Identifying the risk of a flood at specific locations in your area?

Meniscus provides software that gives a “heads up” about the risks of flooding at a specific flood risk location. Our service brings together a number of sets of data into one easy to use dashboard and calculates a range of metrics that identify if there is a potential flood risk.

Do you have locations where an early warning of a potential flood risk would be beneficial?

  • We can supply customisable data for any specific location with the high alert limits set from local specific knowledge
  • We can then mail out warnings to any nominated contact
  • We can apply more complex models if required
  • Everything is based on real time data so all the calculations are continually updated every 5 minutes as new rainfall data becomes available

Would a visual overview of likely rain events and any potential flood risk be helpful to you? If so, this is how it works:

    Meniscus software uses and combines a range of data source sets and collates these into one simple dashboard to monitor and predict likely rainfall levels to provide early warning signs of potential risks. The information displayed in the dashboard includes:

  • Current rainfall (updated every 5 minutes)
  • Forecast rainfall for the next 36 hours
  • Antecedent Precipitation Index (API) to calculate ground saturation – uses the last 30 days of rainfall (updated every 5 minutes)
  • Maximum forecast rainfall today and tomorrow
  • Maximum Rainfall Return Period (1 in 5 year rain event) for today and tomorrow
  • River level – if appropriate and if it is monitored by the Environment Agency (updated every 5 minutes)
  • The Environment Agency gauging station river level data is an open dataset and we use the Environment Agency flood and river level data from the real-time data API (Beta)

    River Ouse burst its banks in commnity picnic area

    River Ouse burst its banks in community picnic area



Flood Forecasting part 2

A new project has been undertaken by several UK Councils using MAP to deliver specific localised flood monitoring and is currently being tested by Cambridge City Council.

Flood forecasting

Flood forecasting

This service combines actual radar rainfall and forecast rainfall data and uses it to calculate the maximum rainfall return period for a specific location for the next 36 hours as well as the Antecedent Precipitation Index (API) as an indicator of moisture levels in the soil (this calculation uses soil type data).

The solution also displays river level gauging data from the Environment Agency and the historic and forecast information is displayed in a mobile-friendly dashboard. The next stage in this project is to implement a learning based model to correlate increases in these rainfall metrics with the increases in the river gauging height.

All the above working examples demonstrate some of the capabilities of MAP in terms of integrating a broad variety of datasets into models built inside MAP as well as the capability to use MAP to deliver aggregated datasets into third party models run externally to MAP.

MAP makes extensive use of RESTful Web Services making it possible for approved third parties to easily load new datasets, create new Entities and extract aggregated/calculated datasets from MAP. An Entity is any unique identifiable “Thing” which in this context might be a community, a property, a catchment etc. Each Entity contains internal ‘hooks’ to the calculations/models required to turn any raw dataset into the required calculated metrics. MAP provides the framework to allow these Entities to be readily extended making it easy to change the underlying models/calculations and adding in new database properties and metadata.

It is also envisaged that MAP will use additional datasets to enhance the capabilities of existing models and potentially use these to improve the inputs into current models. These additional datasets might include:

  • Satellite based imagery. MAP already has the capability to process images into gridded datasets and this is already used to capture soil type information. Such imagery might improve estimates of permeable/impermeable contributed areas to name one such use.
  • Topological data or potentially LIDAR data to improve the topographical data fed into models.
  • Using data from third party weather stations to include companies who operate a network of weather stations providing soil moisture sensors at various depths, humidity and evaporation sensors. Meniscus is already looking to integrate such data.

It is envisaged that a final solution may comprise an enhanced mobile app and associated mobile friendly dashboard delivering location specific flood information derived from this broad range of datasets. Importantly this flood information will use machine learning to improve flood predictions based on the relationship in the actual data and will not rely upon complex deterministic models – unless they are already available.

How Innovative is MAP for Predicting Flooding?

Predicting Flooding

Predicting Flooding

Flood Prediction

Existing solutions for predicting flooding are heavily reliant on the use of complex models that are very expensive and time-consuming to build. In addition, these models can be too complex to readily run in real time conditions.
The Meniscus approach looks to replace this by using existing datasets and models wherever possible to build up simplified models that can be run in real time.

These simplified models can then be improved upon using a combination of machine learning and by using additional datasets (like satellite imagery) to improve the assumptions and variable on which the models are built. Consequently, this approach is ideal for delivering real-time flooding information for a large number of relatively small catchments (it is assumed that the existing more complex models will cover known flooding hotspots).

The use of the algorithms already developed in MAP to track existing rainfall and predict its course over the next hour will enable the solution to rapidly respond to the development of short summer high-intensity rain events rather than relying on forecasts that are notoriously poor at forecasting such events.

MAP itself is a new and highly innovative platform (the development was initially part funded by InnovateUK in 2014) and its structure is specifically developed to allow rapid development and changes to the underlying database structure and models. It is cloud based with a comprehensive RESTful web service interface making it possible for third parties to interact with it.

Flood Forecasting part 1

MAP-Rain is an existing flood forecasting and rainfall prediction solution based on the proven Meniscus Analytics Platform (MAP) which is a high performance, generic, Big Data, cloud based real time calculation/analytics platform.

MAP-Rain is a generic and initial solution for flood forecasting and integrates additional datasets and models from the existing systems, APIs and databases already used and developed as well as a range of new datasets.

