in/thematic/thematic/index.php

Ima dosta podataka o eroziji tla i u mojoj knjizi (Geološki procesi u Zemljinoj kori i na površini - Academia.edu) ali i drugih autora. Na Vama je to malo proučiti i inkorporirati i prilagoditi sa u Vašim problemom in situ!

Srdačan pozdrav!

Reading this review article may help you a lot:

inclinometer data should be used very carefully. The field accuracy of the data is about 8 mm per 30 m of the casing.

And systematic errors are very limiting in its use unless you are familiar with the errors and how to correct them.

Most failures in rocks are due to shear failure, both in static and dynamic stess.

Go for PLAXIS and ABAQUS.

geo studio is the best way to model a slope

Geotechnical enginnering is iportant area of research

Hello, Andesta Irwan

You can go through the tutorial manuals available online to understand the basic concepts behind 3DEC distinct element modelling.

As requested: to define a basic slope model, you can follow the basic input code with a short write up for each command.

poly brick 0 20 0 1 0 12

plot create plot Blocks

plot block

plot reset

jset dip 0 dd 180 or 0 0 2

hide range plane dip 0 dd 180 or 0 0 2 below

jset dip 45 dd 270 or 12 0 12

hide range plane dip 45 dd 270 or 12 0 12 below

del

seek

jset dip 60 dd 90 or 14 0 12 spac 3.6 num 10

jset dip 20 dd 270 or 20 0 12 spac 2.2 num 10

gen edge .7

change cons 2

prop mat 1 dens 2000.0

prop mat 1 bulk 1.0e8 shear 3.0e7 bcohesion 1e20

prop mat 1 bfriction 20.0 bdilation 20.0 btens 1e10

prop jmat 1 jkn 1e10 jks 1e9 jfric 30 jcoh 1e20

gravity 0,0 -10.0

boun zvel 0 range z 0

boun xvel 0 range z 0

boun xvel 0 range x 20

boun xvel 0 range x 0

boun yvel 0 range y 0

boun yvel 0 range y 1

damp auto

Solve

plot clear

plot contour velocity

plot add velocity

plot reset

prop jmat 1 jcoh 1e4

prop mat 1 bcoh 12380.0

solve fos associated

ret

Nowadays, the most important advances in the LEM world is the search methods to find the most critical slip surface used together with the LEM approaches. These methods are Metahueristic methods such as Cuckoo Search, Particle Swarm, Simulated annealing from other fields brought to the geotechnical applications. The value of the LEM methods to be combined with the new search methods becomes more important (these are all non-circular methods). Our studies showed that, for complicated models, simplified Bishop method cannot give good results. Janbu method gives the lower-bound for the factor of safety. The best methods that give similar answer to even FEM analysis are Spencer and Morgenstern Price methods. I hope that helps.

Mr.Muneeb,

I feel the main important one in all over the world is population increase and no space available for developing infrastructure relative to increase in population. so the construction activities have taken place as closer to an existing structure. In view of this, the stability analysis of existing structure adjacent to new construction in terms of excavation, embankment, tunneling or pile driving is a serious problem. As a geotechnical engineer we need to come out with design idea to protect the existing structure due to the effect of new construction.

Another important issue is we don't have excellent supporting ground for the new construction. So, in this case we need to develop economical ground improvement technique to support the load. Ground improvement technique alternate to conventional method is catching up among researcher . ok all the best in your research..

In the case of protecting with Riprap, you must take care to place layers of sand and gravel filter in the contact between the marl and the bedrock, to avoid washing and dissolution, reduce the hydraulic gradient of the possible filtration flow and separate the surface runoff.

Mr.Koushik,

Slope stability analysis in PLAXIS software can be performed by varying the ground water level with respect to time and study the response due to change in ground water level. This depicts the water level before and after rainfall. If you want to simulate debris flow in analysis, first you need to select the region that would fall after rainfall..this can be simulated by applying displacement as boundary conditions and study the response due to change in displacements within the selected region. i suggest you to read PLAXIS manual and collect literature related to your study is available. Find attached the paper related to the work for your reference. all the best in your research..

If you still didnt get response then my answer is applicable.

