One of the upcoming area AI in Green Computing discusses the same. I have tried to use AI in predicting AQI values of air pollutants. I have also considered sleep modes of sensors and their switching when they are idle. Maybe these articles may help you.....1. http://www.cit.iit.bas.bg/CIT-2020/v-20-2/10341-Volume20_Issue_2-10_paper.pdf 2. Article Pollution Weather Prediction System: Smart Outdoor Pollution...

AI can be used to detect toxins in the environment. It can actually be used, for example, on vehicles to detect such emissions. This is Internet of Things problem that will require you to investigate how algorithms can be fused into the device to help with such detections.

Systems, which consume energy and produce emissions, are often dynamical systems. Furthermore, these systems are often complex and nonlinear. Of course, one approach is to optimize the mechanical/electrical design of the underlying physical system. Here, machine learning approaches can be used to model the effects and interaction effects of varying design parameters (design of experiments). Once these effects are modelled, this model can be used to optimize the system design mathematically. Since these phenomena can be often reduced to quasi-static problems, this can be implemented quite easily.

As I stated before, energy consuming and emission generating nonlinear systems are often dynamical. Therefore, the control of these systems can significantly affect the consumption and emission of pollutants. Often, especially in traffic, many different nonlinear systems will interact with each other dynamically (e.g. traffic signals with vehicles or vehicles with other vehicles). Often, these (nonlinear) couplings and nonlinear systems are so numerous and complex that they are impossible to model physically. However, to be able to e.g. calculate an optimal control strategy, a model is required. Here ANN can be used to model the nonlinear systems and couplings dynamically using measured data sequences of the process(es). This is called nonlinear system identification. Note, that this process is extremely complex and the model quality and applicability depend on a lot of different factors. Once these dynamical systems are identified, the ANN-based, nonlinear dynamical model can be used for advanced process control methods (e.g. nonlinear model predictive control or optimal control). These predictive control methods allow furthermore the incorporation of lots of (future) information and predictions, which can further reduce the consumptions and emissions.

Another method to address this dynamical problem using ANN would be e.g. reinforcement learning.

Of course, there are many more possibilities to use AI to optimize these quantities but this should be enough to start the discussion.

I shall conclude by making two observations.

Firstly, AI can expand energy markets dramatically by unlocking new sources, reducing transaction costs and making it easier for consumers to define their market purchases. Efficient markets are fantastic, but they can also lead to more rapid market failures.

Climate change could be the world's greatest failure in the market — emission of warming gases has global external ramifications, and failure to implement taxes or additional incentives contributes to greater pollution and externalities than warranted for companies and individuals.

AI can transform markets, but without clear signals the markets will not transform emissions. The political capacity to enforce and organize these signals through countries remains a challenge as much today as it was 30 years ago — and AI did practically have little control.

=========================================

Secondly, the world will possibly discover that the distinction between adaptation and successful growth will blurred as it deals with the consequences of climate change and adjustment. Among the most important development policies are also some of the key adaptation policies.

For instance, early warning systems for crops are one way to mitigate the impacts of climate change on agriculture — in which farmers can modify seeds, cultivation methods and plantation times (including other variables) to minimise adverse effects due to weather vagaries. Also without altering atmosphere, the same structures make sense.

AI can help to improve the economic and political performance, administrative

and democratic orientation of these kinds of development-oriented activities and policies. As long as it continues, the line from adaptation to growth will further blur.

By using AI techniques the most conventional techniques may be data filtering or nose reductions. For example via Butterworth filtering, Kalman Filtering and the most recent filtering technique known as Grassmann Filtering.

Okuthe P Kogeda , Christian Gletter, Ahmed A. Mawgoud Muhammad Ali , thank you all for your input. From responses so far there is a clear tie of AI to algorithms (e.g. neural networks & filtering) and the so called internet of things (IoT). Please continue to share details of projects you are working on.

AI can monitor demand trends and be able to balance supplies.

