Loading
O17-2020: Team A- Landslide Prediction

O17-2020: Team A- Landslide Prediction

by ashish dsaharia998 pen_flex | updated April 14, 2020
based on O17-2020: Team XX

Landslides are a damaging natural hazard because of their difficulty in forecasting, and fast onset that limits emergency responses. We aim to model a spatial variable that helps in predicting the chances of occurrence of such an event. We also propose to develop a multi-platform application aimed to crowdsource the process of data accumulation of any such event and update our model based on the procured data.

0

Challenge 2- Landslide Prediction

Project Description:

Landslides are a damaging natural hazard because of their difficulty in forecasting, and fast onset that limits emergency responses. We propose to declare a new variable - 'cascade' as a probabilistic parameter of landslide occurrence. We will train the model on data procured from NDMA of India, local newspapers and television reports. We will develop a multi-platform application to collect landslide reports from users with all the relevant geographical information. The data will be modelled using AI techniques such as Deep Neural Networks, Expectation Maximisation, and Maximum Likelihood Estimation. Input variables will consist of a large number of geomorphological and climatological parameters such as soil type, precipitation, slope, topographic curvature, distance from drainage, lithology, which will then be used to extend and regionalise the 'cascade' variable to a high-resolution grid covering India. The 'cascade' variable will help in forecasting future landslide occurrence depending on precipitation levels over a certain grid.

Team Introduction:

We are a team of motivated junior undergrads and are looking to make use of what knowledge we have for deriving solutions to itching and persistent problems to make the world a better and safer place.

March 30, 2020 at 5:02 PM
Created by amudha
Edited by ashish and pen_flex
Comments (2)
Cool project! The problem definition is clearly defined and well explained (why landslides are difficult to predict and respond to, and their negative impacts). If you can talk a bit about why your project is unique (are there any other projects around the world that are trying to solve the same problem?), that would improve your project.

Make sure you fill out all of the material under "Week I".
3 months ago
Super cool project!
About the scope though, would another territorial cut be more interesting than India? Maybe a smaller area, or maybe a very large hydrographic basin? Maybe a mountain range and all its "sides"?
Consider the quantity, quality and consistency of data that you need, and the partnerships you may want to form with authorities or citizens.
3 months ago

Please sign in to leave comments

Describe what is the need of this project?

Landslides are on the rise around the world and India is among the most-affected countries, accounting for at least 28% of such events over the last 12 years. Most of which occurs due to heavy rainfall.

Since we plan to cover a very large area to model and train our dataset over, the rainfall data over the entire region may not be readily available and we might need to fill in or extrapolate the missing gaps using a predictive model.

Collecting data (with complete parameters) of the landslide region- crowdsourcing might be challenging as people might not acknowledge all the geomorphological parameters involved while reporting such an incident.

March 30, 2020 at 4:53 PM
Created by amudha
Edited by pen_flex
Comments (3)
Can you consider a proxy problem that could make it easier for people to contribute to your project? Sometimes sophisticated knowledge is necessary to answer one question, but the answer to a simpler second one will give you a pretty good idea of the answer to the first.
3 months ago
crowdsourced need not always be field data. it could be crowd validation as well. Identifying 'what data' can easily be crowdsourced, then deciding who the crowd is and then later how could that be done. you could work with a group of researchers or geologists as well. A crowd could be used equally to validate not just report. The kind of data determines the type and method of crowdsourcing.
3 months ago
Crowdsourcing point by Amudha is well taken. ‘Crowd’ will be the local people residing at the chosen location. The following options will be available to a user to report data on our app:
1. Validate a past landslide event at a particular place- User will upload the photographs along with his exact location coordinates.
2. Report a real time event- User will upload photographs, with close up on the soil, along with his exact location coordinates.
3. Report a nearby event that may induce a landslide- User will describe a nearby event such as unusual loosening of soil in a sloped terrain etc. along with photographs and location.
* There will be a ‘further information’ section where the user can report some extra information such as soil type if he has the knowledge to identify, any poor construction practices taking place in the region etc.
3 months ago

Please sign in to leave comments

Describe who is affected?

The primary stakeholders that hold our main focus are the people living in areas where such landslide incidents take place, as they are the ones who suffer the damage of property and many times, their lives. We can use this point to further educate and incentive the people of this region to contribute to our application platform, any such event witnessed in the region.

The other stakeholder would be the local governing body, as with a predictive model for such events, they could deploy their resources or needs as per the requirements and execute their strategies accordingly. And if successful, we can incentive them to use the Government framework to carry out the task of reporting the incidents on our application to further strengthen the model.

