Yuntao Mao

Dr. Yuntao Mao

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
18 March 2024 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
YMYuntao Mao
Yuntao Mao
ZCZiwei Chen
Ziwei Chen
SLSiyuan Liu
Siyuan Liu
Yanfeng LiYanfeng Li
Yanfeng Li

25 October 2025 in Applied Soft Computing
Verified
Journal Article
Closed access
JXJianan Xu
Jianan Xu
YMYuntao Mao
Yuntao Mao
LWLichun Wang
Lichun Wang

10 February 2026 in Ocean Engineering
Verified
Journal Article
Closed access
CYChunyang Yu
Chunyang Yu
YMYuntao Mao
Yuntao Mao
DLDengke Liu
Dengke Liu
ZCZiwei Chen
Ziwei Chen

19 January 2024
Verified
Conference Paper
Open access
YMYuntao Mao
Yuntao Mao
JZJinwei Zhu
Jinwei Zhu
ZCZiwei Chen
Ziwei Chen
YLYou Li
You Li
ZDZiyang Deng
Ziyang Deng
Predicting urban carbon emissions has a significant impact on sustainable development. We introduce two types of deep learning models based on spatio-temporal (ST) encoding and simplify both architectures to forecast the carbon emissions of nine districts in Beijing. The models include the innovative multi-time prediction model, STID, and the advanced MLP architecture integrating with ST encoding, ST-MLP. The results indicate that ST-MLP performs best. The ST structure greatly enhances the performance of the conventional MLP. The ST-MLP demonstrates certain advantages in predicting urban carbon emissions compared to other complex models. Additionally, the STID surpasses some traditional prediction models and achieves second place behind the ST-MLP. Keywords: Urban Carbon Emission, Deep Learning, Spatio-Temporal Encoding, MLP

Verified
Journal Article
Open access
PDF file
HGHaowen Ge
Haowen Ge
YLYing Li
Ying Li
YMYuntao Mao
Yuntao Mao
JLJian Li
Jian Li
ZCZiwei Chen
Ziwei Chen
XPXueming Peng
Xueming Peng
Given the central importance of maritime logistics to global trade, accurate and efficient vessel motion forecasting is essential for strengthening supply chain resilience and improving operational efficiency. However, traditional physical and statistical models often fail to effectively capture the multivariate, noisy, and strongly coupled nature of maritime dynamics. In this manuscript, we adapt the DSformer architecture for ship motion forecasting, leveraging its dual sampling and dual-attention design to address the multi-scale and cross-variable dependencies inherent in maritime data. Across three real-world datasets, the adapted DSformer reduces prediction error by 23% and training time by 70% compared with 13 state-of-the-art (SOTA) baselines. Moreover, we identify a consistent relationship between sampling strategies and sea states, where dense sampling performs best under stable conditions, whereas moderately sparse sampling with multi-head attention improves robustness under turbulent environments. These results apply the algorithm’s new capabilities to the daily management of maritime logistics. By adapting the architecture to real-world operational settings and optimizing its key parameters, the approach enables efficient, real-time vessel forecasting and decision support across global supply chains.

22 October 2025 in Advances In Space Research
Verified
Journal Article
Closed access
YMYuntao Mao
Yuntao Mao
HGHaowen Ge
Haowen Ge
ZCZiwei Chen
Ziwei Chen
TMTian Mao
Tian Mao
YWYungang Wang
Yungang Wang