Improving Estimates of Transitions from Satellite Data: A Hidden Markov Model Approach

• 成果类型: Article
• 署名作者: Torchiana, Adrian L.; Rosenbaum, Ted; Scott, Paul T.; Souza-Rodrigues, Eduardo
• 署名单位: New York University; University of Toronto
• 刊物名称: REVIEW OF ECONOMICS AND STATISTICS
• ISSN/ISSBN: 0034-6535
• DOI: 10.1162/rest_a_01301
• 发表日期: 2025-03
• 页码: 426-441
• 关键词: misclassification error; LAND; parameter

摘要

Satellite-based image classification facilitates low-cost measurement of the Earth's surface composition. However, misclassified imagery can lead to misleading conclusions about transition processes. We propose a correction for transition rate estimates based on the econometric measurement error literature to extract the signal (truth) from its noisy measurement (satellite-based classifications). No ground-truth data are required in the implementation. Our proposed correction produces consistent estimates of transition rates, confirmed by longitudinal validation data, while transition rates without correction are severely biased. Using our approach, we show how eliminating deforestation in Brazil's Atlantic forest region through 2040 could save $100 billion in CO2 emissions.