 

March 30, 2020 at 4:53 PM
Created by amudha
Edited by pen_flex and ashish
Comments (2)
What kind of information did you have in mind here, when stating that the gvt can do the reporting in your app? Why would the gvt be more trustworthy than the citizens, or regarding which queries? Would you collect both to have all the relevant info you could?
3 months ago
While stating that the government can do the reporting, we mean that the government officials including expert geologists, appointed by the government, can report with the geological parameters of that particular region which can be then verified with our existing data. This will in turn enhance our prediction model accuracy.
Data reported on the app will be cross validated with more than one source so as to mark a reliable data point. These sources will include local newspapers, television reports, consulting with geotechnical engineers, crowdsourced public data.
We will collect data from all the available sources and cross validate it accordingly.
3 months ago

Please sign in to leave comments

What are the causes?

I believe the major causes of landslide occurrence are as follows:

Sloped terrains contribute to a major part of rural India and because of this reason, proper slope stability testing is not performed before the construction of houses there. This increases burden on the soil and it becomes more prone to shear failure. Without proper engineering practices, damage on the soil increases and ultimately landslide occurs with even a little rainfall.

Sometimes over excavation at sites weaken the soil above it leading to a greater shear force on the terrain. Proper excavation techniques must be practised, along with the presence of a geo-technical consultant.
When heavy rainfall occurs, soil porosity increases which decreases the shear strength, ultimately leading to shear failure. Hence, it is of utmost importance to forecast heavy rainfall and estimate the shear capacity of the terrain.

March 30, 2020 at 4:53 PM
Created by amudha
Edited by ashish
Comments (4)
Could you use satellite images and aggregate income data for specific areas to hypothesize if the constructions on particular slopes exist and are poorly executed and maintained? Could this help you predict landslides?
3 months ago
Considering this, could the ultimate goal of avoiding tragic and damaging landslides have more to do with urban planning than climate, in certain cities? How would this affect your project? Could your AI tool or model distinguish if the landslides may be averted by a local government?
3 months ago
Have you looked at the landslide zonation map of the locality you are thinking of? There are Hill Area Development Plans and the authorities are to ensure whether the construction are to be allowed and what kind of construction in the landslide-prone regions. (ideally). Also if possible gather the data on the type of landslide, that would determine the cause.
3 months ago
Analysing satellite images to hypothesize the poor construction on slopes would be very difficult as the satellite images will not give us enough information on the “poor construction practices” on a certain sloped terrain. Urban planning will play a major role in our project, to address this we will include another option in our application in which users can report poor construction practices site as well, this will help us to model our approach in a realistic manner rather than using ideal assumptions. After looking at the landslide prone areas, we have decided to work on north-eastern Himalayan region of India.
3 months ago

Please sign in to leave comments

What is the evidence? Also who can you interview? What can you find out? What experiment can you run?

 

I believe this because in the recent years, India had been worst hit by the Kedarnath landslide which took place in 2013 in Uttarakhand state. It was caused by floods in the region due to constant heavy rainfall. This incident alone nearly took lives of about 5000 people. It gives enough motivation to devise a system that can predict landslides some time before their arrival with high accuracy.


A lot of information can be extracted by interviewing the geotechnical engineers who must have performed a detailed analysis of the region post landslide. This will help us to identify the importance of geological parameters and how they govern a landslide.

To dive deeper in understanding why landslide would have occurred, we can take the soil sample of that site and perform various tests such as shear strength test, test to measure porosity, etc. This will give us enough information to conclude the relevant parameters due to which landslide had occurred or landslide occurs.

March 30, 2020 at 4:53 PM
Created by amudha
Edited by ashish
Comments (0)

Please sign in to leave comments

Start documenting your thoughts and ideas

March 30, 2020 at 4:53 PM
Created by amudha
Comments (1)
You have stated a few facts and figures, so it's important to add references.
3 months ago

Please sign in to leave comments

What is The Big Idea? What is the value proposition?

In the past, there have been several studies which mapped the region with a degree of landslide susceptibility. The following research paper uses a heuristic approach to model the susceptibility of landslides:

Stanley, T., and D. B. Kirschbaum (2017), A heuristic approach to global landslide susceptibility mapping, Nat. Hazards, 1–20, doi:10.1007/s11069-017-2757-y

Our idea is to combine similar study along with AI and crowdsourcing techniques. We aim to collect regional data from citizens though an application and also from local government bodies which have previously worked in the region for infrastructural projects. We will use AI tools to map the landslide susceptibility all over India.

Another sub-problem can be to forecast rainfall over a region(instead of relying on Indian Meteorological Department) and then predict landslide with that data.

