TY - GEN
T1 - Life Cycle Assessment (LCA) Score Prediction Using Deep Learning on Detergent Plastic Packing Products
AU - Fatriansyah, Jaka Fajar
AU - Putri, Anisa Rahmania
AU - Hartoyo, Fernanda
AU - Pradana, Agrin Febrian
AU - Fauzi, Andrian
N1 - Publisher Copyright:
© 2023 American Institute of Physics Inc.. All rights reserved.
PY - 2023/12/15
Y1 - 2023/12/15
N2 - Life cycle assessment (LCA) is a systematic method for quantitatively analyzing the environmental impact of a product throughout the product life cycle. However, the obstacle in doing LCA is that it takes quite a lot of time to identify and register products to obtain an LCA score for the entire life of a product. One solution to overcome these limitations is to build a deep learning model to predict LCA scores on detergent plastic packaging products. The result of the research is an LCA score prediction program for detergent plastic packaging products using the eco-indicator 99 method using a total of 240 datasets consisting of 8% real/actual data, 75% dummy data, and 17% hybrid data. Other model parameters include test size 0.2, random state 6, batch size 64, with three hidden layers and density 64,32,16, epoch 1000, and learning rate 0.01. The program produces an optimum accuracy of 99.39% resulting from regression metrics using the R2 score.
AB - Life cycle assessment (LCA) is a systematic method for quantitatively analyzing the environmental impact of a product throughout the product life cycle. However, the obstacle in doing LCA is that it takes quite a lot of time to identify and register products to obtain an LCA score for the entire life of a product. One solution to overcome these limitations is to build a deep learning model to predict LCA scores on detergent plastic packaging products. The result of the research is an LCA score prediction program for detergent plastic packaging products using the eco-indicator 99 method using a total of 240 datasets consisting of 8% real/actual data, 75% dummy data, and 17% hybrid data. Other model parameters include test size 0.2, random state 6, batch size 64, with three hidden layers and density 64,32,16, epoch 1000, and learning rate 0.01. The program produces an optimum accuracy of 99.39% resulting from regression metrics using the R2 score.
UR - http://www.scopus.com/inward/record.url?scp=85180560136&partnerID=8YFLogxK
U2 - 10.1063/5.0179523
DO - 10.1063/5.0179523
M3 - Conference contribution
AN - SCOPUS:85180560136
T3 - AIP Conference Proceedings
BT - AIP Conference Proceedings
A2 - Shankar, H.
A2 - Thangaraj, P.
A2 - Mohana Sundaram, K.
PB - American Institute of Physics Inc.
T2 - 3rd International Conference on Advances in Physical Sciences and Materials: ICAPSM 2022
Y2 - 18 August 2022 through 19 August 2022
ER -