1. Try to look for velocity spectrum in Kangra Earthquake papers. Even if papers dont share data, get the figures.

2. Extract data from figures.

3. Use this load under dynamic load conditions...

4. Select time query points.

5. Run the analysis.

Thanks for your useful information William F. Hansen . Actually, I need an idea. If you use these values ( C, Phi of C. C. Block) in any one of your research work, then, let me know.

Dear Dr. Maysam,

I think that the probabilistic and sensitivity analysis may be enough. But, for intensive results and comparisons, you have to consider the statistical analysis. The choice may depend on the nature of your application and research work.

Good Luck!

Thank you Mr Moataz.

I would like to know the steps for finding it using Factor of safety. Can you please tell me how it is?

Go to

for a free finite element slope stability program

FLAC can be operated in command-driven or graphical, menu-driven mode. Command lines must be entered as input to FLAC, either interactively via the keyboard or from a remote data file, in order for the code to operate. There are over 40 main commands and nearly 400 command modifiers (called keywords) which are recognized by FLAC. The menu-driven mode is an easy-to-use alternative to the command-driven procedure. All of the commands in FLAC can be accessed by point-and-click operation from the graphical mode. We call this mode the “GIIC” for Graphical Interface for Itasca Codes; eventually, the GIIC will operate with all Itasca software.

Having done a good deal of this kind of work, it is important to understand that this is more than just technical exercise. It is important to understand the standard of care and local practices by which the performance is judged. The American Consulting Engineers Council has an excellent publication on this topic: https://docs.acec.org/pub/18803059-a2fd-2d06-cc39-a6d1dd575265.

It is also important to understand the roles of all parties to the case. Failures are seldom the result of a single error or oversight, but often are the result of a perfect storm of factors involving multiple parties from the initial investigation, design assumptions, owner inputs, contracting limitations, information sharing, construction practices, etc.

There are many companies around the world flying different Lidar scanners for different purposes and they only exist because indeed someone is prepared to pay good money for the data. Many of those are multi-million dollar aerial systems in aircraft or helicopter, i think you are looking at UAV based solution though.

To attempt any freelance work with the Lidar unit you mentioned would be a waste of time however, the data precision and accuracy would not be considered good enough for the majority of end users.

A much higher level unit such as the Riegl Mini-VUX or the VUX-1UAV would operate well in that environment and with an appropriate IMU and GNSS/RTK system produce survey grade results of some value to an end user.

If you have elevation data, its possible with Arc GIS . This is one of YouTube tutorial that I found.

https://www.youtube.com/watch?v=2lnT9HJzt1c

Best regards

Ahmad -

This is a pretty complex type of analysis. Unfortunately, I can't seem to find your attached files. There are many different pitfalls that can occur when attempting this, however, the rezoning function that FLAC uses should automatically account for a non-horizontal phreatic surface, I have had success with this type of problem. It is possible that your error is due to something external to the internal rezone function that FLAC applies, meaning, it could be a user-defined variable (or something similar) that is being used that is the problem.

Idealizing the earthquake forces by static forces is an approximate approach and is applicable only when there is one dominant mode shape of the structure.

Dear Ridz Aqil

Relating to your work, i think the following paper can help you:

Chai and Bergado 1993 "Performance of reinforced embankment on Muar clay Deposit" Soil and Foundation 33(4) 1-17.

This case is in Malaysian soil

good luck

Hi,

There are MPM codes with different perspectives. For geotechnical analysis, in my opinion these are the main available codes:

Regards,

Fabricio

Hi, there are pro and cons for each software.

Slope/w is widely used tool due to easiness and less cost. This program is developed based on Limit Equilibrium methods. The limit equilibrium method of slices is based purely on the principle of statics; that is, the summation of moments, vertical forces, and horizontal forces. The method says nothing about strains and displacements, and as a result it does not satisfy displacement compatibility. Due to this, we don't know the deformation of stable and unstable slope.

FLAC is finite difference method and needs a lot of time to generate model, meshing and assiging suitable constitutive model and to run. In FLAC you can write the program as per your /client requirement. It is more versatile and much costlier than Slope/w.

There are many models available. Voellmy fluid friction model is used in RAMMS developed by Switzerland authorities. There are some models developed by United States Geological Survey for Debris flow modelling. Also, there are various numerical models developed by Iverson, Ohungr, Pudasaini.