March 30, 2020 at 4:53 PM
Created by amudha
Edited by ashish
Comments (3)
It's great you did your homework.
For the Theory of Change exercise, we would like you to think about what needs to happen for your idea to work. What are the stages that you need to go through or that are beyond you?
(Is prediction the whole story? What's the before, during, and after? What else needs to happen for the ultimate goal to occur?)
3 months ago
What regional data do you plan to collect from the citizen and and what application? Is this application part of your output? Why do you want to map the landslide susceptibility for whole of India again? what added value can you provide to the existing maps or data? have you had a chance to look at the existing Zonation of the considered area? have you got data on the type of landslides that had occurred in the past ? The cause is determined by identifying the type of landslide( even within rainfall induced landslides).
3 months ago
For our idea to work, the following stages we need to go through:
1. The first stage is to collect existing landslide data. We have obtained the NASA landslide data over North-Eastern Himalayan region of India (not taking the whole India) and filtered out rain induced landslides. These include landslides caused by downpour, floods etc.
2. Next stage will be to consult expert geologists who can highlight the relevant factors due to which a landslide may occur. We will gather information on each of these factors of each data point we have in our existing data set through news reports, govt. Agencies, expert geologists etc.
3. A multi platform application will be made as described before, this app will enable us to collect all the information which will be required in predicting future landslides.
4. We will then use AI tools to produce a landslide susceptibility grid over the mentioned region. As soon as the rainfall reaches a threshold value as per a particular grid, citizens will be alerted over that region.

We have procured the data set from NASA website and after looking at the severity of landslides in North-Eastern Himalayan region, we have chosen to proceed with this region regarding this project.
3 months ago

Please sign in to leave comments

What is the mechanism of beneficial change?

Our approach will use the past landslide and rainfall data from news reports, government bodies and real time crowdsourced data through an app. We will then train our model with the data and predict landslide occurrence using soil and terrain parameters and forecasted rainfall as input parameters to get a reliable prediction.

We believe that our approach will have an impact because we will collect all the landslide governing parameters for a region either through crowdsourcing or news reports. In the past, individual studies have been conducted like mapping landslide susceptibility region, filtering of parameters that cause landslide in a region, but here we aim to combine these studies and produce a common model with which we will be able to quantify the haphazardness of landslide going to occur in a region with some amount of forecasted rainfall. 

March 30, 2020 at 4:53 PM
Created by amudha
Edited by ashish
Comments (2)
So what will the impact be?
3 months ago
so your crowdsourced reporting will be a validator to the existing reports? or an attribute overlay, that will fill the missing gaps in the susceptibility mapping?
3 months ago

Please sign in to leave comments

What are the key metrics?

In our model, we propose to distribute our area of focus into small unit grids. Then we plan to assign each grid with 2 values.

For the first value, we propose to coin a new variable - 'cascade', from scratch. This value would take into account various geomorphological and climatological parameters such as soil type, slope, topographic curvature, distance from drainage and lithology. And by determining the weighted influence of each of these individual parameters, we would assign a normalized (on a scale of 0.0-1.0) value to each of the grids. Note that the 'cascade' value would remain the same if we assume no major changes in the geomorphological characteristics of the area being analysed, which seems a valid assumption.

As for the second value, we would club grids having a similar range of cascade values and then assess what would be a 'Threshold Rainfall' value for a particular cascade value, any rainfall recorded above this threshold would signal an alert for a probable case of an impending landslide. This 'Threshold Rainfall' value would be determined by deploying our Machine Learning Algorithm on the acquired data set of 'Rainfall Vs Region (in the events of landslide)' from local authorities or governing bodies or NDMA of India.

March 30, 2020 at 4:53 PM
Created by amudha
Edited by pen_flex
Comments (2)
Nice! You are convincing me.
3 months ago
please cross check what are the existing metrics they use in assessing landslide susceptibility in India (geological Survey of India) and mention what are the added parameters. Have you looked at adding other observations or warning signs? like for example, citizen or news reporting of sunken roads or lose soil etc.,
3 months ago

Please sign in to leave comments

Who is most likely to be supportive?

We can get the maximum encouragement and inputs from:

1. Local Government Bodies/ Authority of Disaster Management of the region: They have the incentive to help us provide the data because once this project is up and running, it would help these governing bodies to better plan their disaster management techniques and hence reduce any hance of casualties or damages.

2. Other Researchers in the domain: We can approach other researchers working in a similar field be it a Geotechnician or Hydrotechnician, to help us understand their model if we find it fruitful to deploy their research into our project. Moreover, there are many faculties at our college with whom we have face to face touch with and we can take their help, to propel the feasibility of our project.

