How Machine Learning beneficial in Climate change and Green Power Generation

This colour-coded map, produced by scientists at NASA's Goddard Institute for Space Studies, shows the 5-year average (2005-2009) global temperature change relative to the 1951-1980 mean temperature. The colour scale varies from darkest red (a 2 degree Celsius, or 3.6 degree Fahrenheit, warming) to orange and yellows (1 degree Celsius, or 1.8 degree Fahrenheit, warming) to light blue (a 0.5 degree Celsius, or 0.9 degree Fahrenheit, cooling). January 2000 to December 2009 came out as the warmest decade on record since global instrumental temperature records began 130 years ago. And 2009 tied as the second warmest year. Image credit: NASA/GISS

Climate change refers to a broad range of global phenomena created predominantly by burning fossil fuels, which add heat-trapping gases to Earth’s atmosphere. These phenomena include the increased temperature trends described by global warming, but also encompass changes such as sea level rise; ice mass loss in Greenland, Antarctica, the Arctic and mountain glaciers worldwide; shifts in flower/plant blooming; and extreme weather events.

There are two type of energy resources renewable and non-renewable. Renewable energy resources include solar, water, wind, biomass, and geothermal. Renewable energy comes from sources with an unlimited supply whereas non-renewable sources of energy comes from sources with limited supply. Fossil fuels i.e. coal, oil, and natural gas are the most common example of non-renewable energy resources. But fossil fuels are the primary culprit behind climate change. So, we have to focus on renewable sources of energy for our use.

Here, I have described few renewable sources of energy which can be boosted with the help of machine learning:

Solar energy is a type of energy generated by sun. Solar energy is a renewable source of energy. Today, photovoltaics is probably the most familiar way to harness solar energy. Photovoltaic arrays usually involve solar panels, a collection of dozens or even hundreds of solar cells. Each solar cell contains a semiconductor, usually made of silicon. When the semiconductor absorbs sunlight, it knocks electrons loose. An electrical field directs these loose electrons into an electric current, flowing in one direction in electrical circuit.

Machine Learning Algorithms play an important role in this field. We can analyse earth’s latitude and longitude data for proper location selection for setup of solar power plant where solar panels are installed. With the help of machine learning algorithm, we can build a model for proper selection of places where we can find the maximum intensity of sunlight most of the day over the year. The prediction of solar energy can be addressed as a time series prediction problem using historical data. Also, solar energy forecasting can be derived from numerical weather prediction models.

For business point of view, big companies are spending money on tracking, monitoring and evaluating data from solar projects worldwide, helping to lower the cost of generating energy from the sun.

If we talk about wind energy, it is a clean and free renewable energy source. Each day around the world, wind turbines are capturing wind’s power and converting it to electricity.

Wind energy is plentiful, readily available and capturing its power does not deplete our valuable natural resources. In fact, wind turbines can help to counter the detrimental effects of climate change.

Wind farms have become an important source of carbon-free electricity as the cost of turbines has plummeted and adoption has surged. However, the variable nature of wind itself makes it an unpredictable energy source less useful than one that can reliably deliver power at a set time.

In search of a solution to this problem, last year, DeepMind and Google started applying machine learning algorithms to 700 megawatts of wind power capacity in the central United States. These wind farms, part of Google’s global fleet of renewable energy projects, collectively generate as much electricity as is needed by a medium-sized city. Using a neural network trained on widely available weather forecasts and historical turbine data, we configured the DeepMind system to predict wind power output 36 hours ahead of actual generation. Based on these predictions, our model recommends how to make optimal hourly delivery commitments to the power grid a full day in advance. This is important, because energy sources that can be scheduled (i.e. can deliver a set amount of electricity at a set time) are often more valuable to the grid. To date, machine learning has boosted the value of our wind energy by roughly 20 percent, compared to the baseline scenario of no time-based commitments to the grid.

We can’t eliminate the variability of the wind, but our early results suggest that we can use machine learning to make wind power sufficiently more predictable and valuable. This approach also helps bring greater data rigour to wind farm operations, as machine learning can help wind farm operators make smarter, faster and more data-driven assessments of how their power output can meet electricity demand.

In field of Geothermal energy, Machine learning uses advanced algorithms to identify patterns in and make inferences from data, could assist in finding and developing new geothermal resources. If applied successfully, machine learning could lead to higher success rates in exploratory drilling, greater efficiency in plant operations, and ultimately lower costs for geothermal energy.

So, new technologies like machine learning used to scale-up the production of renewable sources of energy. If we use more renewable sources of energy than dependency of non-renewable sources of energy should be decreased which will ultimately help to reduce global warming to a lot of extent and make this planet a better place to live.