Solving Climate Change Using Machine Learning
Learning widens our horizons, enhances our knowledge and keeps us up to date with the current world. At first, learning was limited only to living beings. But in the last few decades, humans have managed to create machines which are capable of learning. Arthur Samuel, who coined the term machine learning, defined it as, “Giving a computer the ability to think without being explicitly programmed to.” Machines can predict the future, if the future is not quite different from the past.
Machine Learning: A computer is able to learn from experience without being explicitly programmed.
Currently, we humans are paying the price of evolution. As we have evolved, our population has increased, which means that more resources are required to satisfy the needs of all, and still millions of people are on the streets. We have crippled our beautiful blue planet and displeased mother nature immensely. All this has caused the most significant obstacle which humanity has to face since its existence, which is climate change.
Today, the effects of climate change can be felt across the world. The water crisis in South Africa and Chennai (most recently), the constant floods Assam, variation in temperature in many places around the world, the melting of ice caps and many other problems, are all causes of climate change. These will soon make our beloved Earth inhabitable, unless we do something about it.
The challenge of sustainable development presents a humongous scope for innovation. Machine Learning techniques have previously been used to solve several diverse problems in this field.
The major areas where machine learning can be applied to mitigate or prevent the effects of climate change are -
1] Electricity Systems :
Electricity systems are responsible for generating about 25–30% of greenhouse emissions which damage the ozone layer. Demand Forecasting of electricity and related predictions of sources like sunlight, wind, etc. can be done to optimize production accordingly. This can be achieved by using past power consumption datasets and weather information. Machine Learning can also be used to optimize existing renewable technology — for instance, by predicting how to rotate solar panels for optimal sunlight.
2] Transportation:
About 25% of all CO2 emissions come from the transport sector. These can be reduced by using machine learning. It can be used to decrease transportation activity by using traffic forecasting to optimize public transit, road development, shipping routes and urban planning generally.
Various deep learning methods heavily power Self-driving cars, and they are already here. Building products or add ons along these lines will present an attractive solution. Another approach is by building technologies for electric vehicles with the same use case.
3] Farm and Forests:
“Our current economy encourages practices that are freeing large amounts of this sequestered carbon through deforestation and unsustainable agriculture. The large scale of this problem allows for a similar scale of positive impact, and ML will play an important role in many of these solutions”, explains Alexandre Lacoste of Element AI. Satellite informed ML can be used to estimate sequestered carbon, monitor the health of forests. In agriculture, which constitutes 14% of greenhouse gases, ML can be used to enable precision agriculture, which can lead to effective weeding, crop yield increase, fertilization, etc.
4] Smart Building and Cities:
There can be a range of solutions to make a building ‘smart’ and energy-efficient, thereby reducing harmful emissions. Dynamic power management systems which are automated to be switched on or off depending on whether the room is occupied or not. It can also be used to forecast the energy demand of the building and optimize its design. It can also be used to help heating and cooling systems dynamically adapt. Google already employs this method to enable its cooling systems in their data centres only when it reaches a specific temperature. A combination of ML and IoT can provide many robust solutions.
5] Optimizing Supply Chain Management:
“The availability of large quantities of data, combined with affordable cloud-based storage and computing, indicates that industry may be an excellent place for ML to make a positive climate impact.” posts Anna Waldman-Brown of MIT. IT can be used to predict supply and demand, identify low carbon products, optimize shipping routes and make factories more efficient.
Conclusion:
Earth’s climate has always been dynamic, changing drastically throughout its history, most of the mechanics behind which we don’t fully understand. It is high time we start focusing on solutions to prepare for any unforeseen circumstances or doomsday scenarios that may happen far ahead in the future.
In fact, the actions we take now, this very moment, may decide if we still exist on this planet a thousand years from now.
