skip to main content


Search for: All records

Creators/Authors contains: "Driscoll, Anne"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Recent dramatic and deadly increases in global wildfire activity have increased attention on the causes of wildfires, their consequences, and how risk from wildfire might be mitigated. Here we bring together data on the changing risk and societal burden of wildfire in the United States. We estimate that nearly 50 million homes are currently in the wildland–urban interface in the United States, a number increasing by 1 million houses every 3 y. To illustrate how changes in wildfire activity might affect air pollution and related health outcomes, and how these linkages might guide future science and policy, we develop a statistical model that relates satellite-based fire and smoke data to information from pollution monitoring stations. Using the model, we estimate that wildfires have accounted for up to 25% of PM 2.5 (particulate matter with diameter <2.5 μm) in recent years across the United States, and up to half in some Western regions, with spatial patterns in ambient smoke exposure that do not follow traditional socioeconomic pollution exposure gradients. We combine the model with stylized scenarios to show that fuel management interventions could have large health benefits and that future health impacts from climate-change–induced wildfire smoke could approach projected overall increases in temperature-related mortality from climate change—but that both estimates remain uncertain. We use model results to highlight important areas for future research and to draw lessons for policy. 
    more » « less
  2. null (Ed.)
  3. Abstract

    Accurate and comprehensive measurements of economic well-being are fundamental inputs into both research and policy, but such measures are unavailable at a local level in many parts of the world. Here we train deep learning models to predict survey-based estimates of asset wealth across ~ 20,000 African villages from publicly-available multispectral satellite imagery. Models can explain 70% of the variation in ground-measured village wealth in countries where the model was not trained, outperforming previous benchmarks from high-resolution imagery, and comparison with independent wealth measurements from censuses suggests that errors in satellite estimates are comparable to errors in existing ground data. Satellite-based estimates can also explain up to 50% of the variation in district-aggregated changes in wealth over time, with daytime imagery particularly useful in this task. We demonstrate the utility of satellite-based estimates for research and policy, and demonstrate their scalability by creating a wealth map for Africa’s most populous country.

     
    more » « less
  4. Accurate and comprehensive measurements of a range of sustainable development outcomes are fundamental inputs into both research and policy. We synthesize the growing literature that uses satellite imagery to understand these outcomes, with a focus on approaches that combine imagery with machine learning. We quantify the paucity of ground data on key human-related outcomes and the growing abundance and improving resolution (spatial, temporal, and spectral) of satellite imagery. We then review recent machine learning approaches to model-building in the context of scarce and noisy training data, highlighting how this noise often leads to incorrect assessment of model performance. We quantify recent model performance across multiple sustainable development domains, discuss research and policy applications, explore constraints to future progress, and highlight research directions for the field.

     
    more » « less