Barchan Dunes Cruising Dune‐Size Obstacles

Borges, D. S.; Franklin, Erick de Moraes

doi:10.1029/2023gl104125

“…This information can be useful for estimating the direction and strength of local winds, determining the regimes of sand transport and accumulation, and estimating the effects of global changes on Earth based on the dynamics of dunes 28 . Other reason is the possibility for predicting the future of barchan fields based on barchan-barchan interaction maps, such as those from Assis and Franklin 11 (or, in the same way, deducing the ancient past of such fields), or the interaction of dunes with dune-size obstacles based on the corresponding maps, such as shown in Assis and Franklin 29 : by training a CNN with interacting patterns measured in laboratory, the trained CNN might predict the same kind of interaction in the field based on satellite images. Here again, this information can be used for estimating the effects of climate change on Earth 28 , and predicting if constructions are under imminent threat of being overtaken by sand 30 .…”

Section: Introductionmentioning

confidence: 99%

Detection and tracking of barchan dunes using Artificial Intelligence

Cúñez,

Franklin

2024

Preprint

1

0

View full text Add to dashboard Cite

Barchans are crescent-shape dunes ubiquitous on Earth and other celestial bodies, which are organized in barchan fields where they interact with each other. Over the last decades, satellite images have been largely employed to detect barchans on Earth and on the surface of Mars, with AI (Artificial Intelligence) becoming an important tool for monitoring those bedforms. However, automatic detection reported in previous works is limited to isolated dunes and does not identify successfully groups of interacting barchans. In this paper, we inquire into the automatic detection and tracking of barchans by carrying out experiments and exploring the acquired images using AI. After training a neural network with images from controlled experiments where complex interactions took place between dunes, we did the same for satellite images from Earth and Mars. We show, for the first time, that a neural network trained properly can identify and track barchans interacting with each other in different environments, using different image types (contrasts, colors, points of view, resolutions, etc.), with confidence scores (accuracy) above 70%. Our results represent a step further for automatically monitoring barchans, with important applications for human activities on Earth, Mars and other celestial bodies.

show abstract

Dataset of turbulent flow over interacting barchan dunes

Alvarez,

Borges,

Franklin

2024

Data in Brief

Self Cite

0

View full text Add to dashboard Cite

Detection and tracking of barchan dunes using artificial intelligence

Cúñez,

Franklin

2024

Sci Rep

0

View full text Add to dashboard Cite

Barchans are crescent-shape dunes ubiquitous on Earth and other celestial bodies, which are organized in barchan fields where they interact with each other. Over the last decades, satellite images have been largely employed to detect barchans on Earth and on the surface of Mars, with AI (Artificial Intelligence) becoming an important tool for monitoring those bedforms. However, automatic detection reported in previous works is limited to isolated dunes and does not identify successfully groups of interacting barchans. In this paper, we inquire into the automatic detection and tracking of barchans by carrying out experiments and exploring the acquired images using AI. After training a neural network with images from controlled experiments where complex interactions took place between dunes, we did the same for satellite images from Earth and Mars. We show, for the first time, that a neural network trained properly can identify and track barchans interacting with each other in different environments, using different image types (contrasts, colors, points of view, resolutions, etc.), with confidence scores (accuracy) above 70%. Our results represent a step further for automatically monitoring barchans, with important applications for human activities on Earth, Mars and other celestial bodies.

show abstract

Barchan Dunes Cruising Dune‐Size Obstacles

Abstract: Barchans are crescent-shaped dunes that grow in gaseous or liquid environments under one-directional flows and limited amount of available grains, being frequently found on Earth, Mars and other celestial bodies (

Cited by 3 publications

References 35 publications

Detection and tracking of barchan dunes using Artificial Intelligence

Detection and tracking of barchan dunes using Artificial Intelligence

Dataset of turbulent flow over interacting barchan dunes

Detection and tracking of barchan dunes using artificial intelligence

Contact Info

Product

Resources

About