Research map / Time series / Causal and generative time series
EcoDiffusion: Uncertainty-Aware Emulation of Ecosystem Processes with Conditional Diffusion for Long Sequences with Single-Step Initialization
Ruohan Li, Zhihao Wang, Xiaowei Jia, Gengchen Mai, Lei Ma, George C. Hurtt, Quan Shen, Zhili Li, Yiqun Xie
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use EcoDiffusion (subset forecasting plus full-set imputation, conditional diffusion) instead of DeepED | ED emulator · annual scale, Height | RMSE: 1.87 -> 1.26 | Improved |
| use non-autoregressive EcoDiffusion instead of autoregressive diffusion TimeGrad | diffusion emulator · annual scale, Height | RMSE: 4.76 -> 1.26 | Improved |
| use EcoDiffusion instead of CSDI | diffusion emulator · annual scale, Height | CRPS: 0.86 -> 0.38 | Improved |
| use frequency-based trend decomposition models (FEDformer) with single-step initial conditions | time-series forecasters · annual scale, Height | RMSE: FEDformer 5.29 vs Informer 2.83 | Hurt |
| add strict temporal causal mask to annual forecasting (ablation) | EcoDiffusion-X · annual scale, Height | RMSE: 1.67 -> 1.55 | Improved |
| add strict temporal causal mask to annual forecasting (ablation) | EcoDiffusion-X · annual scale, AGB | RMSE: 0.47 -> 0.42 | Improved |
| add global conditioning (climate type, initial forest age) (ablation) | EcoDiffusion-causal · annual scale, Height | RMSE: 1.55 -> 1.26 | Improved |
| add global conditioning (climate type, initial forest age) (ablation) | EcoDiffusion-causal · annual scale, Soil carbon | RMSE: 0.35 -> 0.40 | Hurt |
| add global conditioning (climate type, initial forest age) (ablation) | EcoDiffusion-causal · annual scale, LAI, GPP, NPP, Rh | RMSE: LAI 0.27 -> 0.27, GPP 0.14 -> 0.14, NPP 0.07 -> 0.07 | No clear effect |
| move from annual to monthly imputation scale | EcoDiffusion · Height and AGB | RMSE: Height 1.26 -> 1.26, AGB 0.42 -> 0.42 | No clear effect |
| move from annual to monthly imputation scale | EcoDiffusion · GPP | RMSE: 0.14 -> 0.23 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CSDI — CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation (NeurIPS 2021) · better on 6 of 6 shared results
- Informer — Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting (AAAI 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model (NeurIPS 2024 · similarity 0.84)
- Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics (NeurIPS 2025 · similarity 0.83)
- stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation (NeurIPS 2026 · similarity 0.83)
- Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme (NeurIPS 2025 · similarity 0.83)
- Causal Climate Emulation with Bayesian Filtering (NeurIPS 2025 · similarity 0.83)
- CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling (ICLR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
