<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Projects on Beichen Zhang</title><link>https://zhang-beichen.github.io/projects/</link><description>Recent content in Projects on Beichen Zhang</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sun, 07 Dec 2025 00:00:00 -0800</lastBuildDate><atom:link href="https://zhang-beichen.github.io/projects/index.xml" rel="self" type="application/rss+xml"/><item><title>Climate ML Workshop Presentation</title><link>https://zhang-beichen.github.io/projects/neurips-climate-ml/</link><pubDate>Sun, 07 Dec 2025 00:00:00 -0800</pubDate><guid>https://zhang-beichen.github.io/projects/neurips-climate-ml/</guid><description>At the NeurIPS 2025 workshop on tackling climate change with machine learning, I presented work on integrated, spatially explicit modeling for energy transition decisions. The project connects machine learning-adjacent modeling practice with environmental systems analysis and climate adaptation questions.</description></item><item><title>Coupled ABM-LCA for Energy Transition Trade-Offs</title><link>https://zhang-beichen.github.io/projects/energy-transition-abm-lca/</link><pubDate>Fri, 05 Dec 2025 00:00:00 -0800</pubDate><guid>https://zhang-beichen.github.io/projects/energy-transition-abm-lca/</guid><description>I developed a coupled agent-based modeling and life cycle assessment framework to study trade-offs in the siting of emerging energy transition pathways. The model was applied to Southern California and designed to reveal how scenario constraints, resource competition, and community burdens shape resilient transition planning.</description></item><item><title>AI for Drought Impact Monitoring</title><link>https://zhang-beichen.github.io/projects/drought-impact-ai/</link><pubDate>Sun, 01 Dec 2024 00:00:00 -0800</pubDate><guid>https://zhang-beichen.github.io/projects/drought-impact-ai/</guid><description>This body of work applies natural language processing, explainable machine learning, and multi-source environmental information to improve drought impact monitoring and assessment. The goal is to capture impacts that are difficult to observe directly through conventional hydro-meteorological datasets alone.</description></item></channel></rss>