• Corpus ID: 226964460

OGNet: Towards a Global Oil and Gas Infrastructure Database using Deep Learning on Remotely Sensed Imagery

@article{Sheng2020OGNetTA,
  title={OGNet: Towards a Global Oil and Gas Infrastructure Database using Deep Learning on Remotely Sensed Imagery},
  author={Hao Sheng and Jeremy A. Irvin and Sasankh Munukutla and Shenmin Zhang and Christopher Cross and Kyle T. Story and Rose Rustowicz and Cooper W. Elsworth and Zutao Yang and Mark Omara and Ritesh Gautam and Robert B. Jackson and A. Ng},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.07227}
}
At least a quarter of the warming that the Earth is experiencing today is due to anthropogenic methane emissions. There are multiple satellites in orbit and planned for launch in the next few years which can detect and quantify these emissions; however, to attribute methane emissions to their sources on the ground, a comprehensive database of the locations and characteristics of emission sources worldwide is essential. In this work, we develop deep learning algorithms that leverage freely… 

Figures and Tables from this paper

Power Plant Classification from Remote Imaging with Deep Learning

This work focuses on classifying different types of power plants from Sentinel-2 imaging data, using a ResNet-50 deep learning model to achieve a mean accuracy of 90.0% in distinguishing 10 different power plant types and a background class.

SCHMEAR: scalable construction of holistic models for energy analysis from rooftops

This work demonstrates that the computer vision system used in this work can accurately predict energy consumption through the extraction of meaningful features contained in satellite imagery, and introduces a data-collection pipeline and computer vision architecture to process satellite photos and contextual information from the urban texture.

Extracting Built Environment Features for Planning Research with Computer Vision: A Review and Discussion of State-of-the-Art Approaches

This paper summarizes the opportunities and challenges of applying computer vision algorithms to extract built environment features revealed by this interdisciplinary synthesis, and examines the different implications of universal output for diverse contexts.

METER-ML: A Multi-Sensor Earth Observation Benchmark for Automated Methane Source Mapping

Reducing methane emissions is essential for mitigating global warming. To attribute methane emissions to their sources, a comprehensive dataset of methane source infrastructure is necessary. Recent

Using Computer Vision to further econometric analysis: A case study with predicting Urban Heat Island

While “explainability” is often discussed for the purpose of ensuring we can trust how a model makes a decision, understanding and quantifying how a model makes deci-sions serves potential additional

Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis

References

SHOWING 1-10 OF 41 REFERENCES

DeepWind: Weakly Supervised Localization of Wind Turbines in Satellite Imagery

Wind energy is being adopted at an unprecedented rate. The locations of wind energy sources, however, are largely undocumented and expensive to curate manually, which significantly impedes their

Four corners: The largest US methane anomaly viewed from space

Methane (CH4) is a potent greenhouse gas and ozone precursor. Quantifying methane emissions is critical for projecting and mitigating changes to climate and air quality. Here we present CH4

Daily Satellite Observations of Methane from Oil and Gas Production Regions in the United States

New measurements from the space-based TROPOspheric Monitoring Instrument (TROPOMI) launched in 2017 are presented that show methane enhancements over production regions in the United States.

Satellite observations of atmospheric methane and their value for quantifying methane emissions

Methane is a greenhouse gas emitted by a range of natural and anthropogenic sources. Atmospheric methane has been measured continuously from space since 2003, and new instruments are planned for

A global gridded (0.1° × 0.1°) inventory of methane emissions from oil, gas, and coal exploitation based on national reports to the United Nations Framework Convention on Climate Change

Abstract. Individual countries report national emissions of methane, a potent greenhouse gas, in accordance with the United Nations Framework Convention on Climate Change (UNFCCC). We present a

SolarNet: A Deep Learning Framework to Map Solar Power Plants In China From Satellite Imagery

To the best of the knowledge, it is the first time that deep learning is used to reveal the locations and sizes of solar farms in China, which could provide insights for solar power companies, market analysts and the government.

Remote sensing of methane leakage from natural gas and petroleum systems revisited

Abstract. The switch from the use of coal to natural gas or oil for energy generation potentially reduces greenhouse gas emissions and thus the impact on global warming and climate change because of

Quantifying methane emissions from the largest oil-producing basin in the United States from space

A high-resolution satellite data–based atmospheric inversion framework is demonstrated, providing a robust top-down analytical tool for quantifying and evaluating subregional methane emissions from the Permian Basin.

Satellite Discovery of Anomalously Large Methane Point Sources From Oil/Gas Production

Rapid identification of anomalous methane sources in oil/gas fields could enable corrective action to fight climate change. The GHGSat‐D satellite instrument measuring atmospheric methane with