Gaussian Process Regression as a Replicable, Streamlined Approach to Inventory and Uncertainty Analysis in Life Cycle Assessment

Abstract

Life cycle assessment plays a critical role in quantifying environmental impacts, but its credibility remains challenged when data and uncertainty analysis are lacking. In this study, we propose a data compilation framework to address these two issues. The framework first quantifies the correlations of production activities among existing data in temporal, geographical, and taxonomic dimensions. The framework then introduces covariance functions to convert these correlations to a similarity matrix, and the Gaussian process regression model is adopted to predict new data based on these covariance functions. The associated uncertainty is automatically characterized using the posterior distribution of predictions. The framework is demonstrated on the nitrogen fertilizer application rate for food productionan activity recognized for its environmental burdenwith results capable of reflecting temporal and geographical variations. By introducing the concept of phylogenetic distance as a correlation of taxonomy, the framework provides a quantitative basis for predictions in a proxy data usage scenario. The framework can be used in developing temporally and regionally representative life cycle inventories and databases and can facilitate consistent uncertainty quantification in future life cycle assessment methodologies.

The life cycle land use of natural gas-fired electricity in the US Western interconnection

“…How to properly quantify the effect of future technological advancement on the environment also needs investigations on the relationship between time and technology, especially when technological renovation happens. Existing frameworks often only consider the consistency between inventory and the technology being used or regard time as a proxy of technological improvement 67 while studies that consider technological improvement leading to a difference in the magnitude of an order or larger are rarely seen.…”

Land Resources for Wind Energy Development Requires Regionalized Characterizations

“…Such information has implications for life cycle assessment (LCA)�a cradle-to-grave analysis of the environmental burdens of products and processes�which mainly relies on background literature or limited inventories to quantify land impacts. 33 LCA has been advancing in its capacity to incorporate spatiotemporal information into environmental impact methods for land, 34,35 which have been challenged by the lack of spatially explicit inventories. 36,37 More recently, a life cycle inventory for all power plants in the United States has been developed; yet, spatially explicit land-use data remains limited.…”

“…Our approach and results will be a stepping stone to regionalized environmental impact assessments by providing a solid base for the evaluation of the land-use impacts in areas with varying levels of human development. Such information has implications for life cycle assessment (LCA)a cradle-to-grave analysis of the environmental burdens of products and processeswhich mainly relies on background literature or limited inventories to quantify land impacts . LCA has been advancing in its capacity to incorporate spatiotemporal information into environmental impact methods for land, , which have been challenged by the lack of spatially explicit inventories. , More recently, a life cycle inventory for all power plants in the United States has been developed; yet, spatially explicit land-use data remains limited. , Impact assessments for wind energy development on ecosystems, landscape, and ecosystem services also require spatially explicit data and high resolution maps. − …”

Resource environment load prediction method for metal material machining based on process condition similarity matching

“…(Warguła et al, 2022). Therefore, the secondary data without considering specific process conditions is unsuitable for accurate environmental impact assessment for the actual metal machining process (Dai et al, 2022).…”