It’s a critical moment in the history of the Earth in terms of environmental action (or non-action) and climate change. It’s also an important time in what will become the history of the IoT (Internet of Things)—particularly robotics, machine learning, and AI (artificial intelligence). Innovative robotics and AI-based solutions aimed at addressing challenges related to climate change represent the culmination of these two realities colliding. Could AI technologies, including robotics and machine learning, help scientists, governments, and society at large solve looming, planet-wide issues?

AI and machine learning can help quantify various climate-change issues by providing data about climate and the environment. A partnership between the Atlanta Botanical Garden and Georgia Tech, for instance, is helping to test a new tool for collecting environmental data that could be used to protect ecosystems. A team at Georgia Tech engineered the SlothBot, a conservation robot that monitors temperature, weather, CO2 levels, and other metrics autonomously. The robot moves (slowly, like a real sloth) along a cable strung between trees at the Atlanta Botanical Garden, demonstrating how similar solutions could one day help provide critical data that can inform research and conservation efforts. After SlothBot finishes its test at the botanical garden, researchers hope to bring the robot to South America to provide data for specific conservation efforts.

AI and machine learning are also playing a role by informing the research, deployment, and operation of energy systems and, therefore, contributing to solutions. A group called CCAI (Climate Change AI) recently published a paper called “Tackling Climate Change with Machine Learning,” which identifies opportunities in the energy industry for machine learning, such as forecasting supply and demand, accelerating materials science, managing existing technologies, detecting methane leaks, reducing system waste and current-system impacts, and improving grid scheduling.

In transportation, too, IoT technologies are enabling autonomous vehicles and ride-sharing paradigms, which could positively impact the amount of carbon emissions produced by vehicles. However, CCAI points out that perhaps the most potent impacts AI and machine learning could have in transportation are improving vehicle engineering, enabling intelligent infrastructure, and providing policy-relevant data that could support crucial public policies that reduce carbon and greenhouse-gas emissions.

The ability to optimize buildings and make cities smarter offers a huge opportunity for reducing harmful emissions, since buildings are such rabid consumers of energy. Machine learning and AI technologies play a role here by optimizing energy use via intelligent system controls and improving urban planning for smart cities. In industry, too, the CCAI points to the opportunity for machine learning and AI to help optimize supply chains, streamline operations and enable predictive maintenance, reduce overproduction and food waste, and contribute to the development of climate-friendly materials (for instance, in construction).

As 2021 approaches, what new ways will the IoT industry find to address planet-wide issues such as climate change, perhaps by helping industries like transportation, energy, and agriculture address their specific needs? Sustainability will continue to be a hot topic into next year, because industries and society at large can no longer afford to ignore it.

Want to tweet about this article? Use hashtags #IoT #sustainability #AI #5G #cloud #edge #digitaltransformation #machinelearning #infrastructure #bigdata #climatechange #robotics #robots #artificialintelligence #transportation #smartcities