Fighting Climate Change With Big Data: Clir And SINAI Technologies | 7wData

• Read original article here

When you think about solving the climate crisis, what springs to mind?

Most people’s knee-jerk reaction is along the lines of “electrification,” “carbon sequestration,” “recycling,” or “renewable agriculture.”

While not many think of phrases like “Big Data” or “artificial intelligence,” several recent conversations have convinced me how important these fields are to helping our civilization thrive and survive into the next century.

The two founder / CEOs with whom I have had the pleasure to speak recently use AI in very different ways and in completely different fields, but it is clear that the ubiquity of cheap computing power, combined with smart engineers and focused, visionary entrepreneurs represents a formidable force in helping us mitigate and adapt to today’s harsher, more challenging post-climate world.

The companies featured in this article are Clir and SINAI Technologies.

Everyone knows that one big downside of renewable energy (RE) generation is intermittency.

While the grid can cushion some of the ill-effects of intermittency through large-scale battery installations, varying production levels inevitably add uncertainty to the operation of RE facilities.

Uncertainty has negative consequences for plant operators and grid managers (who must instantaneously match power supply to power demand), but it also has negative consequences for financiers of renewable energy projects.

When owners take on leverage (i.e. borrow money) they provide lenders with forecasts of energy production and prices. Inaccurate forecasts can result in banks charging higher interest rates and insurers higher premiums. M&A deal flow also depends on quickly and accurately assessing the production potential of RE assets.

One start-up, Clir, has been using innovations in data science and artificial intelligence to understand operational drivers at renewable energy plants, then leveraging that understanding to improve plant efficiency and decrease uncertainty. By doing so, Clir can bring down the cost of capital for clean electricity generators — making RE facilities more attractive investment assets.

Clir consolidates data from all the units in a wind farm or solar array – a truly enormous amount of data – and runs that data through machine learning algorithms to get a picture of how the facility operates over time and in different environmental conditions.

Clir’s AI then identifies ways to maximize the overall efficiency of the facility in ways that CEO Gareth Brown says might sometimes seem counter intuitive.

For example, for offshore wind farms or those in the middle of large US deserts, there is not much mixing between air at different elevations. In these low-mix cases, efficiency for the farm overall increases when the leading turbines are set to operate at less than peak efficiency.

The wind left un-churned by the leading, wake-creating turbines hits the blades of the trailing, wake-affected turbines with greater force, generating more power. The power generated by the wake-affected turbines more than offsets the reduction in power from the wake-creating ones. According to academic research, this process, known as “wake steering,” can increase the power generated by around 10% and, more importantly, decreases the variability of the power generated by around 70%.

A 70% decrease of uncertainty represents a big win for asset owners and the financiers that back them. With operational uncertainty decreased, banks and insurers can better assess the potential risks and returns, and price their financial products more appropriately. Investors looking to acquire renewable energy assets also have a better idea what a fair price to pay is.

The main premise behind this column is that — insofar as it represents the economic manifestation of humanity’s ability to adapt — capitalism is an irreplaceable tool for fighting climate change.