| 来源类型 | Working Paper |
| 规范类型 | 报告 |
| DOI | 10.3386/w28045 |
| 来源ID | Working Paper 28045 |
| A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery | |
| Esther Rolf; Jonathan Proctor; Tamma Carleton; Ian Bolliger; Vaishaal Shankar; Miyabi Ishihara; Benjamin Recht; Solomon Hsiang | |
| 发表日期 | 2020-11-09 |
| 出版年 | 2020 |
| 语种 | 英语 |
| 摘要 | Combining satellite imagery with machine learning (SIML) has the potential to address global challenges by remotely estimating socioeconomic and environmental conditions in data-poor regions, yet the resource requirements of SIML limit its accessibility and use. We show that a single encoding of satellite imagery can generalize across diverse prediction tasks (e.g. forest cover, house price, road length). Our method achieves accuracy competitive with deep neural networks at orders of magnitude lower computational cost, scales globally, delivers label super-resolution predictions, and facilitates characterizations of uncertainty. Since image encodings are shared across tasks, they can be centrally computed and distributed to unlimited researchers, who need only fit a linear regression to their own ground truth data in order to achieve state-of-the-art SIML performance. |
| 主题 | Econometrics ; Data Collection ; Development and Growth ; Development ; Environmental and Resource Economics ; Environment ; Regional and Urban Economics ; Regional Economics |
| URL | https://www.nber.org/papers/w28045 |
| 来源智库 | National Bureau of Economic Research (United States) |
| 引用统计 | |
| 资源类型 | 智库出版物 |
| 条目标识符 | http://119.78.100.153/handle/2XGU8XDN/585718 |
| 推荐引用方式 GB/T 7714 | Esther Rolf,Jonathan Proctor,Tamma Carleton,et al. A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery. 2020. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 资源类型 | 版本类型 | 开放类型 | 使用许可 | ||
| w28045.pdf（7751KB） | 智库出版物 | 限制开放 | CC BY-NC-SA | 浏览 | ||
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
