Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Structured dataset of reported cloud seeding activities in the United States (2000-2025) using an LLM

Jared Joseph Donohue, Kara D. Lamb

Abstract

Cloud seeding, a weather modification technique used to increase precipitation, has been practiced in the western United States since the 1940s. However, comprehensive datasets are not currently available to analyze these efforts. To address this gap, we present a structured dataset of reported cloud seeding activities in the U.S. from 2000-2025, including the project name, year, season, state, operator, seeding agent, apparatus used for deployment, stated purpose, target area, control area, start date, and end date. Combining our multi-stage PDF-to-text extraction pipeline with OpenAI's o3 large language model (LLM), we processed 832 historical reports from the National Oceanic and Atmospheric Administration (NOAA). The resulting dataset demonstrates 98.38% estimated accuracy, based on manual review of 200 randomly sampled records, and is publicly available on Zenodo. This dataset addresses the gap in cloud seeding data and demonstrates the potential for LLMs to extract structured information from historical environmental documents. More broadly, this work provides a scalable framework for unlocking historical data from scanned documents across scientific domains.

Structured dataset of reported cloud seeding activities in the United States (2000-2025) using an LLM

Abstract

Cloud seeding, a weather modification technique used to increase precipitation, has been practiced in the western United States since the 1940s. However, comprehensive datasets are not currently available to analyze these efforts. To address this gap, we present a structured dataset of reported cloud seeding activities in the U.S. from 2000-2025, including the project name, year, season, state, operator, seeding agent, apparatus used for deployment, stated purpose, target area, control area, start date, and end date. Combining our multi-stage PDF-to-text extraction pipeline with OpenAI's o3 large language model (LLM), we processed 832 historical reports from the National Oceanic and Atmospheric Administration (NOAA). The resulting dataset demonstrates 98.38% estimated accuracy, based on manual review of 200 randomly sampled records, and is publicly available on Zenodo. This dataset addresses the gap in cloud seeding data and demonstrates the potential for LLMs to extract structured information from historical environmental documents. More broadly, this work provides a scalable framework for unlocking historical data from scanned documents across scientific domains.
Paper Structure (20 sections, 6 figures, 3 tables)

This paper contains 20 sections, 6 figures, 3 tables.

Table of Contents

  1. Abstract
  2. Background & Summary
  3. Methods
  4. Data Records
  5. Technical Validation
  6. Usage Notes
  7. Data Availability
  8. Code Availability
  9. Author Contributions
  10. Competing Interests
  11. Acknowledgments

Figures (6)

  • Figure 1: NOAA Form 17-4 Dataset Extraction Pipeline
  • Figure 2: Screenshot of the CSV Dataset (cloud_seeding_us_2000_2025.csv)
  • Figure 3: Cloud Seeding Activity by U.S. State (2000–2025). States with active weather modification programs show the highest number of recorded operations. Specific locations (shown as salmon markers) are from geocoding the stated target_area field with the GoogleMaps API.
  • Figure 4: Cloud Seeding Activity by U.S. State over Time (2000–2025). The number of activities peaked between 2003-2005, declined gradually, and rose again after 2021.
  • Figure 5: Stated Purpose of Cloud Seeding Activity (2000–2025). Augmenting snowpack is the leading purpose, followed by increasing precipitation.
  • ...and 1 more figures