By 2020, the Fourth Industrial Revolution will be characterized by many technological developments, including but not limited to advanced robotics, autonomous transport, AI, and Machine Learning, advanced materials, biotechnology, and genomics. On the other hand, despite these technological advancements, the world is also experiencing some of the most challenging sustainability issues ever experienced by planet earth such as climate change.
Smart technology combined with AI can help individuals and businesses manage their environmental impact. AI and smart technology can help to collect, analyze data using machine learning to help monitor and improve energy consumption, water consumption while increasing operational efficiency because of lowered of reducing costs and material waste. As such, it is worthwhile to learn how big data and AI can be applied in the industrial, energy, agricultural and water sectors to help monitor and reduce material, water, and energy wastage while increasing operational efficiency.
Below we capture some interesting case studies for companies implementing interesting AI concepts in their respective sectors to help achieve sustainability.
Application of AI in the Industrial Sector.
A combination of software and hardware technology with the use of AI and machine learning is beginning to enter the market and some businesses have adopted such technology to help them manage and improve their environmental performance while saving money.
For instance, in the industrial sector in the US has experienced a high growth of the use of AI-enabled devices to help improve operational efficiency, reduce materials waste, predict interruptions, take advantage of predictive maintenance and optimize resource consumption. The use of AI technology in the industrial sector grows every year at a rate of nearly 65% through 2024.
In the energy sector, the National Renewable Energy Laboratory (NREL) in collaboration with Hewlett Packard Enterprises have developed AI and machine learning technologies to automate and improve operational efficiency, including resiliency and energy usage for data centers. This concept helps to reduce energy consumption and lower operating costs through monitoring and predictive analytics in power and cooling systems for HP data centers.
Uses of Artificial Intelligence in the Energy Sector.
As such, historical data (about 16 terabytes of data) collected from sensors in NREL”s supercomputers are used to train models for anomaly detection to predict and prevent issues before they occur.
This collaboration will help to address future water and energy consumption as early results based on the models trained with historical data have successfully predicted or identified events that previously occurred and thus can be replicated in other data centers.
Also, AI coupled with smart sensors or devices can help to reduce building energy consumption by up to 30% using accurate sensing and predictive analytics according to Department of Energy (DOE) studies.
Furthermore, ABB has developed machine learning algorithms to predict unplanned peaks in power consumption and identify strategies to prevent them. According to ABB, its Energy Forecasting AI uses neural network methods to identify and learn patterns in a circuit or a building’s energy consumption, while also factoring weather data.
As such, using weather forecasts and historical data, ABB’s Energy forecasting is then able to predict power consumption(kW) for the next 24 hours, updating its forecast every 15 minutes with best-in-class accuracy. This ABB system through accurate power consumption prediction will enable facility managers to take full advantage of Time of Use (TOU) tariffs and to take timely action to reduce unplanned consumption.
With regard to renewable energy, the application of AI and machine learning can help to solve the intermittent nature of wind and solar power that may bring about grid stability issues. Currently, pumped hydro or batteries (energy storage) is employed to solve this intermittent nature of renewable energy.
However, the grid will be more stable when AI and machine learning algorithms are employed with renewable energy to predict or forecast when the amount of solar or wind power goes down so that the power stored can kick in. This can help to avoid expensive or use of fossil fuel-powered standby generators.
Application of AI in the Agricultural Sector.
Similarly, smart sensors and AI can be applied by farmers that have connectivity to save water, energy, fertilizer and pesticide usage. One great example of a company that is implementing the Internet of Things (IoT) to bring improvement in energy and sustainability is Foris.io powered with IBM Watson.
Working with IBM Watson™ and IBMCloud™, foris.io™ uses data from precision agriculture tools and grower records, cognitive computing, and analytics to enable holistic field management.
Using probes installed on the soil, smart devices are capable of measuring and transmitting data on moisture, PH level, salinity, temperature and other factors that are fed into IBM’s data storage, processing, and analytics cloud for analysis.
Using AI and machine learning, the data gained from the soil sensors are combined with a variety of other environmental factors, such as weather, geographic location, crop yield statistics, and other data to provide farmers with real-time feedback to inform about how much to water and fertilize according to Foris.io’s motto, “just enough • just in time”.
Application of AI in the Water sector
According to UN-Water, water scarcity already affects every continent and water use has been growing globally at more than twice the rate of population increase in the last century, and an increasing number of regions are reaching the limit at which water services can be sustainably delivered, especially in arid regions.
In the US, nearly two trillion gallons of water are lost in the country before it even reaches an end-use due to leaks and pipeline faults according to ABB. To address this, ABB amongst many other companies are implementing flow and sound sensors into water infrastructure to pinpoint leaks and predict and proactively maintain the water supply using AI and machine learning.