Research map / Time series / Long-term forecasting
Exploiting Time-Series Image-to-Image Translation to Expand the Range of Wildlife Habitat Analysis
Ruobing Zheng, Ze Luo, Baoping Yan
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 temporal-embedding conditional GAN instead of pix2pix | time-series image-to-image translation model · HSI mapping, Overall | RMSE: 24.143 -> 19.096 | Improved |
| use temporal-embedding conditional GAN instead of pix2pix | time-series image-to-image translation model · HR mapping, Overall | RMSE: 17.758 -> 15.941 | Improved |
| use temporal-embedding conditional GAN instead of pix2pix | time-series image-to-image translation model · HSI mapping, Temporal test | LSSIM: 0.619 -> 0.462 | Improved |
| use adversarial loss encoder-decoder instead of CNN with l2 loss | time-series image-to-image translation model · HSI mapping, Overall | MAE: 14.817 -> 11.433 | Improved |
| use adversarial loss encoder-decoder instead of CNN with l2 loss | time-series image-to-image translation model · HR mapping, Overall | LSSIM: 0.503 -> 0.324 | Improved |
| use image-based model instead of pixel-based Decision Tree | time-series image-to-image translation model · HSI mapping, Overall | RMSE: 26.885 -> 19.096 | Improved |
| use image-based model instead of pixel-based Decision Tree | time-series image-to-image translation model · HR mapping, Overall | RMSE: 30.673 -> 15.941 | Improved |
| pix2pix versus CNN + l2 loss for HSI mapping (adversarial loss without temporal info) | time-series image-to-image translation model · HSI mapping, Overall | RMSE: 19.974 -> 24.143 | Hurt |
| pix2pix versus CNN + l2 loss for HR mapping | time-series image-to-image translation model · HR mapping, Overall | RMSE: 18.385 -> 17.758 | Improved |
| test on unseen location (spatial split) instead of random overall split | time-series image-to-image translation model · HSI mapping, Our model | RMSE: 19.096 -> 19.631 | Hurt |
| test on unseen location (spatial split) instead of random overall split | time-series image-to-image translation model · HR mapping, Our model | MAE: 11.126 -> 13.973 | Hurt |
| spatial split for Decision Tree (less affected by new geomorphology) | time-series image-to-image translation model · HSI mapping, Decision Tree | RMSE: 26.885 -> 26.842 | No clear effect |
Closest papers by meaning
- RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings (CVPR 2025 · similarity 0.83)
- Reconstructing Animals and the Wild (CVPR 2025 · similarity 0.83)
- SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery (AAAI 2025 · similarity 0.83)
- MammAlps: A Multi-view Video Behavior Monitoring Dataset of Wild Mammals in the Swiss Alps (CVPR 2025 · similarity 0.82)
- MOVEBENCH: A Benchmark for Global-Scale Wildlife Movement Forecasting (NeurIPS 2026 · similarity 0.81)
- DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications (ICML 2025 · similarity 0.81)
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.
