2026
Mapping on a budget: Optimizing spatial data collection for ML
Betti et al. 2026, Proceedings of the AAAI Conference on Artificial Intelligence
Principal Investigator(s): Tamma Carleton
Abstract for Mapping on a budget: Optimizing spatial data collection for ML
In applications across agriculture, ecology, and human development, machine learning with satellite imagery (SatML) is limited by the sparsity of labeled training data. While satellite data cover the globe, labeled training datasets for SatML are often small, spatially clustered, and collected for other purposes (e.g., administrative surveys or field measurements). Despite the pervasiveness of this issue in practice, past SatML research has largely focused on new model architectures and training algorithms to handle scarce training data, rather than modeling data conditions directly. This leaves scientists and policymakers who wish to use SatML for large-scale monitoring uncertain about whether and how to collect additional data to maximize performance. Here, we present the first problem formulation for the optimization of spatial training data in the presence of heterogeneous data collection costs and realistic budget constraints, as well as novel methods for addressing this problem. In experiments simulating different problem settings across three continents and four tasks, our strategies reveal substantial gains from sample optimization. Further experiments delineate settings for which optimized sampling is particularly effective. The problem formulation and methods we introduce are designed to generalize across application domains for SatML; we put special emphasis on a specific problem setting where our coauthors can immediately use our findings to augment clustered agricultural surveys for SatML monitoring in Togo.
Demand for foodstuffs and nutrients under urbanization in Zambia and Tanzania
Wang et al. 2026, Agriculture & Food Security
Empirical estimates of installed capacity density for solar photovoltaic and onshore and offshore wind power plants
Covey et al. 2026, Environmental Research: Infrastructure and Sustainability
Causal inference for biodiversity conservation
Baylis et al. 2026, Review of Environmental Economics and Policy
Safeguarding climate-resilient mangroves requires only a moderate increase in the global protected area
Dabalà et al. 2026, Nature Communications
2025
Global forest dataset incongruence creates high uncertainties for conservation, climate, and development policy
Castle et al. 2025, One Earth
Does humidity matter? Prenatal heat and child health in South Asia
McMahon et al. 2025, Science
Inside the black box: how consistent are global food security crisis analyses?
Lentz et al. 2025, Food Policy
Official estimates of global food insecurity undercount acute hunger
Lentz et al. 2025, Nature Food
Aquaculture coupled with trade is sustaining growth and improving stability in global aquatic food supply
Zhao et al. 2025, Aquaculture
Economic benefits and cost competitiveness of green hydrogen in decarbonizing China's electricity and hard-to-electrify sectors
Yang et al. 2025, Environmental Research Letters
Monitoring maize yield variability over space and time with unsupervised satellite imagery features
Molitor et al. 2025, Remote Sensing
Strategies to accelerate US coal power phase-out using contextual retirement vulnerabilities
Gathrid et al. 2025, Nature Energy
When crops fail, forests follow: Agricultural shocks and deforestation in Zambia
Ordóñez et al. 2025, PNAS
Health losses attributed to anthropogenic climate change
Carlson et al. 2025, Nature Climate Change
Near-global spawning strategies of large pelagic fish
Buenafe et al. 2025, Nature Communications
Uneven participation of independent and contract smallholders in certified palm oil mill markets in Indonesia
Ekaputri et al. 2025, Nature Communications Earth & Environment
Complementary perspectives and metrics are essential to end deforestation
Lathuillière et al. 2025, Conservation Letters
A causal inference framework for climate change attribution in ecology
Dudney et al. 2025, Ecology Letters
Aquaculture isn’t always the answer: rethinking blue transitions through justice and community experience
Castillo et al. 2025, Global Environmental Change