Machine learning to forecast electricity hourly LCA impacts due to a dynamic electricity technology mix

Portolani, Pietro; Vitali, Andrea; Cornago, Simone; Rovelli, Davide; Brondi, Carlo; Low, Jonathan Sze Choong; Ramakrishna, Seeram; Ballarino, Andrea

doi:10.3389/frsus.2022.1037497

Cited by 7 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Hourly forecast of electricity LCA using machine learning considering dynamic electricity technology mix (Portolani et al, 2022). • Use of machine learning to find design aspects of buildings that provide an optimized LCSA score (Amini Toosi et al, 2022).…”

Section: Digitalization and Automation Techniquesmentioning

confidence: 99%

Life cycle inventory analysis modelling in LCSA: from basic aspects to advanced techniques

Schaubroeck,

Benetto

2024

Handbook on Life Cycle Sustainability Assessment

View full text Add to dashboard Cite

Section: Digitalization and Automation Techniquesmentioning

confidence: 99%

Life cycle inventory analysis modelling in LCSA: from basic aspects to advanced techniques

Schaubroeck,

Benetto

2024

Handbook on Life Cycle Sustainability Assessment

View full text Add to dashboard Cite

“…However, for certain unknown data points, modeling might be needed to obtain them. For example, if the exact electricity mix is unknown at the considered point in time, one can use models for a price change or even machine learning, as exemplified in the following article published in this journal (Portolani et al, 2022). If such modeling is needed in the background, many decisions that have shaped the world may need to be considered.…”

Section: Figurementioning

confidence: 99%

Relevance of attributional and consequential life cycle assessment for society and decision support

Schaubroeck

2023

Front. Sustain.

View full text Add to dashboard Cite

Life cycle assessment (LCA) is an essential tool for assessing the environmental impact of product systems. There are two main types: attributional LCA (ALCA), which assesses the global impact share of a product's life cycle, and consequential LCA (CLCA), which evaluates the consequential impact of a decision. In our analysis, we explored the relevance of these types for society and their ability to aid decision-making. This analysis builds upon existing literature and incorporates two ideological and three pragmatic criteria. First, when it comes to realistic modeling as desired in the context of sustainable development, in theory, CLCA attempts to model realistically, whereas ALCA falls short to a certain degree because of conceptual rules, e.g., artificial splitting of co-product processes. Concerning the second criterion of alignment with ethics, CLCA completely aligns with consequential ethics, where an action is judged based on its consequences. This alignment of CLCA makes it undoubtedly relevant in a world where we aim to obtain favorable consequences in the future, e.g., meeting sustainability goals. ALCA is only partially consequential, as it is restricted by conceptual rules relating to deontological ethics and, for example, covers the relative past of the product. Since deontological ethics, i.e. judging an action based on its alignment with rules, is generally relevant for our modern human society, there is room for complementarity in ethical relevance between ALCA and CLCA. However, the conceptual rules of ALCA (e.g., additivity) and their relevance have not been accepted by society. As a result, ethical acceptance of ALCA is still required. In the context of decision support, CLCA evaluates the consequences of decisions, while ALCA encompasses the approval and sharing of potential responsibility for the environmental impact throughout the life cycle of the product associated with the decision. We also highlight the unique valorization of Organizational ALCA, which entails the aforementioned aspects for the organizations responsible for the product. Concerning the three practical criteria, the following conclusions were drawn. Although ALCA has received the most attention in terms of standards, only CLCA can currently be consistently conducted in a reliable manner. This is because the current life cycle impact assessment methods applied in ALCA do not yet partition environmental multi-input processes. CLCA should be given greater prominence in standards. Furthermore, the complexity and uncertainty associated with modeling may often be only slightly higher for CLCA than for ALCA, mainly due to the consideration of change resulting from a decision. However, both ALCA and CLCA modeling may be similarly complex and have equally high levels of uncertainty as both methods encompass past and/or future projections (e.g., prediction of future background processes). Finally, ALCA modeling may be viewed as a practical approximation of CLCA, but the current CLCA models are more suitable for studying consequential effects. As CLCA modeling and databases continue to improve, this distinction will become even more pronounced.

show abstract

“…Using natural language processing (NLP) and random forest algorithms to train models to provide quick predictions for LCA practitioners and testers in implementing LCA, Similar things have been analyzed to predict the impact of LCA on electricity consumption. Comparing feed-forward (NN) neural networks and repetitive neural (RNN) networks, although limited to one data set (Ghoroghi et al, 2022), (Koyamparambath et al, 2022), (Portolani et al, 2022).…”

Section: Literature Reviewmentioning

confidence: 99%

Optimizing Sustainability: A Deep Learning Approach on Data Augmentation of Indonesia Palm Oil Products Emission

Tahyudin,

Tikaningsih,

Suryana

et al. 2023

Preprint

View full text Add to dashboard Cite

Life Cycle Assessment (LCA) is a widely used methodology for quantifying the environmental impacts of products, including the carbon footprint. However, conducting LCA studies for complex systems, such as the palm oil industry in Indonesia, can be challenging due to limited data availability. This study proposes a novel approach called the Anonymization Through Data Synthesis (ADS-GAN) based on a deep learning approach to augment carbon footprint data for LCA assessments of palm oil products in Indonesia. This approach addresses the data size limitation and enhances the comprehensiveness of carbon footprint assessments. An original dataset comprising information on various palm oil life cycle stages, including plantation operations, milling, refining, transportation, and waste management. The number of original data is 195 obtained from the Sustainable Production Systems and Life Assessment Research Centre of Indonesia's National Innovation Research Agency (BRIN). To measure the performance of prediction accuracy, this study used regression models: Random Forest Regressor (RFR), Gradient Boosting Regressor (GBR), and Adaptive Boosting Regressor (ABR). The best-augmented data size is 1000 data. In addition, the best algorithm is the Random Forest Regressor, resulting in the MAE, MSE, and MSLE values are 0.0031, 6.127072889081567e-05, and 5.838479552074619e-05 respectively. The proposed ADS-GAN offers a valuable tool for LCA practitioners and decision-makers in the palm oil industry to conduct more accurate and comprehensive carbon footprint assessments. By augmenting the dataset, this technique enables a better understanding of the environmental impacts of palm oil products, facilitating informed decision-making and the development of sustainable practices.

show abstract

Machine learning to forecast electricity hourly LCA impacts due to a dynamic electricity technology mix

Cited by 7 publications

References 32 publications

Life cycle inventory analysis modelling in LCSA: from basic aspects to advanced techniques

Life cycle inventory analysis modelling in LCSA: from basic aspects to advanced techniques

Relevance of attributional and consequential life cycle assessment for society and decision support

Optimizing Sustainability: A Deep Learning Approach on Data Augmentation of Indonesia Palm Oil Products Emission

Contact Info

Product

Resources

About