In Apennine area (Italy) DSGSDs are located in mesozoic limestones which constitute the core of anticlinalc ridges.

I don't think that it has anything to do with natural slopes versus open pit slopes. In the case of natural slopes, some natural slopes are teetering on the edge of failure and thus susceptible to being triggered by even the smallest earthquake (acknowledging that some natural slope fail with no earthquake at all). Other natural slopes are so thoroughly stable that they will not fail in even the most severe earthquake.

In the case of open pit mines and other cut slopes, the slopes are designed to some degree of stability (depending on the skill of the designer and the accuracy of the material properties). In some cases, the design objective is to just get the slope to stand up long enough for a short-term purpose, judging that the probability of an earthquake occurring in this short period of exposure is acceptably small. One example might be the slope created during the construction of a retaining wall that will ultimately be holding the slope. In the past some were willing to take greater risks in this way than may be common in the present. In other cases the objective is to assure safety under all foreseeable circumstances, including an earthquake, and long into the future. In the latter cases, the actual performance of the slope is again dependent on the skill of the designer and the accuracy of the material properties. An example of this might be the wall of a pit away from which excavation activity is working.

We design human-made slopes to varying levels of stability while nature creates slopes of varying levels of stability.

You may try Optum packages like Optum G2. It is a completely user-friend and free to access. It also provides many equipment for a geotechnical problem as well as continuous run process.

Thank you for your interest Samuel J. Abbey , Which constitutive model do you recommend?

You have to check the manuals of the calculation programs if the model you need is available. Many software mentioned in the answers above include the "cam-clay" (0). Is that what you need? Do you have the data necessary for the implementation? Or do you want to apply a 'mohr-coulomb' with resistance/stiffness degradation? and in this case, the reduction must be immediate (1) or with progressive reduction as a function of shear deformation (2), or (being next to the residual parameters) is sufficient the degradability of the deformability module (G / Go) (3)?

In my experience (I dont' use geostudio), the answers are:

(0) almost of all sw

(1) flac, Phase2/RS2

(2) flac,

(3) flac, Plaxis, RS2

Take a look on constitutive models available:

Look first what you have in the university (maybe in the university you have Abaqus and someone who can give you assistance in using it), and then choose.

I recommend the ITASCA software such as (UDEC, PFC, 3DEC). They are designed specifically to anaylze the behavior of discontinuous media such as rock masses Bekir Salih Firincioglu

Dear Mirjana Vukicevic, perhaps we refer to different quantities. The plasticity index, intended as the difference between the liquid limit and the plastic limit, is an intrinsic soil property (index property), and as such it does not depend on water content. What you are referring to, I suppose, is the "soil consistency" (or "consistency index", CI), which depends on how the current water content relates with the plastic and liquid limits (e.g. CI > 1 if w < wP, CI = 1 if w = wP, CI < 1 if w > wP, CI = 0 if w = wL). Similarly, the "liquidity index", LI, can be defined (e.g. LI=1 if w=wL, LI=0 if w=wP).

However, in my understanding, Kobid Panthi means that there is a change in index properties, not (just) a change in state variables.

Numerical methods are techniques to approximate the governing equations in the mathematical models. Common numerical methods include finite element method, spectral method, finite difference method, and finite volume method.

Dear Bakir,

You have distinct weathering zones in your bench slope. So, you can define these zones in your model as a starting point. You can use GSI for estimating material properties of these zones. Since you do not have any defined joint sets, as you said, you can apply RS2 or RS3, both are FEM analysis program. Your slope dimension seems greather than REV size of your rock mass. Therefore, you can model your slope using continuum approach. Your bench slope is more prone to circular or non-circular failure mechanisms rather than discontunity controlled slip failures, such as plane, wedge or toppling.

I don't think using a probabilistic approach is the right thing to do. The most dangerous and statistically processed direction of cracks is not the same. The safety factor is very sensitive to the orientation of the cracks and changing the orientation by 5-10 degrees can change the safety factor several times. Enough odnogo adverse combination that basically the ledge collapsed. The analysis of field measurements of cracks and the choice of the most critical combinations is necessary. Also, it is possible to analyze already accomplished collapses (on what systems of cracks they occurred).

I had a communication with Dr. Duncan C Wyllie regarding this question and got very convincing explanation. Hereby, I am sharing the communication in the attached document.