Notice

AI for Decarbonisation Innovation Programme: Stream 2 successful projects

Updated 19 March 2024

OptimalPrime

Owner: Future Decisions Ltd.
Amount: £104,651
Location: London

Description: Future Decisions is focused on augmenting building control systems using artificial intelligence (AI). The addition of an AI layer superimposed on the building management system (BMS) allows the benefits of AI without the cost or need to change the incumbent system. The AI layer can monitor the incumbent control system, learn the building physics, and create operational mathematical models of behaviour. This combined with external data allows the AI engine to use prediction to optimise control of the building providing significant sustainability savings in the order of 40% to 65% per building.

State-of-the-art solar PV forecasting user real-time PV and satellite data

Owner: Open Climate Fix Ltd.
Amount: £121,500
Location: London

Description: The project will use artificial intelligence (AI) and real-time electricity grid data, satellite imagery, solar PV site data, and weather data to create an open-source model which will forecast hyper-local solar PV generation, with extensions to electric vehicle (EV) load modelling. This will lead to better forecasts of grid load allowing improved scheduling of generation assets, reducing network congestion and renewable energy curtailment. The project is targeting a 20% reduction in the average absolute error of PV forecasts.

HyAI4RES

Owner: H2GO Power Ltd.
Amount: £130,621
Location: London

Description: This project has developed the world’s first artificial intelligence (AI)-driven software management platform for hydrogen systems – HyAI - which has been designed specifically for the hydrogen market’s needs. This project aims to develop an additional module for cases with highly seasonal power demand and extreme events (e.g., weather conditions, energy pricing etc), and optimising hydrogen delivery for multiple off-takers. The model will be based on a facility operated by RWE, a partner in this project, which has an installed renewable capacity of around 50 MW and will use hydrogen to replace LNG for an off-gas-grid town.

AI machine learning for solar forecasting for improved grid management and decarbonisation

Owner: University of Nottingham
Amount: £133,932
Location: Nottingham

Description: This project will create artificial intelligence models combining both sky images and numerical weather data for forecasting solar production (for very short-term, short-term and medium term) to significantly improve the prediction accuracy of meteorological parameters, reducing the power mismatch caused by solar forecast errors.

Neuromorphic computing: ultra-low power AI for cross-industry improved energy productivity

Owner: Secqai Ltd.
Amount: £100,000
Location: London

Description: This project aims to create a novel neuromorphic computing unit which emulates the neural structure of the human brain and consumes a fraction of the power of conventional AI hardware. This project will take the first steps towards achieving a more efficient use of energy in AI computing by testing the principles underlying the proposed device and designing the microarchitecture ready for manufacturing.

Adaptive AI for total substitution rate of alternative fuels in cement manufacturing

Owner: Carbon Re Ltd.
Amount: £135,000
Location: London

Description: The company has developed a platform which uses artificial intelligence / machine learning to optimise production control and delivers a reduction in fuel consumption in the manufacturing of cement. The project will upgrade this platform to identify an optimum fuel mix for the cement plant using alternative fuels, using the unique data from the platform to enhance their AI-powered predictive tools that can guide cement manufacturers on their use of alternative fuels – making the transition to the use of alternative fuels easier. The project is targeting to improve the carbon emission reduction achieved by DeltaZero from 8% to 20%.

Improving the utilisation of raw materials in concrete using artificial intelligence

Owner: FP McCann Ltd.
Amount: £110,636
Location: Belfast

Description: The project aims to reduce carbon emissions due to waste resulting from variability in concrete quality. The size, shape, and moisture content of the concrete aggregate influence the quantity of binder, water and additives required to create a high-quality mix. Currently the monitoring of the ingredients is done manually and is labour intensive. This project will combine AI decision making systems with high-resolution industrial cameras to predict the properties of the aggregate particles. A laboratory setup will be constructed consisting of a camera system attached to a conveyor belt. This generates data to produce computer vision models that can provide real-time decision capability to concrete mixing operations to finely tune the ingredients for optimal strength mixes. With the reduction in waste, less carbon-intensive raw materials are consumed, and less energy is utilised in the production process.

AI for grassland monitoring and management to support decarbonisation

Owner: list.io Ltd.
Amount: £132,147
Location: London

Description: The project proposes to develop AI and machine-learning for grassland monitoring and management to support decarbonisation, with a focus on dairy farms. The company has developed an autonomous soil and crop health monitoring solution, based on mobile robotics for agriculture. The concept is to deliver high-accuracy sensors to provide high-integrity soil and crop data for reporting and validation purposes. This project will use AI across the full stack of such solutions - from translating earth observation (EO) data to actionable areas, identifying sample points, to interpreting the data gathered.