Eventos Anais de eventos
COBEM 2023
27th International Congress of Mechanical Engineering
Machine Learning for barchan dune detection
Submission Author:
Esteban Andres Cúñez Benalcazar , SP
Co-Authors:
Esteban Andres Cúñez Benalcazar, Erick de Moraes Franklin
Presenter: Esteban Andres Cúñez Benalcazar
doi://10.26678/ABCM.COBEM2023.COB2023-0088
Abstract
Barchan dunes are commonly found on the surface of planets such as Earth and Mars, playing an important role in the evolution of landscapes and ecosystems. Over the last few decades, imagery from remote sensing has been a valuable tool for investigating the morphodynamics of barchans, but their complex interactions and transformations make them sometimes difficult to be detected. In this study, we use the capabilities of Artificial Intelligence (AI) and neural networks to develop an accurate and efficient model for detecting dunes formed in an experimental rectangular channel. First, we collected a dataset of barchan images that we used to train and evaluate the accuracy of our model, based on convolutional neural network (You Only Look Once-YOLO) method, which can can accurately determine if an image contains dunes with an efficient success rate. We processed the images and data in Python using some of its libraries such as tensor flow, keras, opencv, numpy and pandas. Next, we created a database to store and organize tagged images, and then, to compute the main results from the automatic detection of dunes such as dimensions, shapes and other properties of barchan dunes. From this technique, the dataset obtained in this study can be used for further studies and applications related to dune detection in remote locations, providing a valuable resource for researchers. Overall, our research shows the potential of artificial intelligence and neural networks in the fields of Physics and Geoscience, and how they can be used to overcome the challenges of studying complex natural phenomena on Earth and on other celestial bodies. The ability to accurately identify and study dunes using AI can improve our understanding of surface processes that are important to shape our landscape. We plan to continue investigating the possibilities to use Artificial Intelligence in other types of dunes and natural formations.
Keywords
Artificial Intelligence, barchan dunes, YOLO
