arXiv subjects

Elizabeth Tellman

Publications and source records attributed to Elizabeth Tellman.

3 recordsLinked to original sources

arXiv2025

Assessing the value of Geo-Foundational Models for Flood Inundation Mapping: Benchmarking models for Sentinel-1, Sentinel-2, and Planetscope for end-users

Geo-Foundational Models (GFMs) enable fast and reliable extraction of spatiotemporal information from satellite imagery, improving flood inundation mapping by leveraging location and time embeddings. Despite their potential, it remains unclear whether GFMs outperform traditional models like U-Net. A systematic comparison across sensors and data availability scenarios is still lacking, which is an essential step to guide end-users in model selection. To address this, we evaluate three GFMs, Prithvi 2.0, Clay V1.5, DOFA, and UViT (a Prithvi variant), against TransNorm, U-Net, and Attention U-Net using PlanetScope, Sentinel-1, and Sentinel-2. We observe competitive performance among all GFMs, with only 2-5% variation between the best and worst models across sensors. Clay outperforms others on PlanetScope (0.79 mIoU) and Sentinel-2 (0.70), while Prithvi leads on Sentinel-1 (0.57). In leave-one-region-out cross-validation across five regions, Clay shows slightly better performance across all sensors (mIoU: 0.72(0.04), 0.66(0.07), 0.51(0.08)) compared to Prithvi (0.70(0.05), 0.64(0.09), 0.49(0.13)) and DOFA (0.67(0.07), 0.64(0.04), 0.49(0.09)) for PlanetScope, Sentinel-2, and Sentinel-1, respectively. Across all 19 sites, leave-one-region-out cross-validation reveals a 4% improvement by Clay compared to U-Net. Visual inspection highlights Clay's superior ability to retain fine details. Few-shot experiments show Clay achieves 0.64 mIoU on PlanetScope with just five training images, outperforming Prithvi (0.24) and DOFA (0.35). In terms of computational time, Clay is a better choice due to its smaller model size (26M parameters), making it ~3x faster than Prithvi (650M) and 2x faster than DOFA (410M). Contrary to previous findings, our results suggest GFMs offer small to moderate improvements in flood mapping accuracy at lower computational cost and labeling effort compared to traditional U-Net.

cs.CV↗

arXiv2025

AI for a Planet Under Pressure

Artificial intelligence (AI) is already driving scientific breakthroughs in a variety of research fields, ranging from the life sciences to mathematics. This raises a critical question: can AI be applied both responsibly and effectively to address complex and interconnected sustainability challenges? This report is the result of a collaboration between the Stockholm resilience Centre (Stockholm University), the Potsdam Institute for Climate Impact Research (PIK), and Google DeepMind. Our work explores the potential and limitations of using AI as a research method to help tackle eight broad sustainability challenges. The results build on iterated expert dialogues and assessments, a systematic AI-supported literature overview including over 8,500 academic publications, and expert deep-dives into eight specific issue areas. The report also includes recommendations to sustainability scientists, research funders, the private sector, and philanthropies.

cs.CY↗

arXiv2024

Impact Evaluations in Data Poor Settings: The Case of Stress-Tolerant Rice Varieties in Bangladesh

New technologies are sometimes introduced at times or in places that lack the necessary data to conduct a well-identified impact evaluation. We develop a methodology that combines Earth observation (EO) data and advances in machine learning with administrative and survey data so as to allow researchers to conduct impact evaluations when traditional economic data is missing. To demonstrate our method, we study stress tolerant rice varieties (STRVs) first introduced to Bangladesh 15 years ago. Using EO data on rice production and flooding for the entire country, spanning two decades, we find evidence of STRV effectiveness. We highlight how the nature of the technology, which is only effective under a specific set of circumstances, creates a Goldilocks Problem that EO data is particularly well suited to addressing. Our findings speak to the promises and challenges of using EO data to conduct impact evaluations in data poor settings.

econ.GN↗