MAP-Rain delivers the following real-time flood forecasting solutions:

Flood Forecasting by Meniscus MAP

flood forecasting

  • Real-time prediction of flooding in sewer networks by using simplified hydraulic models, real-time actual radar-based rainfall, forecast rainfall and sewer pumping station operational data. MAP is currently able to process over 6,000 sewer catchments with the latest rainfall data within five minutes.
  • Aggregating real-time radar rainfall data (five-minute updates for 65,000 km2 at 1km2 pixel resolution) into over 1,000 polygon based sewer catchments. Used by modellers to build a range of hydraulic models. Calculating a range of rainfall related metrics for each polygon.
  • On Demand calculation of rainfall return period calculations (using the Flood Estimation Handbook FEH methodology) for any point in a region for any time during the past three years and comparing this result to a similar calculation from the local Environment Agency rain gauge.
  • Integrating an open source complex third party pollution transportation and hydraulic model (Soil and Water Assessment Tool) to predict the impact that rainfall has on pesticide runoff (in particular metaldehyde) concentrations at key water abstraction points in sensitive river catchments.

MAP-Rain is also being used to as part of an InnovateUK funded Smart City project (Hyperlocal Rainfall) looking to increase the use of sustainable transport in cities. This solution predicts the path of actual rainfall over the course of the next hour, at five-minute increments, and relates this to specific journeys that users can create. The aim being to increase the use of cycling and walking by answering the question, “Will it rain during my journey”? This solution uses a combination of real-time radar rainfall data, local wind speed and direction data from an existing local network of weather stations and high altitude wind forecasts. The radar rainfall data is also being ground truthed to local rain gauge data to increase accuracy. As part of this Hyperlocal Rainfall project Meniscus has developed an Android mobile app for users to create journeys and to track and plan journeys around rainfall. MAP-Rain is integrating a third party personalisation engine developed to learn users’ behaviour and to personalise the app based on insights learnt by the engine. The project is initially focused around Peterborough but is also being tested using the entire radar rainfall dataset for England and Wales.

Hyperlocal Rainfall Predictions

Rainfall prediction app

Rainfall prediction app

Our innovative Hyperlocal Rainfall app has recently been published on the Playstore. We have had 5* reviews and between 100 and 500 installs in less than one month.

We believe the positive reviews are predominantly down to our highly accurate and hyper-localised rainfall predictions. These predictions are updated every five minutes to give 12 new rainfall predictions at five-minute intervals for the coming hour. The predictions are made using a combination of data sets including radar rainfall, wind speed and direction and rain gauges.

The ability to provide such accurate hyper-localised predictions can be somewhat attributed to ground truthing. A lot of weather predictions are based solely on radar rainfall data and although this is accurate to some extent; the radar rainfall data does not usually match the rainfall data that fell on the ground beneath the radar image. This is due to conditions such as wind speed and direction, topography etc.

The benefit of ground truthing radar data is that based on the relationship between historic radar and ground rainfall data, an equation can be derived for any location to manipulate the radar data into more closely matching the ground data. Ground-truthing significantly contributes to enabling us to deliver these highly accurate hyperlocal predictions.

Multiple Regression Analysis Lowers Fleet Costs

Do you have a fleet management system? Does this calculate how much fuel is being consumed by each vehicle and by whom? This is very important information and very often nothing, or not enough, is being done with your information.

With the constant fluctuation in fuel prices, it can be difficult for transport companies to budget their fuel costs as accurately as possible. Many factors contribute to the total fuel cost.


lower fleet fuel

Multiple Regression Analytics lower fleet fuel

Lowers Fleet Costs

Meniscus has used these factors to model the cost of fuel for transport companies. Through Multiple Regression Analysis, an 11% reduction in total fuel costs could be achieved, by reducing the number of idling hours of drivers and their harsh driving scores by 20%.

Multiple Regression Analysis allows a correlation between a dependent variable and many independent variables. The analysis provides the coefficients for each variable giving an equation in the format of y = β0+ β1X1+ β2X2 +…+βnXn. From the established regression equation, it is then possible to use the independent variables to estimate the dependent variable, in this case, fuel cost. Multiple Regression Analysis also allows us to determine the contribution each individual independent variable makes to the dependent variable value. We are in the early stages of analysing transport data and believe it is a sector that would see real benefit from our MCE (Meniscus Calculation Engine).

We are not saying you shouldn’t use the system you have. All we are saying is that maybe we can do more with data and help you become even more cost efficient. In other words, get more from your system and by analysing the data produced to reduce costs, giving you more time to focus on other pertinent areas of your business.

Watch this space for new amazing on developments.


Overview of Aggregation Period and Aggregation Function

Aggregation is the process of performing a simple data-reduction function over a section of time.The section of time is from the current pre-processed Data Point time (inclusive) to the last pre-processed Data Point time (exclusive).

Overview of Item Types for entering raw data into MCE

MCE supports a number of different Item Types. Each Item Type is designed to simplify the processing of the most common types of raw data that are found in general everyday use. MCE process each type of data slightly differently and this article sets outs the differences.

MAP Items and DataItems

An Item owns a number of DataItems (called Item DataItems) related to the processing of Item Type data. The input is either raw meter data imported into storage, or data from any of the stages of processing other Items.

Core Concepts for MCE. Data Point and Data Point List

MCE processes sequences of time-variant data. Each time-value pair within this data is a Data Point, and each sequence of them is a Data Point List.