March 30, 2020 at 4:53 PM
Created by amudha
Edited by pen_flex
Comments (2)
Is there anyone else/ any other group that could have the great interest in change?
3 months ago
People :)
3 months ago

Please sign in to leave comments

Key foes? Who is most likely to oppose?

Although, there are no exact 'foes' relevant to the purpose of our project, there might be a few itches down the path due to:

  • Any false report that is posted on our app that we would be using for our crowdsourcing. In order to curb that, we would cross-reference each reported incident with multiple reports of the same event and with the local news reports for that event. And if we found it to be a false alarm, we would simply flag that user and not consider his/her report alerts in future.
  • One other cause of disruption to the feasibility could be, if the local authorities are not proactive in participating to provide us with data, or any other delays that may be caused due to the 'system procedure'. We can try to curb this disadvantage by, selling our idea that it is more of a self -help investment for the betterment of policymaking at their level

March 30, 2020 at 4:53 PM
Created by amudha
Edited by pen_flex
Comments (1)
Good start, but keep trying to think of the foes of the project. Think about who would bear the cost of developing this kind of project, or the impacts it may have on property owners/developers.
3 months ago

Please sign in to leave comments

What is the user experience?

March 30, 2020 at 4:53 PM
Created by amudha
Comments (0)

Please sign in to leave comments

Who has to do what. to make it happen?

March 30, 2020 at 4:53 PM
Created by amudha
Comments (0)

Please sign in to leave comments

Who are the key partners to execute? Key partners to help others evaluate your value preposition?

March 30, 2020 at 4:53 PM
Created by amudha
Comments (0)

Please sign in to leave comments

What are the precipitating events?

March 30, 2020 at 4:53 PM
Created by amudha
Comments (0)

Please sign in to leave comments

who else is in the field?

The following stakeholders have worked or are working in this field:

1. NASA- They have developed a Global Landslide Hazard Assessment model, which assess the hazardousness of a landslide event and predict future landslides on the same region. This model is not effective where there is no landslide observation.

2. Various citizen scientists have conducted post landslide research on areas to identify the cause of a particular landslide. A number of research papers have been published in reputed journals with chunks of information on landslide occurences.

3. Local govt. authorities of landslide prone areas have been researching with the help of geologists to find out what are the primary and secondary factors that govern a landslide.

We will combine those individual researched to produce a model that can be used widely.

March 30, 2020 at 4:53 PM
Created by amudha
Edited by ashish
Comments (0)

Please sign in to leave comments

What's wrong? Missing? Not working?

My approach is better because, we plan to predict landslide occurence even at a place when there is no previous observation. Our AI model will analyse the geographical parameters such that it will be able to tell a threshold precipitation value, given all the geographical information at that place (which will be collected by us as described before).
Our approach will also involve Indian Meteorological Department in the picture so that we can use the forecasted rainfall data and alert the citizens beforehand, saving their lives from a landslide event.
We will also take into account the secondary observations that may induce a landslide, for example- loosening of soil or sunken roads near a sloped terrain.

The most crucial part of our project will be to identify the information on geographical parameters of a region, which we plan to collect through crowd-sourcing technique(developing a multi platform app), consulting geologists, past researches by local govt. agencies etc.
Once we are able to collect this information, we can start with applying AI techniques, to come up with a model that can be used to alert citizens.

March 30, 2020 at 4:53 PM
Created by amudha
Edited by ashish
Comments (0)

Please sign in to leave comments

Physical and intellectual resources needed (besides financial resources)

Physical and intellectual resources include the following:

1. Physical interpretation of various geological features of a terrain such as soil type, permeability, porosity etc.

2. Expert geologists to highlight the most important landslide governing factors.

3. A multi platform application developer.

4. Previous knowledge in the field if AI so as to interpret the working of already available AI tools.

5. Previous know-how of modelling a data set so as to use it for prediction through AI tools.

6. Help from local govt. bodies to better understand the behaviour of sloped terrains.

March 30, 2020 at 4:53 PM
Created by amudha
Edited by ashish
Comments (0)

Please sign in to leave comments

Next steps? Pilots?

March 30, 2020 at 4:53 PM
Created by amudha
Comments (0)

Please sign in to leave comments

Cost structure? Financial Sustainability? Revenue streams?

March 30, 2020 at 4:53 PM
Created by amudha
Comments (0)

Please sign in to leave comments

How might this go wrong? How might the problem evolve? What are the legal, cultural and other impediments?

March 30, 2020 at 4:53 PM
Created by amudha
Comments (0)

Please sign in to leave comments

How will i promote adoption?

March 30, 2020 at 4:53 PM
Created by amudha
Comments (0)

Please sign in to leave comments