FLOOD PREVENTION USING ARTIFICIAL INTELLIGENCE
CASE STUDY
Flooding in the UK
Floods have been a consistent problem for the roads in the UK. Not only, they occur regularly, they occur without warning and are often reported late.
What Are the Effects of Flooding in the UK?
Around 2.4 million properties in the UK are at risk from river and coastal flooding each year.
A further 2.8 million properties in the UK are susceptible to surface water flooding.
One in six properties in the UK are located in areas where there is significant risk of flooding.
As many as 40% of businesses do not reopen after suffering from a flood.
Flooding can cost the economy upto £100,000 per hour per major road affected.
Mental Health impacts of flooding can be prevalent for more than 2 years.
Overview
Current Flood Prediction Methods.
Currently, there are two ways of prediction, either guessing or watching through a camera feed attached to some motorways.
Data Collection to solve the problem.
To solve this problem, we used state-of-the-art methods in data engineering and artificial intelligence. We gathered three different data sources: conditions of pipes data, historical weather data and historical flood index data. By combining these data sources, we created a week-in-advance flood warning system.
Identification of Flood Hotspots.
This helped us predict the flooding hotspots and report them before there was likely to be any flood. Most likely to flood and recurring hotspots were dealt with first and this gave our clients a grip on a staggering problem.
Our client was thrilled to hear we had a solution!
Our client had been collecting data of pipe conditions and historical flood index for many years now. This data was used for a different purpose altogether. However, with the realisation that this gold-mine of data could be used for something much more powerful, our client was thrilled and immediately saw greater value in this dataset and other similar internal datasets.
80%
RESULTS
80%
More floods predicted
7 Days
In advance predictions
0
Devices installed on roadside for monitoring
Smart Solutions are needed!
Highways agencies need a smart solution to the flood prevention problem. This solution also needs to be as lightweight in terms of attaching sensors as possible.
Artificial Intelligence has proven.
Data Engineering and Artificial Intelligence have shown many business problems can be addressed by asking the right questions and querying the datasets with a specific problem in mind. AI algorithms have great predictive powers if provided enough data.
We at ML Sense found the solution!
We combined the domain knowledge, data already owned by Highways England and expertise on Artificial Intelligence to produce a data product. This data product takes in weather as input and outputs flooding hotspots. It is also designed to stay up to date. Daily weather data is consumed automatically.
Highways England
