Jinyong (Edward) Sung

Jinyong (Edward) Sung

Auto-generated profile, based on publicly available information

Jinyong (Edward) Sung

Institute for Sustainable Futures, University of Technology Sydney (UTS) Sydney Australia

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

2 June 2026 in Resources Policy
Verified
Journal Article
Open access
JSJinyong Sung
Jinyong Sung
Xunpeng ShiXunpeng Shi
Xunpeng Shi
STSven Teske
Sven Teske
MLMengheng Li
Mengheng Li

1 January 2026 in International Journal of Energy Research
Verified
Journal Article
Open access
PDF file
JSJinyong (Edward) Sung
Jinyong (Edward) Sung
Xunpeng ShiXunpeng Shi
Xunpeng Shi
Sven TeskeSven Teske
Sven Teske
MLMengheng Li
Mengheng Li
China’s natural gas (NG) consumption is expected to grow in the short and medium term under the country’s carbon neutrality policy, but this growth is accompanied by increasing uncertainty driven by geopolitical developments and ongoing market liberalisation. This highlights the need for accurate demand forecasting. This study proposes a hybrid forecasting framework that integrates the Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SARIMAX) model and the Long short‐term memory (LSTM) neural network through an artificial neural network (ANN). The analysis focuses on 1‐year‐ahead forecasting of China’s NG consumption at the national level using monthly data from April 2009 to July 2023. Eight key drivers reflecting market, economic, and infrastructure conditions are incorporated as model inputs. Forecasting performance is evaluated using out‐of‐sample R‐squared ( R 2 ), root mean square error (RMSE) and mean absolute error (MAE). The results demonstrate that the ANN‐optimised SARIMAX–LSTM hybrid model with a trend‐capturing function achieves the highest predictive accuracy, with an R 2 of 47.94%, RMSE of 5.23 and MAE of 1.70. This superior performance is further supported by the model’s lowest cumulative squared forecast error (CSFE), confirming its robustness and consistency in predictive performance. In addition, principal component analysis (PCA) confirms the validity of the selected input drivers and identifies NG‐related infrastructure variables as the most influential factors in near‐term forecasting. These findings provide robust evidence for the effectiveness of hybrid modelling in short‐term energy demand forecasting and offer practical implications for policy design, investment planning, and operational decision‐making in the context of China’s carbon‐neutral energy transition.

28 July 2026 in Sustainable Development
Verified
Journal Article
Open access
JSJinyong (Edward) Sung
Jinyong (Edward) Sung
A major transformation in China's energy mix is underway as the country pursues carbon neutrality by 2060, posing significant structural challenges for Australia as a major exporter of carbon‐intensive resources. This study examines the economic impacts of China's decarbonisation on Australia by applying static and dynamic input–output (IO) models using the Environmentally Extended Multi‐Regional Input–Output Database (EXIOBASE). Addressing a gap in the literature on bilateral spillover effects and policy‐responsive modelling, the study introduces a modular dynamic IO framework incorporating competing natural gas and renewable energy stimulus scenarios. The results show that China's decarbonisation negatively affects Australia's resource and mineral export sectors, with substantial inter‐industry propagation effects. While Australia's current gas‐focused policies generate limited economic benefits, with peak output increases of approximately 0.0075, its renewable energy–based stimulus yields significantly higher peak output increases of around 0.02, alongside broader spillover effects. This study contributes by developing a flexible and policy‐adaptive framework for analysing cross‐country energy transitions and their economic effects. The findings highlight the need for Australia to transition away from its carbon‐intensive export structure and accelerate investment in renewable energy industries to sustain long‐term economic resilience and competitiveness amid China's energy transition.