Estimation of Unit Process Data for Life Cycle Assessment Using a Decision Tree-Based Approach

Zhao, Bu; Shuai, Chenyang; Hou, Ping; Qu, Shen; Xu, Min

doi:10.1021/acs.est.0c07484

Cited by 43 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhao et al. (2021) show how unit process data can also be estimated using machine learning. Such developments could not only benefit LCA but also input–output databases in mapping activities and products as well as their environmental extensions.…”

Section: Envisioning the Role Of Ai In Iementioning

confidence: 99%

“…For example, there are opportunities to be investigated in the conversion of domain-specific data into data useful for life cycle inventories, as shown by Mittal et al (2018) in the use of data mining to convert industrial process databases in data useful for LCI. Zhao et al (2021) show how unit process data can also be estimated using machine learning.…”

Section: Envisioning the Role Of Ai In Iementioning

confidence: 99%

See 1 more Smart Citation

The future of artificial intelligence in the context of industrial ecology

Donati

Dente

et al. 2022

J of Industrial Ecology

View full text Add to dashboard Cite

Artificial intelligence (AI) applications and digital technologies (DTs) are increasingly present in the daily lives of citizens, in cities and in industries. These developments generate large amounts of data and enhance analytical capabilities that could benefit the industrial ecology (IE) community and sustainability research in general. With this communication, we would like to address some of the opportunities, challenges, and next steps that could be undertaken by the industrial ecology community in this realm. This article is an adapted summary of the discussion held by experts in industrial ecology, AI, and sustainability during the 2021 Industrial Ecology Day conference session titled “The Future of Artificial Intelligence in the Context of Industrial Ecology.” In brief, building on previous studies and communications, we advise the industrial ecology community to: (1) create internal committees and working groups to monitor and coordinate AI applications within and outside the community; (2) promote and ensure transdisciplinary efforts; (3) determine optimal infrastructure and governance of AI for IE to minimize undesired effects; and (4) act on effective representation and on reduction of digital divides.

show abstract

Section: Envisioning the Role Of Ai In Iementioning

confidence: 99%

Section: Envisioning the Role Of Ai In Iementioning

confidence: 99%

The future of artificial intelligence in the context of industrial ecology

Donati

Dente

et al. 2022

J of Industrial Ecology

View full text Add to dashboard Cite

show abstract

“…When the learning rate is set to 0.5 and the number of center points is 2 and 3, respectively, the center points of the four attributes of the dataset are shown in Figure 7. It can be seen that there is a big difference between the four major attributes under different numbers of center points [18]. e maximum and minimum number of center points of browsertime are 7.1 and 9.58, respectively, the maximum and minimum number of center points of onlinenotes are 0.1 and 43.75, respectively, the maximum and minimum number of center points of bbspost are 25.37 and 43.85, respectively, and the maximum and minimum number of center points of test-Score are 0.57 and 43.75, respectively.…”

Section: Evaluation and Analysis Of Moocs Model In College Physical E...mentioning

confidence: 99%

Construction of College Physical Education MOOCS Teaching Model Based on Fuzzy Decision Tree Algorithm

Yang

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the continuous development of the MOOCS model in college physical education, the corresponding teaching evaluation has also been widely concerned by the community. The development of a traditional education mode in college physical education cannot meet the current teaching requirements. In order to solve the problem of narrow application and insufficient accuracy in traditional education, on the basis of the Kohonen fuzzy decision tree algorithm and the MOOCS fuzzy decision tree algorithm, a fuzzy evaluation model of P.E. teaching is proposed. The results show that the fuzzy ID3 algorithm can achieve high accuracy in the four databases, and the classification accuracy of the A-D database is 75.9%, 62.9%, 76.6%, and 95.1%, respectively. Except for database C, the classification accuracy of the minimum classification uncertainty algorithm is lower than the other two clear decision tree algorithms. Compared with the minimum classification uncertainty algorithm, the fuzzy ID3 algorithm has obvious advantages in classification rules. The classification rules of A-D database are 18, 12, 16, and 10, respectively. When the authenticity threshold is about 0.8, the fuzzy ID3 algorithm has the highest classification accuracy. The proposed MOOCS model for college physical education based on the fuzzy decision tree algorithm has strong practicability and high accuracy. This paper studies the MOOCS model of college physical education and introduces the fuzzy decision tree algorithm to evaluate the MOOCS model of college physical education. It solves the problem that traditional sports cannot satisfy the needs of “Internet plus education” at all. Compared with the traditional sports model, it has better applicability and higher accuracy.

