activity
20242026
most citedKnowledge Guided Encoder-Decoder Framework: Integrating Multiple Physical Models for Agricultural Ecosystem Modeling

1 citations · 2 across the 11 of their papers we have counts for

collaborators

14 papers

cs.LG2026

AgroFlux: A Spatial-Temporal Benchmark for Carbon and Nitrogen Flux Prediction in Agricultural Ecosystems

Qi Cheng, Licheng Liu, Yao Zhang +3

Agroecosystem, which heavily influenced by human actions and accounts for a quarter of global greenhouse gas emissions (GHGs), plays a crucial role in mitigating global climate cha…

cs.LG2025

GREAT: Generalizable Representation Enhancement via Auxiliary Transformations for Zero-Shot Environmental Prediction

Shiyuan Luo, Chonghao Qiu, Runlong Yu +2

Environmental modeling faces critical challenges in predicting ecosystem dynamics across unmonitored regions due to limited and geographically imbalanced observation data. This cha…

cs.LG2025

Geo-Aware Models for Stream Temperature Prediction across Different Spatial Regions and Scales

Shiyuan Luo, Runlong Yu, Shengyu Chen +4

Understanding environmental ecosystems is vital for the sustainable management of our planet. However,existing physics-based and data-driven models often fail to generalize to vary…

cs.ET2025

Truth Without Comprehension: A BlueSky Agenda for Steering the Fourth Mathematical Crisis

Runlong Yu, Xiaowei Jia

Machine-generated proofs are poised to reach large-scale, human-unreadable artifacts. They foreshadow what we call the Fourth Mathematical Crisis. This crisis crystallizes around t…

cs.LG2025

Learning to Retrieve for Environmental Knowledge Discovery: An Augmentation-Adaptive Self-Supervised Learning Framework

Shiyuan Luo, Runlong Yu, Chonghao Qiu +5

The discovery of environmental knowledge depends on labeled task-specific data, but is often constrained by the high cost of data collection. Existing machine learning approaches u…

cs.ET2025

RAG for Geoscience: What We Expect, Gaps and Opportunities

Runlong Yu, Shiyuan Luo, Rahul Ghosh +3

Retrieval-Augmented Generation (RAG) enhances language models by combining retrieval with generation. However, its current workflow remains largely text-centric, limiting its appli…