Search papers, labs, and topics across Lattice.
This study enhances the KidSat model for childhood poverty prediction by integrating geographical encoding and implementing a rigorous data quality assessment pipeline. The authors address challenges such as noisy supervision and image quality issues by refining the fine-tuning target matrix, introducing a two-stage quality-screening procedure, and fusing visual embeddings with geographic features. The resulting improvements yield a significant reduction in mean absolute error (MAE) from 0.2167 to 0.1658 across 33 African countries, demonstrating the effectiveness of the proposed enhancements in leveraging publicly accessible satellite data for socioeconomic predictions.
Integrating geographical encoding with a robust data quality assessment reduces poverty prediction errors by nearly 19% in satellite imagery analysis.
Accurate poverty mapping using satellite imagery is often hindered by (i) noisy and sparse survey-derived supervision, (ii) image quality issues such as cloud cover and image corruption, and (iii) lack of explicit spatial structure in image-only models. Building on the KidSat framework, we develop an enhanced pipeline that improves predictive accuracy via refined data preprocessing, systematic image quality assessment, and mathematically defined geographic encoding. First, we refine the fine-tuning target matrix by resolving high-cardinality sparsity and reducing one-hot dimensionality from 103 to 51 via DHS re-aggregation. Second, we introduce a simple two-stage quality-screening procedure to filter heavily clouded or corrupted observations. Third, we fuse DINOv2 visual embeddings with Spherical Harmonics (SH) location features. Across extensive experiments, these changes reduce MAE from 0.2167 to 0.1759, corresponding to an 18.83% relative reduction on the cluster-level severe-deprivation proportion scale. When extended from 16 to 33 African countries, the best-performing configuration achieves an overall MAE of 0.1658. We find that SH features consistently improve performance over the image-only backbone, whereas higher-capacity coordinate Multi Layer Perception augmentation (SH+SIREN) can underperform without carefully designed objectives. Finally, gradient-boosted tree heads (XGBoost/LightGBM) most effectively exploit nonlinear interactions in the fused visual-geographic representation. These findings provide a scalable and principled recipe for improving satellite-based socioeconomic predictions using only publicly accessible data.
