This interactive, AI-powered platform delivers risk-weighted material assessments, enabling safer, more resilient, and sustainable construction decisions. Material failure accounts for roughly 20-25% of home damage during natural disasters, costing millions of dollars each year in cleanup and repair. Conventional statistical models for material selection work well for short-term forecasting but rely on the assumption of past patterns reliably predicting future outcomes. However, because these models fail to capture complex interdependencies among variables, they can produce biased or misleading assessments. Consequently, designers and builders lack a dependable tool for evaluating material performance against environmental hazards. The global sustainable materials market is valued at over $375 billion in 2025 and is expected to increase to $1.078 trillion by 2034. This lack of a reliable assessment tool, combined with rising demand for resilient materials, creates a clear need for a novel, improved platform.
Resilience engineering research from the Florida Institute for Built Environment Resilience (FIBER) demonstrated that interior materials, smart home technologies, and hazard exposures interact in complex ways that traditional checklist-based tools cannot capture. The Resilience Inference Performance Level (RIPL) report identified a need for a dynamic material intelligence platform that evaluates materials before failure occurs, creating a continuous chain of evidence from specification through post-disaster remediation. Neither the AEC industry nor the property insurance market currently has a practical forecasting tool to quantify material performance under hazard stress at the product level, limiting their ability to price resilience and guide material selection decisions.
Researchers at the University of Florida developed the Sustainable Adaptive Material Performance Level (SAMPL) system, an AI-powered platform for evaluating and selecting safer, more resilient building materials. SAMPL provides a visual, interactive framework that forecasts how building materials and finishes will perform under place-based environmental risks. The system allows architects, developers, and procurement professionals to compare materials using a tunable, risk-weighted evaluation model that reflects real-world hazard conditions. By enabling more informed material selection, SAMPL can improve building resilience, support safer retrofit decisions, and promote healthier and more sustainable built environments. SAMPL evaluates each material across three core dimensions: strength (technical durability, safety, and longevity), symbiosis (contextual adaptability and user-centered performance under specific risk scenarios), and sustainability (environmental and health impacts across the material’s lifecycle).
An AI-powered resilience-engineering decision-support platform that forecasts how building materials and finishes perform under context-specific environmental hazards, enabling designers, builders, regulators, insurers, and homeowners to make safer construction, retrofit, and underwriting decisions before failure occurs
SAMPL is an AI-powered, dynamic, and tunable platform that evaluates the resilience and performance of building materials used in residential construction against real-world environmental hazards. It combines data on local risk factors with material specifications to generate a risk-weighted score for each product. This score is displayed on an interactive dashboard that is customizable to specific regional climate conditions and weather hazards. The underlying AI uses fuzzy-logic inference to model complex interdependencies among variables, enabling more reliable predictions than traditional short-term statistical methods. By presenting strength, symbiosis, and sustainability ratings in a clear visual format, SAMPL helps builders, developers, and insurers identify construction and retrofit choices that improve long-term resilience.