Research map / Large language models / AI and society
Mapping on a Budget: Optimizing Spatial Data Collection for ML
Livia Betti, Farooq Sanni, Gnouyaro Z. Sogoyou, Togbe Agbagla, Cullen Molitor, Tamma Carleton, Esther Rolf
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 image-cluster representation utility instead of default cluster sampling | MOSAIKS augmentation · Togo Soil Fertility (budget 100) | R^2: 0.10 -> 0.17 | Improved |
| use image-cluster representation utility instead of greedy size maximization | MOSAIKS augmentation · Togo Soil Fertility (budget 100) | R^2: 0.08 -> 0.17 | Improved |
| use admin-group representation utility instead of default cluster sampling | MOSAIKS augmentation · India Consumption (budget 2000) | R^2: 0.18 -> 0.33 | Improved |
| sample random clusters instead of greedy size maximization | MOSAIKS augmentation · India Consumption (budget 1000) | R^2: 0.18 -> 0.26 | Improved |
| maximize dataset size greedily instead of default cluster sampling | MOSAIKS augmentation · USA Population (budget 50) | R^2: 0.25 -> -0.21 | Hurt |
| use NLCD-group representation utility instead of default cluster sampling | MOSAIKS augmentation · USA Treecover (budget 50) | R^2: 0.56 -> 0.68 | Improved |
| use admin-group representation utility instead of default cluster sampling | MOSAIKS augmentation · USA Treecover (budget 50) | R^2: 0.56 -> 0.55 | No clear effect |
| use admin-group representation utility instead of default cluster sampling | MOSAIKS augmentation · USA Population (budget 50) | R^2: 0.25 -> 0.10 | Hurt |
| use admin-group representation utility instead of greedy size maximization | MOSAIKS augmentation · USA Population (budget 1000) | R^2: 0.48 -> 0.52 | Improved |
| use image-cluster representation utility instead of random clusters | MOSAIKS augmentation · Togo Soil Fertility (budget 500) | R^2: 0.17 -> 0.21 | Improved |
| use image-cluster representation utility instead of random clusters | MOSAIKS augmentation · India Consumption (budget 5000) | R^2: 0.37 -> 0.39 | No clear effect |
| rank datasets by image-group representation instead of size utility | utility function · USA Population (all sampling types pooled) | Spearman rho with R^2: 0.381 -> 0.510 | Improved |
Closest papers by meaning
- Position: Mission Critical – Satellite Data is a Distinct Modality in Machine Learning (ICML 2024 · similarity 0.89)
- HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing (AAAI 2024 · similarity 0.85)
- Fields of The World: A Machine Learning Benchmark Dataset for Global Agricultural Field Boundary Segmentation (AAAI 2025 · similarity 0.85)
- Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentation (CVPR 2025 · similarity 0.85)
- SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery (AAAI 2025 · similarity 0.85)
- Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind (NeurIPS 2025 · similarity 0.85)
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.