One of the upcoming area AI in Green Computing discusses the same. I have tried to use AI in predicting AQI values of air pollutants. I have also considered sleep modes of sensors and their switching when they are idle. Maybe these articles may help you.....1. http://www.cit.iit.bas.bg/CIT-2020/v-20-2/10341-Volume20_Issue_2-10_paper.pdf 2. Article Pollution Weather Prediction System: Smart Outdoor Pollution...

• Forecasting energy demand and managing the output accordingly. This can help to reduce reliance on fuel, or manage its consumption, thereby also reducing emissions.
• Reducing breakdowns. AI uses data and analytics about operations to forecast any possible failures of critical energy infrastructure.
• Managing power grids. Some AI applications are designed to handle multiple energy sources such as solar, wind and fossil fuels.
• Maximising plant outputs by optimising processes.
• Reducing energy used for heating and cooling.
• Reducing utility costs (such as for compressed air, nitrogen and water) by optimising performance and identifying maintenance issues ahead of time.

Dear Cory,

Artificial Intelligence can improve energy efficiency and reduce emissions by plenty of ways and it can improve predictions of how much electricity we need, discovering new materials, optimize how freight is routed, checking lower barriers to electric-vehicle adoption, helping to make buildings more efficient by meant of building energy efficiency analysis, better estimates of how much energy we are consuming and hence can cut energy emissions, optimizing supply chains, and make precision agriculture possible at scale, cut costs, etc. Most visible in the energy and climate space is the impact of AI on how energy is supplied. That's why more intelligent energy supply systems, in effect, shift outward the supply curves. They take resources that are hard to tap and lower the cost. AI can be used to solve an array of environmental problems, such as climate change and natural calamities prediction. AI will also take over many hazardous jobs in the future. Although AI is in its early stages of implementation, it is poised to revolutionize the way we produce, transmit, and consume energy. At the same time, AI is also limiting the industry’s environmental impact at a time when demand is steadily growing, our energy production portfolio is diversifying, and we are witnessing the ramifications of fossil fuel consumption on biodiversity, air quality, and quality of life. Using AI, it can modernize the energy grid, by which we can be optimistic in expecting the smart grid system to lower electricity bills and prevent catastrophic blackouts by optimizing supply and demand at local and national levels. For those looking to make a difference in shaping the future of society, the interface between AI and energy is a great place to start.

Ashish

Tackling carbon emissions is one of the biggest challenges faced by the world today. For big business, this means making a strategic and managed move towards increasing the use of renewable energy sources, as well as creating efficiencies across all aspects of their operations.

It’s a difficult task to manage alone, even for an enterprise on the scale of tech giant Microsoft or energy titan Shell. But working together creates new possibilities that go further than what it is likely they could accomplish individually. Beyond meeting their own zero-carbon commitments, there's the opportunity to help other companies within their vast ecosystems of customers and suppliers to meet their environmental and safety goals, too...

https://www.linkedin.com/pulse/microsoft-shell-announce-new-partnership-use-artificial-bernard-marr/?trk=eml-email_series_follow_newsletter_01-hero-1-title_link&midToken=AQHLIjW6KB_ESw&fromEmail=fromEmail&ut=2u41RwKC6GsFs1

Sharnil Pandya , Eliud Perez , thank you for these specific examples! Ljubomir Jacić I am interested in the level of detail as part of the Shell-Microsoft story as presented in some of the literature referenced in this discussion. The conversation after the story seems less than positive and calls for more information too.

Dear Cory Jensen , you will, probably, get faster this information than me. I can only bring some more info from both parties.

https://www.shell.com/energy-and-innovation/digitalisation/news-room/shell-and-microsofts-strategic-alliance.html

https://news.microsoft.com/2020/09/22/shell-and-microsoft-form-alliance-to-help-address-carbon-emissions/

https://www.power-technology.com/news/shell-microsoft-expand-partnership-support-net-zero-emissions/