Notre Dame junior wins Grand Award at metro Detroit science fair; looks forward to getting Ph.D in college.
Malini Mukherji, a Notre Dame junior, center, is with science teacher Jocelynn Yaroch and NDP principal Fr. Joe Hindelang, s.m., after she was honored March 30 for her science fair award.
Mukherji’s Grand Award was one of only seven given out in the senior division of the annual science fair, which hosted more than 2,000 competitors from 142 Michigan schools in Wayne, Oakland, Macomb, Washtenaw, Lenawee, Livingston and Monroe counties. As a result of winning the award, she will be attending the Intel International Science and Engineering Fair in Los Angeles in May.
More reliable renewables
Mukherji said her project this year was inspired by current world trends that show the reduced utilization of fossil fuels and the renewed focus on renewable sources of energy, such as solar energy. Her project specifically investigated ways to more efficiently collect solar energy by tracking the movement of the sun.
“As fossil fuels and other sources of energy are depleting, the world is turning to green energy,” Mukherji said. “A major type of green energy is solar energy and solar trackers provide an effective way to collect the sun’s energy by tilting and rotating to follow the sun’s position throughout the day. Identifying the position of the sun is important for solar trackers. These trackers often use chronological or passive systems to determine the position of a light source.”
Using machine learning, a method for computers to learn without being directly programmed, and dye-sensitized solar cells, Mukherji created an alternative method for solar trackers and other light tracking machines to identify the direction of a light source.
“This ‘smart’ light tracker can be implemented with current solar trackers and my machine learning program will allow the trackers to always know the position of the sun in real-time and in turn face the sun at the optimum angle,” she explained. “This technology can also be used in any machine that needs to identify the direction of a light source — even robots or autonomous cars.”
A more detailed summary of Mukherji's project follows:
"As fossil fuels and other sources of energy are depleting, the world is turning to green energy. A major type of green energy is solar energy. Solar trackers provide an effective way to collect the sun’s energy by tilting and rotating to follow the sun’s position throughout the day. Identifying the position of the sun is important for solar trackers. These trackers often use chronological or passive systems to determine the position of a light source. The shortcomings in these methods is that they don't account for all the various weather conditions well. Using machine learning, a method for computers to learn without being directly programmed, and dye-sensitized solar cells, I have created an alternative method for solar trackers and other light tracking machines to identify the direction of a light source. This “smart” light tracker can be implemented with current solar trackers and my machine learning program will allow the solar trackers to always know the position of the sun in real-time and in turn face the sun at the optimum angle. This technology can also be used in any machine that needs to identify the direction of a light source such as a robot or autonomous cars.
"In this project, I investigated whether variations in current caused by difference in the angle and intensity of a light incident upon solar cells can be utilized to design an “intelligent” solar panel that can predict the position of the light source. Dye-sensitized solar cells (DSSCs) were used due to the ease with which they can be fabricated at home and their responsiveness to low ambient light conditions. Several configurations of solar panels were tested, out of which a semi-spherical configuration that used five DSSCs, yielded the best inter-cell variations of short-circuit currents. The electrical response of each cell in the array was different for different locations of a source of light pointed towards this configuration. These electrical response values were recorded and the data, along with the positional information of the light source, were used to train two supervised, logistic regression machine-learning models, one for the zenith angle and one for the azimuth angle of the light source. The generated model was then used to predict the zenith (vertical) and azimuth (horizontal) angles of an incandescent light source pointed at the array. Most of the results were fairly or very accurate. The novelty of this work lies in the use of individual solar cells as the data source for machine-learning algorithms – we have found no prior work that has used machine-learning models as the tool for recording knowledge about light-source positions and subsequent real-time predictions."
In addition to her science fair accolades, Mukherji also recently learned that she was named one of the top 100 students in the latest edition of the Michigan Mathematics Prize Competition (MMPC), which is sponsored by the Michigan Section of the Mathematical Association of America (MAA).
Future college and career plans
Like most high school juniors, Mukherji is looking toward the next level of education with increasing interest.
“In college, I’d like to study materials science and engineering,” she said. “I believe future technological changes will be based on the discovery of new and improved materials. My science fair experiences of the past few years have stimulated my interest in this field. I hope to eventually get a Ph.D in it as well.”
Mukherji also has some specific career goals in mind as she hopes to someday be a materials science engineer.
Mukherji is with her project at the 60th Science and Engineering Fair of Metropolitan Detroit, which was held at Detroit’s Cobo Center.
Mukherji noted that without Notre Dame and its teachers, she probably would not have been as successful as she has over the last several years in her many competitions and events.
“One of the big motivations for me to continue my science fair projects in high school was to fulfill requirements of Notre Dame’s International Baccalaureate personal project, internal assessments in science classes, and the extended essay for the IB program,” she said. “Since the types of projects I have been doing use knowledge from many disciplines, the contributions of all of my science and math teachers have been equally important. All of those teachers continue to make learning their respective subjects fun, interesting and exciting every single day. Ms. [Jocelynn] Yaroch, for example, is one of those teachers who can really teach us in a unique style that keeps us wanting to learn more. I really appreciate that.”
Comments or questions? mkelly@ndpma.org.
Follow us on Twitter @NDPMA
About Notre Dame Preparatory School and Marist Academy
Notre Dame Preparatory School and Marist Academy is a private, Catholic, independent, coeducational day school located in Oakland County. The school's upper division enrolls students in grades nine through twelve and has been named one of the nation's best 50 Catholic high schools (Acton Institute) four times since 2005. Notre Dame's middle and lower divisions enroll students in jr. kindergarten through grade eight. All three divisions are International Baccalaureate "World Schools." The Marist Fathers and Brothers sponsor NDPMA's Catholic identity and manages its educational program. Notre Dame is accredited by the National Association of Independent Schools, the Independent Schools Association of the Central States and the North Central Association Commission on Accreditation and School Improvement. For more on Notre Dame Preparatory School and Marist Academy, visit the school's home page at www.ndpma.org.