Why ML is Pivotal in Securing a Sustainable Future

ML CleanTech
Machine learning has the possibility to optimise energy grids, ensure waste is kept to a minimum, and renewable sources are maximised

We live in an age of data, with digital information now being seen as more valuable than oil. Fittingly, then, this overtaker of oil also holds the keys to helping us reduce our reliance on it. 

Despite being an issue that has almost all the world’s leaders' attention, stopping climate change seemingly still has no definitive answer. But in the current craze for AI, industry experts are pointing at how a subset of the technology, machine learning (ML), can help us get a handle on it. 

By applying ML to work on the terabytes of data collected from the grid of a country, we can optimise the outputs of systems that are in charge of energy, and balance those that are intensive users of it.

Analysing this data effectively is still a massive challenge, as is implementing a system to power it. The impetus for doing so is, however, apparent. So what do business leaders need to know to get the wheels in motion on the train to a more sustainable tomorrow?

Leveraging ML for energy

ML is a subset of AI that allows computers to learn without explicit programming. It works by feeding algorithms massive amounts of data to enable them to identify patterns and make predictions. 

Machine learning applications are widespread and constantly evolving, impacting fields like healthcare (analysing medical images for disease detection), finance (identifying fraudulent activity), and self-driving cars (interpreting sensor data to navigate safely). 

The technology can also have a positive effect on climate change, particularly when aimed specifically at the energy system. Energy grids, interconnected networks that generate, transmit and distribute electricity, are often a large source of domestic pollution for a country due to the fossil fuels by which they are typically powered. 

The entire grid is constantly monitored and adjusted to ensure a continuous flow of electricity, balancing supply and fluctuating demand in real time to stop blackouts. It’s this balancing of demand and supply where ML comes into play.

“Machine learning can be used to analyse vast amounts of data on energy consumption and predict demand,” explains Erik Terjesen, Partner at Silicon Foundry, a subsidiary of Kearney. “This helps optimise energy production and distribution in electricity grids, reducing reliance on fossil fuels.”

By using ML to analyse the masses of data taken from the grid, it can signal when demand will be high and changes can be made to factor this in. This optimisation can ensure that less energy is spent balancing, less energy is wasted, and therefore, less is needed to power the grid. 

“One of the most important ways AI is improving energy production and efficiency is that it’s enabling us to redistribute energy across the grid in such a way that you can have up to 50% of energy optimisation in terms of use and consumption,” explains Elena Morettini, Global Head Sustainable Business at Globant.

This may not only help reduce emissions, but counterintuitively, may actually become more of a necessity for the grid as other elements of our world – EVs, solar power, wind turbines – become more common. 

Sustainability makes ML a necessity

Many of the world’s power grids were originally designed for a world dominated by petrol-powered cars. Therefore, a surge in demand for the soon-to-be millions of EVs plugged in every night will represent a massive shock that many systems frankly cannot handle.

“EVs are critical for reducing fossil fuel reliance, but by 2030, EV charging capacity will need to be 12 times greater than it is today,” Rob McInerney, CTO at Lightstate, tells AI Magazine. “Emerging AI solutions that can forecast localised EV demand and enable complex, real-time decision-making will be a huge weapon in slowing down climate change.”

Demand for energy will also change, and a larger portion of that energy will come from renewable sources. For example, if a low-wind summer results in minimal power generation from a wind turbine, employing a machine learning model to optimise operations can enhance energy security. 

ML models can also allow better placement of future renewable assets. Through geospatial decision-making, it uses data from advanced mapping technologies to gather and analyse spatial information from sources such as satellites and ground observations to identify optimal sites for renewable energy assets. 

"Developers can assess critical factors such as sun exposure, wind patterns and water resources, which are essential for determining the feasibility and potential energy yield of a project,” Rob explains. 

Smarter sustainable energy

With a 2023 report released by the UN claiming the world is likely to pass a dangerous temperature threshold within the next 10 years, time is not on our side when it comes to implementing sustainable solutions. 

Yet, heedless implementation of any AI solutions like ML should still be argued against. “We absolutely still need human intelligence to ensure responsible and effective decision-making,” says Globant’s Elena Morettini. 

Having due diligence in overseeing data will also avoid biases in the modelling. For instance, using data captured from developed nations for a model to be pushed across grids across the world might not be suitable for developing countries with different needs and infrastructure.

But there is a lot to be optimistic about. In 2023, Google announced the discovery of 380,000 new stable materials thanks to GNoME, its ML tool. These materials have the potential to develop future technologies, including next-generation batteries to power EVs, and address the inherent contradiction in the production of some clean technologies which can use rare earth materials. 

For Elena, the best thing about this AI boom and its associated technologies is how it has made them more accessible. 
“What’s arguably most exciting for me is that embedding ML into business practices is becoming increasingly scalable and cost-effective – you don’t have to be the latest clean tech startup or a big company to integrate ML into your business reporting and operational processes,” she asserts. “ML is going to be central to scalable, affordable energy solutions, no matter the size of your business.”

******

Make sure you check out the latest edition of AI Magazine and also sign up to our global conference series - Tech & AI LIVE 2024

******

AI Magazine is a BizClik brand

Share

Featured Articles

Sophia Velastegui: Overcoming Enterprise AI Challenges

AI Magazine speaks with AI business leader Sophia Velastegui as she offers advice for businesses seeking to advance their AI use cases responsibly

Bigger Not Always Better as OpenAI Launch New GPT-4o mini

OpenAI release new GPT-4o mini model designed to be more cost-efficient whilst retaining a lot of the same capabilities of larger models

Why are the UK and China Leading in Gen AI Adoption?

China and the UK are leading the adoption of Gen AI, which although sounds surprising to begin with, becomes clearer as you dig into their state strategies

Moody's Gen AI Tool Alerts CRE Investors on Risk-Posing News

Data & Analytics

AWS Unveils AI Service That Makes Enterprise Apps in Minutes

Data & Analytics

Jitterbit CEO: Confronting the Challenges of Business AI

AI Strategy