Predictive modeling for levelized cost of green ammonia

Ayşe Özmen and Szu Hui Ng

Applied Energy, 2025, vol. 398, issue C, No S0306261925011298

Abstract: The cost is a vital consideration in the execution of any effective initiative, including the integration of new technology or the utilization of more sustainable materials. In ammonia production, machine learning (ML)-driven models have been used for some fields, such as the prediction of ammonia synthesis and levelized cost of energy (LCOE). However, ML-driven models have not been applied to directly predict the levelized cost of ammonia (LCOA). This paper introduces different kinds of predictive models that can forecast the cost of producing green ammonia using many kinds of ML algorithms. We employ a dataset from a techno-economic (TE) model to develop predictive models for LCOA. We represent the models as useful surrogates for an existing TE model. This study considers interpretable supervised ML models, which provide explicit formulations and coefficients for the prediction of LCOA. We also employ neural network-based and ensemble-based supervised learning models (SML) for comparison, despite their lower interpretability. These statistical ML models can offer investors and suppliers enhanced transparency and simplicity in estimating the production cost of green ammonia. Different sectors can readily understand and utilize these models to estimate LCOA. Our analysis indicates that, based on modeling and prediction, the multivariate adaptive regression splines (MARS) model performs better than other proposed models for LCOA in terms of the worst-case analysis and the average measures. This study also conducted a sensitivity analysis, which can provide information on the factors that are most sensitive to estimating LCOA and have a significant impact, including making decisions before investing.

Keywords: Decarbonization; Green ammonia; Supervised machine learning; Regression models; Forecasting; LCOA (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261925011298
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:398:y:2025:i:c:s0306261925011298

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2025.126399

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().