Proxy Chemical Selection for Life Cycle Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Life cycle assessment (LCA) practitioners face challenges in accurately estimating inputs and outputs for synthetic chemicals, as only a small number of these chemicals have thoroughly quantified data, leading to laborious and variable selection of proxy chemicals.
Innovation Solution
The use of retrosynthetic data and machine learning-assisted proxy chemical selection to automate the determination of life cycle inventories (LCIs), where a computing system processes chemical structures to identify primary and ancillary chemicals, and selects proxy chemicals with available LCI data for estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual selection of proxy chemicals is used, then LCA practitioners can estimate inputs and outputs for non-qualified synthetic chemicals, but the process becomes laborious and time-consuming
Solution Approach 1:
The patent replaces the manual mechanical process of proxy chemical selection with an automated computational system. The system uses machine learning models trained on chemical structure data to automatically identify and select appropriate proxy chemicals, eliminating the need for manual labor while maintaining or improving selection accuracy.
Solution Approach 2:
The system enables self-service by allowing the computational algorithm to autonomously perform the entire proxy chemical selection process without human intervention. The machine learning model independently analyzes chemical structures, compares them against database entries, and selects the most appropriate proxies based on structural similarity metrics.
2Measurement precision
If manual selection of proxy chemicals is used, then LCA practitioners can estimate inputs and outputs for non-qualified synthetic chemicals, but the selection becomes variable depending on practitioner knowledge
Solution Approach 1:
The patent transforms the subjective parameter of practitioner chemistry domain knowledge into an objective computational parameter. The system uses quantifiable chemical structure descriptors and similarity metrics to consistently evaluate and compare chemicals, replacing variable human judgment with reproducible algorithmic assessment based on structural parameters.
Solution Approach 2:
The patent replaces the variable human decision-making process with a consistent computational system. The machine learning model applies the same selection criteria and algorithms to all chemical queries, ensuring uniform and reproducible results regardless of which practitioner uses the system.
3Measurement precision
If thorough quantification of inputs and outputs is performed for all synthetic chemicals, then accurate LCA data is obtained, but the complexity and resource requirements increase significantly
Solution Approach 1:
The patent introduces proxy chemicals as intermediaries between the target chemical and the LCA database. Instead of requiring complete quantification data for every synthetic chemical, the system uses structurally similar proxy chemicals with known data to estimate inputs and outputs, thereby reducing the burden on the LCA database while maintaining estimation accuracy.
Solution Approach 2:
The patent applies partial action by thoroughly quantifying only a representative subset of chemicals (the proxies) rather than all possible synthetic chemicals. This selective approach provides sufficient data coverage through structural similarity, avoiding the excessive resource requirements of complete quantification while achieving practical accuracy for estimation purposes.
Data Source
AI summary
A computing system is provided. The computing system comprises a processor, and memory comprising instructions executable by the processor to receive a chemical structure input, obtain retrosynthetic step data based on the chemical structure input, determine a chemical structure of a primary chemical in the retrosynthetic step data, the primary chemical being a chemical used as a starting material in a retrosynthetic step, when the structure of the primary chemical is not available in a life-cycle inventory (LCI), input the primary chemical into a trained proxy chemical selection model to select a proxy chemical for which an LCI is available, and obtain proxy chemical LCI data to include in an estimated LCI for a life cycle assessment (LCA).