4.7 Article

Predicting energy poverty with combinations of remote-sensing and socioeconomic survey data in India: Evidence from machine learning

期刊

ENERGY ECONOMICS
卷 102, 期 -, 页码 -

出版社

ELSEVIER
DOI: 10.1016/j.eneco.2021.105510

关键词

Remote sensing data; Machine learning; Energy poverty prediction; Random forest; Precipitation; PM2.5 concentration

资金

  1. National Social Science Foundationof China [20CSH048, 20AZD024, 21ZDA062]
  2. National Natural Science Foundation of China [71773099]
  3. Rural Finance Survey of the Ministry of Agriculture and Rural Affairs [05190084]
  4. Fundamental Research Funds for the Central Universities [SWU2009105]

向作者/读者索取更多资源

The study demonstrates that a machine learning algorithm incorporating satellite remote sensing data and socioeconomic survey data can accurately predict energy poverty, with precipitation and PM2.5 being the most important environmental indicators.
Identifying energy poverty and targeting interventions require up-to-date and comprehensive survey data, which are expensive, time-consuming, and difficult to conduct, especially in rural areas of developing countries. This paper examined the potential of satellite remote sensing data in energy poverty prediction combined with so-cioeconomic survey data in response to these challenges. We found that a machine learning algorithm incor-porating geographical and environmental remotely collected indicators could identify 90.91% of the districts with high energy poverty and performs better than those using socioeconomic indicators only. Specifically, precipitation and fine particulate matter (PM2.5) offer the most significant contribution. Moreover, the algorithm, which was trained using a dataset from 2015, could also perform well to predict energy poverty using two environment indicators: precipitation and PM2.5 concentration.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据