AstraMix AI
Founder & Developer: Nikolay Khachatryan
AI-assisted sustainable concrete mix design and optimization platform.
AstraMix AI maps binder hydration chemistry using machine learning. The system predicts concrete compressive strength, estimates lifecycle environmental footprint (CO₂), and calculates raw cost variables, wrapping all predictions in a scientific validation framework.
Core Platform Tools
Strength Prediction
Run machine learning evaluations to forecast 28-day concrete strength using raw ingredients.
Mix Optimization
Search for optimal low-carbon and cost-effective mixes using our bounded SLSQP solver.
AstraMix Showcase
Explore the research positioning, model cards, offline metrics, validation reports, and roadmap.
Project Motivation
Cement manufacturing accounts for approximately 8% of global CO₂ emissions. Designing sustainable concrete requires civil engineers to replace conservative, over-dimensioned formulas with optimized binder blends. AstraMix AI couples XGBoost prediction models with SciPy solvers to explore how algorithms can support material science decisions.
Integrated Stack
Backend Core
FastAPI, Python, Pydantic, XGBoost, SciPy SLSQP
Frontend UI
Next.js 14, TypeScript, Tailwind CSS, Chart.js