https://zhang-beichen.github.io/experience/Recent content in Experience on Beichen ZhangHugoen-USWed, 01 Jan 2025 00:00:00 -0800https://zhang-beichen.github.io/experience/blackrock/Wed, 01 Jan 2025 00:00:00 -0800https://zhang-beichen.github.io/experience/blackrock/At BlackRock, I work within climate and energy analytics on modeling approaches that help connect environmental processes, risk, and decision-relevant outcomes. My work emphasizes rigorous quantitative thinking, interpretable modeling, and practical analytical workflows that can support real-world use. This role builds on my research background while pushing the work closer to applied decisions. It has strengthened my focus on scalable modeling, cross-functional communication, and the translation of scientific complexity into clear analytical products.https://zhang-beichen.github.io/experience/lbnl/Mon, 01 Jan 2024 00:00:00 -0800https://zhang-beichen.github.io/experience/lbnl/At Berkeley Lab, I worked on integrated environmental impact assessment for energy transition pathways. A major focus was translating conceptual impact frameworks into quantitative tools that could represent trade-offs among water, land, technology deployment, and community outcomes. I developed a coupled agent-based modeling and life cycle assessment framework to study how pathway portfolios interact with local resource constraints and policy priorities. This work connected modeling design, environmental systems thinking, and scenario-based analysis.https://zhang-beichen.github.io/experience/unl/Thu, 01 Aug 2019 00:00:00 -0500https://zhang-beichen.github.io/experience/unl/During my doctoral work, I studied climate assessment and impacts with a minor in statistics. My dissertation focused on applications of artificial intelligence for drought impact monitoring and assessment, combining Earth science knowledge with machine learning, text data, and environmental indicators. This period shaped the core of my research profile: using data-driven methods to understand complex environmental systems while staying grounded in physical context, public relevance, and methodological transparency.