Using reinforcement learning to improve drone-based inference of greenhouse gas fluxes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: van Hove, Alouette, Aalstad, Kristoffer, Pirk, Norbert
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913189001691136
author van Hove, Alouette
Aalstad, Kristoffer
Pirk, Norbert
author_facet van Hove, Alouette
Aalstad, Kristoffer
Pirk, Norbert
contents Accurate mapping of greenhouse gas fluxes at the Earth's surface is essential for the validation and calibration of climate models. In this study, we present a framework for surface flux estimation with drones. Our approach uses data assimilation (DA) to infer fluxes from drone-based observations, and reinforcement learning (RL) to optimize the drone's sampling strategy. Herein, we demonstrate that a RL-trained drone can quantify a CO2 hotspot more accurately than a drone sampling along a predefined flight path that traverses the emission plume. We find that information-based reward functions can match the performance of an error-based reward function that quantifies the difference between the estimated surface flux and the true value. Reward functions based on information gain and information entropy can motivate actions that increase the drone's confidence in its updated belief, without requiring knowledge of the true surface flux. These findings provide valuable insights for further development of the framework for the mapping of more complex surface flux fields.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03932
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using reinforcement learning to improve drone-based inference of greenhouse gas fluxes
van Hove, Alouette
Aalstad, Kristoffer
Pirk, Norbert
Machine Learning
Robotics
Atmospheric and Oceanic Physics
Accurate mapping of greenhouse gas fluxes at the Earth's surface is essential for the validation and calibration of climate models. In this study, we present a framework for surface flux estimation with drones. Our approach uses data assimilation (DA) to infer fluxes from drone-based observations, and reinforcement learning (RL) to optimize the drone's sampling strategy. Herein, we demonstrate that a RL-trained drone can quantify a CO2 hotspot more accurately than a drone sampling along a predefined flight path that traverses the emission plume. We find that information-based reward functions can match the performance of an error-based reward function that quantifies the difference between the estimated surface flux and the true value. Reward functions based on information gain and information entropy can motivate actions that increase the drone's confidence in its updated belief, without requiring knowledge of the true surface flux. These findings provide valuable insights for further development of the framework for the mapping of more complex surface flux fields.
title Using reinforcement learning to improve drone-based inference of greenhouse gas fluxes
topic Machine Learning
Robotics
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2401.03932