https://ericjin73.github.io/news/NewsHugo Blox Builder (https://hugoblox.com)en-usMon, 14 Apr 2025 00:00:00 +0000https://ericjin73.github.io/media/icon_hu7729264130191091259.pnghttps://ericjin73.github.io/news/https://ericjin73.github.io/news/2025-04-15-website-launched/Mon, 14 Apr 2025 00:00:00 +0000https://ericjin73.github.io/news/2025-04-15-website-launched/<p>We are pleased to announce the official launch of our website.</p> <p>The site provides information on our projects and research. Please feel free to browse and stay updated with our latest developments.</p>https://ericjin73.github.io/news/2025-04-14-rser/Sun, 16 Mar 2025 00:00:00 +0000https://ericjin73.github.io/news/2025-04-14-rser/<p>We are excited to announce that our paper, <em>Machine learning for predicting urban greenhouse gas emissions: A systematic literature review</em>, has been published in <strong>Renewable and Sustainable Energy Reviews</strong> (Vol. 215, 2025, Article 115625). Authored by Yukai Jin and Ayyoob Sharifi, this review examines 75 studies from 2003 to 2023, focusing on the models used and the driving factors influencing urban greenhouse gas emissions.</p> <p><strong>Key Findings:</strong></p> <ul> <li><strong>Model Performance:</strong> Hybrid and neural network models show better performance than single models with R² ranging from 0.5231 to 0.9989 and MAPE between 0.3017% and 26.3%.</li> <li><strong>Recommendations:</strong> Standardize evaluation criteria, improve spatial prediction with hybrid models, and conduct cross-urban comparisons.</li> </ul> <p>For more details, please refer to the full article on <a href="https://www.sciencedirect.com/science/article/pii/S1364032125002989" target="_blank" rel="noopener">ScienceDirect</a>.</p>