The biggest energy transition in history is well and truly underway, and nowhere is the shift more readily apparent than in the transport industry. Wall Street is almost unanimous that electric vehicles are the future of the industry, with EV sales already outpacing ICE sales in markets such as Norway.
That kind of exponential growth can only mean one thing: Explosive demand for the metals that go into those batteries.
Demand for battery metals is projected to soar as the transport industry continues to electrify at a record pace. In fact, there’s a real danger that current mining technologies might struggle to keep up with the demand for battery metals in the near future.
Thankfully, Artificial intelligence (AI) can not only be deployed to help improve the way these crucial elements are mined but can replace them altogether.
KoBold Metals is a mining technology startup that’s developing an AI agent to identify the most desirable ore deposits in the least problematic locations.
IBM Research, meanwhile, is working round the clock harnessing AI techniques to identify alternative materials that could be used as substitutes for existing battery elements.
Battery metals, including lithium, cobalt, and nickel, are enjoying a banner year, with lithium carbonate prices having surged 52% in the year-to-date.
Related Video: Institutional Investors Hold $1.03 Trillion In Coal
Source: Trading Economics
Low hanging fruit
According to Kurt House, co-founder and CEO of KoBold, the low-hanging fruit in the form of easy-to-reach mineral reserves are mostly gone, and the narrow window available to act to prevent climate change means that we simply don’t have the luxury of time to wait another 10 or 20 years to make more discoveries.
KoBold is partnering with Stanford University’s Center for Earth Resource Forecasting in developing an AI agent that will make decisions about where explorers should focus their attention. KoBold will first look for copper, cobalt, nickel, and lithium--key metals in the manufacture of batteries for EVs, smartphones, and other renewable equipment such as solar panels.
KoBold’s AI-driven approach begins with a comprehensive data platform, which stores all available forms of information about a particular area, including satellite-based hyperspectral imaging, soil samples, and even century-old handwritten drilling reports. The company then applies machine learning tools to make predictions about the location of compositional anomalies--i.e., unusually high concentrations of ore bodies in the Earth’s subsurface.
KoBold’s AI agent could make mining decisions ~20 times faster than humans can while dramatically reducing the rate of false positives in mining exploration.
Jef Caers, professor of geological sciences at Stanford, says the AI agent is ‘‘...completely new within the Earth sciences.”
The EV and renewable energy sectors might have AI and machine learning technologies to thank for a smooth and speedy transition to green energy.
A December paper in the journal Nature has predicted that the global fleet of battery-powered vehicles will expand from 7.5 million in 2019 to a staggering 2 billion cars by 2050. According to energy watchdog Bloomberg New Energy Finance (BNEF), EV sales globally are expected to grow fifteen-fold over the next 10 years from 1.7M units in 2020 to 26M units in 2030, with EVs accounting for 28% of new vehicle sales from just 2.7% in the current year.
By 2040, EVs will account for ~58% of new vehicle sales globally.
Consequently, the global EV fleet is expected to jump from 8.5M in the current year to 116M in 2030, while the installed battery cell capacity for EVs has been forecast to grow from around 70GWh in 2017 to 1,600GWh in 2030.
With nearly 40% of the world’s lithium supply and half of the cobalt going into EV batteries, the EV explosion will be a key driver of the demand for these two key battery metals over the next decade.
AI is also being directly incorporated into our power grids.
As the Arctic Blast has so painfully reminded us, our electric grids are simply ill-prepared for the energy shift. That’s because renewable energy is highly intermittent by nature, whereas our grids are designed for near-constant power input/output.
Indeed, wind and solar energy have the lowest capacity factors of any energy source.
For the energy transition to be successful, our power grids have to become a lot smarter. Luckily, there’s an encouraging precedent.
Three years ago, Google announced that it had reached 100% renewable energy for its global operations, including its data centers and offices. Today, Google is the largest corporate buyer of renewable power, with commitments totaling 2.6 gigawatts (2,600 megawatts) of wind and solar energy.
In 2017, Google teamed up with IBM to search for a solution to the highly intermittent nature of wind power. Using IBM’s DeepMind AI platform, Google deployed ML algorithms to 700 megawatts of wind power capacity in the central United States--enough to power a medium-sized city. Related: Tesla Is Silently Building Another Huge Battery In Texas
IBM says that by using a neural network trained on widely available weather forecasts and historical turbine data, DeepMind is now able to predict wind power output 36 hours ahead of actual generation. Consequently, this has boosted the value of Google’s wind energy by roughly 20 percent.
A similar model can be used by other wind farm operators to make smarter, faster, and more data-driven optimizations of their power output to better meet customer demand.
IBM’s DeepMind uses trained neural networks to predict wind power output 36 hours ahead of actual generation
Houston, Texas-based Innowatts, is a startup that has developed an automated toolkit for energy monitoring and management. The company’s eUtility platform ingests data from more than 34 million smart energy meters across 21 million customers, including major U.S. utility companies such as Arizona Public Service Electric, Portland General Electric, Avangrid, Gexa Energy, WGL, and Mega Energy. Innowatts says its machine learning algorithms can analyze the data to forecast several critical data points, including short- and long-term loads, variances, weather sensitivity, and more.
Innowatts estimates that without its machine learning models, utilities would have seen inaccuracies of 20% or more on their projections at the peak of the crisis, thus placing enormous strain on their operations and ultimately driving up costs for end-users.
Further, AI and digital solutions can be employed to make our grids safer.
In 2019, California’s biggest utility, PG&E Corporation (NYSE:PCG), found itself in deep trouble after being found culpable for the tragic 2018 wildfire accident that left 84 people dead and, consequently, was slapped with hefty penalties of $13.5 billion as compensation to people who lost homes and businesses and another $2 billion fine by the California Public Utilities Commission for negligence.
Needless to say, it’s going to be a long climb back to the top for the fallen giant after its stock crashed spectacularly after the disaster despite the company emerging from bankruptcy.
Perhaps the loss of lives and livelihood could have been averted if PG&E had invested in some AI-powered early detection system like Innowats.
By employing digital and AI models, our power grids will become increasingly smarter and more reliable and make the shift to renewable energy smoother.
By Alex Kimani for Oilprice.com
More Top Reads From Oilprice.com:
- Oil Falls After Spiking Due To Missile Attack On Saudi Tank Farm
- Oil Soars As OPEC+ Sources Suggest No Production Increase
- $70 Oil May Cause Slowdown In Demand Recovery