# OGInfra: Geolocating Oil & Gas Infrastructure using Remote Sensing based Active Fire Data

arXiv: https://arxiv.org/abs/2210.16924 · HTML: https://mlsanity.com/paper/2210.16924/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 15 references that are in the map.
- First posted on arXiv 30 Oct 2022.

## Builds on (most cited first, 2 of 2)

- [Benchmark Analysis of Representative Deep Neural Network Architectures](https://mlsanity.com/paper/1810.00736/) (2018)
- [OGNet: Towards a Global Oil and Gas Infrastructure Database using Deep Learning on Remotely Sensed Imagery](https://mlsanity.com/paper/2011.07227/) (2020)

## Built on by (most cited first, 1 of 1)

- [Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery](https://mlsanity.com/paper/2410.09032/) (2024)

## Abstract (arXiv)

Remote sensing has become a crucial part of our daily lives, whether it be from triangulating our location using GPS or providing us with a weather forecast. It has multiple applications in domains such as military, socio-economical, commercial, and even in supporting humanitarian efforts. This work proposes a novel technique for the automated geo-location of Oil & Gas infrastructure with the use of Active Fire Data from the NASA FIRMS data repository & Deep Learning techniques; achieving a top accuracy of 90.68% with the use of ResNet101.