5 papers
Unfolding the Interdisciplinary Complexities of Climate Science: Fuxi-Climate Foundational Model
Zhengyu Shi, Shaojie Shi, Rui Xu +8
Climate research and decision-making require integrating evidence across physical processes, socio-economic dynamics and policy responses. Large language models (LLMs) have been ex…
InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems
Shaojie Shi, Zhengyu Shi, Lingran Zheng +15
Causal inference in social science relies on end-to-end, intervention-centered research-design reasoning grounded in real-world policy interventions, but current benchmarks fail to…
Zero-Shot Statistical Downscaling via Diffusion Posterior Sampling
Ruian Tie, Wenbo Xiong, Zhengyu Shi +4
Conventional supervised climate downscaling struggles to generalize to Global Climate Models (GCMs) due to the lack of paired training data and inherent domain gaps relative to rea…
Generative artificial intelligence improves projections of climate extremes
Ruian Tie, Xiaohui Zhong, Zhengyu Shi +4
Climate change is amplifying extreme events, posing escalating risks to biodiversity, human health, and food security. GCMs are essential for projecting future climate, yet their c…
Inferring Economic Condition Uncertainty from Electricity Big Data
Haoqi Qian, Zhengyu Shi, Libo Wu
Inferring the uncertainty in economic conditions is significant for both decision makers as well as market players. In this paper, we propose a novel approach to measure the econom…