paper-with-me

홈 › Papers

A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery

2020-10-16 · Esther Rolf, Jonathan Proctor, Tamma Carleton, Ian Bolliger, Vaishaal Shankar, Miyabi Ishihara, Benjamin Recht, Solomon Hsiang

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.

📄 PDF Abstract BibTeX arXiv:2010.08168

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningregressionSuper-Resolution

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Using Game Engines and Machine Learning to Create Synthetic Satellite Imagery for a Tabletop Verification Exercise

2024-04-17 · Johannes Hoster, Sara Al-Sayed, Felix Biessmann, Alexander Glaser 외

Satellite imagery is regarded as a great opportunity for citizen-based monitoring of activities of interest. Relevant imagery may however not be available at sufficiently high resolution, quality, or cadence -- let alone…

Machine Learning for Generalizable Prediction of Flood Susceptibility

2019-10-15 · Chelsea Sidrane, Dylan J Fitzpatrick, Andrew Annex, Diane O'Donoghue 외

Flooding is a destructive and dangerous hazard and climate change appears to be increasing the frequency of catastrophic flooding events around the world. Physics-based flood models are costly to calibrate and are rarely…

BIG-bench Machine LearningEarth ObservationPrediction

Generating Synthetic Multispectral Satellite Imagery from Sentinel-2

2020-12-05 · Tharun Mohandoss, Aditya Kulkarni, Daniel Northrup, Ernest Mwebaze 외

Multi-spectral satellite imagery provides valuable data at global scale for many environmental and socio-economic applications. Building supervised machine learning models based on these imagery, however, may require gro…

BIG-bench Machine LearningData Augmentation

Poverty Prediction with Public Landsat 7 Satellite Imagery and Machine Learning

2017-11-10 · Anthony Perez, Christopher Yeh, George Azzari, Marshall Burke 외

Obtaining detailed and reliable data about local economic livelihoods in developing countries is expensive, and data are consequently scarce. Previous work has shown that it is possible to measure local-level economic li…

BIG-bench Machine Learning

Using Satellite Imagery and Machine Learning to Estimate the Livelihood Impact of Electricity Access

2021-09-07 · Nathan Ratledge, Gabe Cadamuro, Brandon de la Cuesta, Matthieu Stigler 외

In many regions of the world, sparse data on key economic outcomes inhibits the development, targeting, and evaluation of public policy. We demonstrate how advancements in satellite imagery and machine learning can help …