Award Value: $250,000
City, State: Exeter, NH

Achyuta Rajaram, 17, of Exeter, improved automatic discovery of visual circuits for the computer science project that he submitted to the Regeneron Science Talent Search. In machine learning, computer algorithms find patterns in data to answer important, practical questions. Achyuta’s research improved our ability to discover what computer models, that find patterns in images, are ‘thinking’ when they analyze a photo and which parts of their ‘mechanical brains’ are contributing to the decision making. For example, when a model identifies a car in a photo, does it first identify wheels and use this to identify ‘car-ness,’ or does it look for something else? Achyuta’s key contribution to this effort was to develop an automatic method for recognizing which parts of the algorithms identify what. This knowledge sheds light on what these algorithms are ‘thinking,’ which can help make them more effective, fair, and safe.

Award Value: $175,000
City, State: Ossining, NY

Thomas Yu-Tong Cong investigated the rapid growth of certain cancers and whether information controlling metabolism is primarily controlled by the expression of genetic information as is widely assumed. He found that immune cancers have pronounced differences in metabolism and gene expression, which suggests that a more complex landscape of metabolic variation exists and gives further insight into cancer studies. Thomas Yu-Tong Cong, 17, of Ossining, researched the rapid growth of certain types of cancers and wondered whether information needed to control metabolism is primarily conveyed by expression of genes for his Regeneron Science Talent Search computational biology and bioinformatics project. For drug developers, metabolic pathways have traditionally been a prime target, so Thomas aimed to evaluate that premise and found it questionable.

Award Value: $150,000
City, State: San Jose, CA

Michelle Wei, 17, of Saratoga, improved second-order cone programming (SOCP) solvers for her Regeneron Science Talent Search mathematics project. All of math is about problem solving, but the field of optimization is about how to solve problems quickly. Michelle studied SOCP problems, an important topic in convex programming, a field that helps optimize company supply chains, schedule airline flights, and distribute electrical power. Because these problems are so common and critical, understanding how to solve them more quickly is important — and that’s exactly what Michelle did.

Award Value: $100,000
City, State: Gainsville, FL

Nathan Wei, 17, of Gainesville, synthesized an ultra-high molecular weight (UHMW) plastic for his Regeneron Science Talent Search chemistry project. UHMW polymers have the advantage of enhanced strength and durability but are more difficult to produce. However, Nathan demonstrated that a UHMW polymer could be created under blue light with much lower energy requirements by incorporating pentafluorostyrene into the polymer.

Award Value: $90,000
City, State: Saratoga, CA

Zeyneb N. Kaya, 17, of Saratoga, improved resources for machine learning models to help preserve endangered languages for her Regeneron Science Talent Search computer science project. Today’s natural language processing (NLP) algorithms, like ChatGPT, work well for languages like English because it has a lot of easily accessible text to learn from. For languages with less accessible text, Zeyneb wrote her own algorithm, called MADLIBS, that generates additional text, which, in turn, allows subsequent NLP algorithms to work better. The key insight was to get more mileage out of the limited existing resources of each language dataset by generating appropriate translation pairs to make grammatically correct sentences and create high-quality translations. Among the endangered languages she investigated was the Māori language from New Zealand. She hopes one day her MADLIBS software will be an open-source resource for people around the world.

Award Value: $80,000
City, State: Irvington, NY

Christopher Zorn, 17, of Irvington, studied how RET, a gene involved in cellular signals, and the MYC genes, which regulate cell growth and death, affect one another in genetically modified lung cancer cells for his Regeneron Science Talent Search medicine and health project. RET commonly fuses with other genes and leads to many types of tumor development. Christopher created multiple lung cancer cell lines with different RET gene fusion combinations, introduced various chemical agents, and then measured the resulting MYC protein levels. He found the MYC levels were elevated in most of the cell lines, and often led to treatment resistance. He believes his work merits further research on the relationship between RET and MYC, the mechanism that leads to treatment resistance, and potentially targeting RET and MYC together for future treatments.

Award Value: $70,000
City, State: Oviedo, FL

Ella Pilacek, 17, of Winter Springs, researched Pavlovian conditioning of honeybees as a way of promoting pollination of the endangered native orchid Prosthechea cochleata for this Regeneron Science Talent Search animal sciences project. Seeking to address the problem of habitat fragmentation and a lack of native pollinators, Ella investigated how to train non-native honeybees (Apis mellifera) to pollinate the endangered orchid. After testing each of the flower’s volatile organic compounds, Ella used them in a synthetic version of the orchid’s scent, mixed with sucrose as a food reward. After five rounds of conditioned feeding, the experimental group of bees were significantly more attracted to the orchid’s scent, showing the possibility of using synthetic scents to train non-native pollinators to help conserve endangered native plant species.

Award Value: $60,000
City, State: Annandale, NJ

Selina Zhang, 18, of Annandale, designed and field tested a synthetic, eco-conscious, A.I.-powered tree that uses machine learning to selectively lure and “zap” the invasive spotted lanternfly (SLF) for her Regeneron Science Talent Search environmental science project. Found in large numbers, with few known predators, SLFs annually cause a tremendous amount of damage to agriculture. Selina’s ArTreeficial tree, made from an umbrella, lures the insects using an incense she made from the SLF’s favorite tree, the tree of heaven, also an invasive species. She used A.I. to first identify the SLF and then energize an electric mesh to kill them. The entire system is solar-powered. Selina’s prototype tree costs just under $200 to construct, but she believes large-scale production could dramatically reduce the cost. She is also researching ways to improve her attractant using an essence from dead SLFs.

Award Value: $50,000
City, State:  Cupertino, CA

Arnav N. Chakravarthy, 18, of Sunnyvale, investigated how macrophage cells replenish in aging humans for his Regeneron Science Talent Search cellular and molecular biology project. A macrophage is a type of immune system cell that’s important for the body’s inflammatory response and cleanup. It is believed these cells originate during fetal development, but recent studies suggest that macrophages may also develop from bone marrow as we age. Arnav hypothesized that a type of brain macrophage called microglia may also replenish in this manner. To test this theory, Arnav used a genomics tool to trace the origins of brain and liver samples alongside bone marrow samples from the same donors and compared the cell’s lineage and unique mutations. His findings show promise for the regenerative possibilities of macrophage cells, including those that affect age-related diseases like Alzheimer’s.

Award Value: $40,000
City, State:  Exeter, NH

Alan Bu, 17, of Glenmont, New York, made connections between graph theory and linear algebra for his Regeneron Science Talent Search mathematics project. Alan’s project provides precise limits on the number of spanning trees a planar graph, a graph in which no edges cross each other, can have. A spanning tree is a minimal selection of edges that connects all the objects in a graph. Mathematical graphs are used to represent and study objects and how they relate to each other, such as how molecules form lattices in solids. Knowing the number of spanning trees of a graph gives important insights into its structure, which can then be used in applications. Previous work had estimated this number, but Alan made these estimates much more precise. His key insight was to connect the number of spanning trees to a linear algebra problem, a different field of math concerned with matrices.