Liangqi Cheng

Liangqi Cheng

Auto-generated profile, based on publicly available information

Liangqi Cheng


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
22 April 2026 in Transportation Research Part D: Transport and Environment
Verified
Journal Article
Closed access
KLKevin X. Li
Kevin X. Li
YFYongxuan Feng
Yongxuan Feng
XBXiwen Bai
Xiwen Bai
KYKum Fai Yuen
Kum Fai Yuen
GYGuanqiong Ye
Guanqiong Ye
LCLiangqi Cheng
Liangqi Cheng

1 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
SDSirui Ding
Sirui Ding
LCLiangqi Cheng
Liangqi Cheng
XBXiwen Bai
Xiwen Bai
Maritime fleet renewal requires long-lived investment and contracting under cyclical market uncertainty. This paper develops an integrated artificial intelligence-operations research (AI--OR) framework linking data-driven market uncertainty generation with efficient long-horizon decision optimization and evaluates it through a Very Large Crude Carrier case study. For uncertainty generation, a Gaussian hidden Markov model fitted to historical freight-market index data identifies latent regimes and transitions, while regime-conditional bootstrapping samples market scenarios. Compared with stylized processes or independent sampling, this design preserves market-cycle dynamics and empirical co-movement among freight rates, vessel prices, and market availability limits. The generated scenarios provide the market environment for fleet renewal decisions. For renewal decision making, existing studies often rely on multi-stage stochastic programming solved by rolling-horizon sample average approximation (RH-SAA). However, repeated finite-horizon optimization is computationally costly and may undervalue long-lived actions with short look-ahead windows. We reformulate the problem as a finite-horizon Markov decision process with a strategic-operational decomposition and develop the Post-Decision Optimization-Decoder Reinforcement Learning (POD-RL) framework. POD-RL learns state-dependent latent valuations for post-decision fleet and contract resources, while an optimization decoder converts them into feasible high-dimensional strategic actions. In two 20-year tests under homogeneous and nonhomogeneous state transitions, POD-RL improves mean cumulative profit over RH-SAA by 16.3% and 19.1%, respectively, while reducing online decision time from over 7,000 s to 0.1-0.2 s. When deployed without retraining in a 1999-2018 historical backtest, POD-RL achieves 18.8% higher realized profit than RH-SAA. The results indicate that the integrated framework improves long-horizon decision quality.

10 June 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
SDSirui Ding
Sirui Ding
LCLiangqi Cheng
Liangqi Cheng
YLYiliang Li
Yiliang Li
XBXiwen Bai
Xiwen Bai
More than 78% of global oil trade is transported by tanker, making it essential to understand how crude-oil shipping systems respond to major disruptions. Such events affect both the exporter-importer trade market and the vessel transportation system. Because exporters,importers, and vessels are linked through cargo allocation and transport capacity, disruptionresponses are inherently coupled. Existing studies typically focus either on exporter–importertrade relationships or vessel operations, limiting their ability to capture system-level adjustment. To address this gap, we develop the Data-Calibrated Oil Market–Vessel Equilibrium Simulation (DOMES) framework, which integrates AIS and market data to reconstruct and simulate the maritime crude-oil transport system. DOMES consists of three layers: an empirical calibration layer that initializes system states from multi-source data, a cargo allocation layer that determines executable trade flows, and a vessel execution layer that performs transport operations. The framework captures the dynamic evolution of exporter cargo allocation, fleet deployment, and importer replenishment under changing market conditions. We evaluate DOMES through stable-year reconstruction, a Russia–Ukraine war disruption experiment, and Strait of Hormuz stress tests. The model reproduces observed route-level transport capacity and freight patterns with weighted absolute percentage errors of approximately 23% and captures major post-war changes in voyage distance, tanker speed, and freight pressure. Counterfactual Hormuz scenarios show that prolonged blockages mainly extend periods of elevated freight rates and longer transport distances rather than proportionally increasing peak freight levels. DOMES provides a data-calibrated tool for analyzing adjustment dynamics in disrupted maritime oil-transport networks.

6 November 2026
Verified
Book Chapter
Closed access
PDF file
LCLiangqi Cheng
Liangqi Cheng
XBXiwen Bai
Xiwen Bai
DYDong Yang
Dong Yang
This chapter uses AIS data to construct the global liner shipping network and analyze port connectivity. It begins by providing an overview of the existing indices employed by industry and academia to measure port connectivity. It then explores measuring port connectivity using AIS data, considering both port-perspective and network-perspective indicators. The chapter also applies this methodology to analyze the impact of the COVID-19 pandemic on port connectivity. It discusses the findings from the case study and presents policy implications based on the results.