IIT BHU | India
Author Profile
🧑🎓 Summary
Anshika Singh, a final-year B.Tech student in Civil Engineering at IIT (BHU), Varanasi, with a CGPA of 8.76. I am passionate about combining sustainable construction practices with modern technologies like machine learning to improve infrastructure systems. Through diverse internships, research projects, and leadership roles, I have developed strong skills in technical problem-solving, team collaboration, and project execution. My academic journey reflects a commitment to engineering excellence, innovation, and social impact.
🎓 Education
I am currently pursuing a B.Tech in Civil Engineering at IIT (BHU), Varanasi, with an overall CGPA of 8.76 and strong semester performances, including 9.43 in Semester VII. I completed my Class XII from Rani Laxmi Bai Memorial Inter College, UP Board, with 79.40% in 2020, and my Class X from the same school with 89.16% in 2018. My academic background has built a solid foundation in structural mechanics, transportation engineering, and geotechnical engineering.
🏗️ Professional Experience
As an intern at Gammon Engineers & Contractors Pvt. Ltd. under the NHAI project from May to July 2024, I contributed to the Varanasi Ring Road Project, particularly on a 1.47 km segmental bridge. I conducted quality tests such as Slump Cone, Sieve Analysis, and soil testing, while also learning about topographic surveys, well foundations, and pre-stressed concrete construction. This experience strengthened my understanding of on-site construction workflows and quality control systems in large-scale infrastructure.
🔬 Academic Projects
My current undergraduate project, “Leveraging AI for Affordable Pavement Performance Assessment”, involves developing a user-friendly GUI and applying ML models such as Random Forest, Decision Trees, and KNN on a dataset of 1,200 samples to predict pavement properties like CT Index and permanent strain, reducing the need for costly lab testing.
Another project, “Performance Evaluation of Sustainable Concrete”, involved testing 300+ concrete mixes with GGBS and fly ash, achieving up to 40 MPa compressive strength and a 15% reduction in water absorption, promoting eco-friendly alternatives in concrete.
In the project “Land Use/Land Cover Evolution and Forecasting in Jabalpur”, I analyzed 30 years of satellite data using a machine learning model with 98% accuracy, helping forecast future urban expansion for sustainable planning.
🛠️ Technical Skills
My technical toolkit includes AutoCAD, STAAD.Pro, MATLAB, and Python for analysis and design, as well as scikit-learn, pandas, and Tkinter for data analysis and GUI development. I am also proficient in material testing, mix design, and survey techniques, enabling me to connect software tools with real-world engineering applications.
👩🏫 Teaching Experience
As a Senior Induction Mentor in the Student Counselling Service, I helped conduct 100+ interviews, trained 25 mentors, and guided 200+ freshmen, creating a welcoming and inclusive environment for new students. I also served as the DUGC Student Representative (2023–24), where I collaborated with faculty to implement curriculum improvements, positively impacting over 800 students and initiating policy reforms for academic betterment.
🔬 Research Interest
My core research interests include sustainable construction materials, transport infrastructure design, and the use of machine learning in civil engineering. I am particularly drawn to AI-driven solutions for pavement evaluation, urban land-use forecasting, and green material innovation, aiming to bridge the gap between traditional engineering and technological advancement.
🏅 Academic Citations & Achievements
I successfully qualified GATE 2024 in Civil Engineering and received an award at the Global Road Construction Conference 2024 in Jaipur for outstanding contribution. Additionally, I was recognized for an impactful poster presentation at the Research and Innovation Day 2024 at IIT (BHU), showcasing my work in AI-integrated pavement analysis.
Publications
Data‑driven predictive models for evaluating optimum binder content and volumetric properties of bituminous mixtures using design variables, 2025