show abstract

“…There are many developments on different knowledge-based and data-driven simulation approaches to estimate life cycle inventories, such as missing inventory estimation tool (MIET), artificial neural networks (ANN), , bill of materials (BOM), and unit process data. , However, there are limitations with these methods. More specifically, MIET suffers from data aggregation, relying on the national input–output tables with respect to input requirements; in this way, the inventory data suffers from scarce accuracy .…”

Section: Introductionmentioning

confidence: 99%

“…List of LCA Studies on PVDF Applied in Emerging Technologies (Note: several methods that have been proposed to address data gaps include (1) new data collection, 17 (2) creation of aggregated datasets, 17 (3) extrapolated data, 18 (4) proxy or surrogate data, 18,19 (5) estimate gate-to-gate life cycle information via engineering process techniques, 20 (6) estimate inventory through the use of stoichiometric equations, 20 (7) purchase from commercial LCA databases, 21 (8) estimate LCI using a generic input−output scheme for product production, with parameter values derived from on-site data and heuristics; 22 There are many developments on different knowledge-based and data-driven simulation approaches to estimate life cycle inventories, such as missing inventory estimation tool (MIET), 38 artificial neural networks (ANN), 39,40 bill of materials (BOM), 41 and unit process data. 42,43 However, there are limitations with these methods. More specifically, MIET suffers from data aggregation, relying on the national input−output tables with respect to input requirements; in this way, the inventory data suffers from scarce accuracy.…”

Section: ■ Introductionmentioning

confidence: 99%

Life Cycle Assessment of the Polyvinylidene Fluoride Polymer with Applications in Various Emerging Technologies

Chopra

2022

ACS Sustainable Chem. Eng.

View full text Add to dashboard Cite

Polyvinylidene fluoride (PVDF) is one of the most popular fluoropolymers in the market. It is commonly used as pipes and cables, binder materials, and membrane materials. Lately, PVDF is being examined for applications in batteries, biomedical research, chemical engineering, and wastewater management. These PVDF applications cover most emerging technologies, which can be attributed to its outstanding physicochemical properties. With the global demand for PVDF in diverse technologies increasing significantly, it is imperative to quantify the environmental impacts associated with its production. Life cycle assessment (LCA) methodology is a standardized approach for evaluating the environmental impacts of novel materials. However, most previous LCA studies have not accounted for PVDF in a scientifically rigorous manner. While compiling the life cycle inventory (LCI) on PVDF, several kinds of surrogates were chosen to bridge the data gap, rather than establishing the new dataset for PVDF. When we investigate the similarities and differences between PVDF and popular surrogates regarding the synthesis pathways, adopting surrogates to replace PVDF becomes difficult. Due to the use of these surrogates, the global warming potential (GWP) calculated in the literature varies significantly, with a difference of 60.7 kg CO 2 equiv between the highest and lowest estimates. After evaluating the life cycle environmental profiles of those commonly used surrogates, we find that the application of surrogates is hardly reliable; besides, the PVDF inventory dataset is underestimated. For this reason, we model the PVDF production process according to the commercialized synthesis approach and assess the cradle-to-gate impacts, which lowers uncertainty. The impact assessment on the PVDF inventory dataset results in an acceptable GWP value (55.8 kg CO 2 equiv/kg PVDF), but a high cumulative energy demand (CED, 756 MJ equiv/kg PVDF), due to the large demand for chlorine during the production of vinylidene fluoride (VDF). In terms of uncertainty analysis, the upper and lower bounds for the newly developed LCI dataset for PVDF are 801 and 714 MJ equiv for CED values and 59.1 and 52.8 kg CO 2 equiv for GWP values, respectively. Notably, this is the first study to develop a detailed LCI for PVDF involved in emerging technologies.

show abstract

Estimation of Unit Process Data for Life Cycle Assessment Using a Decision Tree-Based Approach

Cited by 43 publications

References 31 publications

The future of artificial intelligence in the context of industrial ecology

The future of artificial intelligence in the context of industrial ecology

Construction of College Physical Education MOOCS Teaching Model Based on Fuzzy Decision Tree Algorithm

Life Cycle Assessment of the Polyvinylidene Fluoride Polymer with Applications in Various Emerging Technologies

Contact Info

Product

Resources

About