Banca de DEFESA: MARCOS VINICIUS GOMES JACINTO

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : MARCOS VINICIUS GOMES JACINTO
DATE: 26/01/2022
TIME: 08:30
LOCAL: videoconferência
TITLE:

Karstified Zone Interpretation Using Convolutional Neural Networks and Model Interpretability
with Explainable AI

KEY WORDS:

Ground Penetrating Radar; Karstified Zones; Deep Learning; Explainable AI.

PAGES: 52
BIG AREA: Ciências Exatas e da Terra
AREA: Geociências
SUMMARY:

Ground penetrating radar (GPR) can be used to assist in mapping karstified zones in analogs for the characterization and understanding of carbonate reservoirs. With the aid of GPR, it is possible to understand the behavior of karstification processes in carbonates and thus expand the knowledge to the reservoir level. In this context, this study seeks to develop deep learning models based on convolutional neural networks using the U-Net architecture capable of assisting in the mapping of karstified zones imaged through GPR surveys. Moreover, explainable artificial intelligence (XAI) techniques using SHapley additive exPlanation (SHAP) values are applied to improve the interpretability and explainability of the generated models. These techniques were employed in order to assess the rules found by the models, the modeling quality and the presence of biases in the model. Moreover, distinct settings with regard to background SHAP values were tested and compared to assess how they influence model explainability. The SHAP values show that the energy attribute was the feature that provided more information in the modeling and consequently provided a greater weight in the model rules while the other features presented less relevant contributions. Furthermore, the type of sampling used to define the reference values for the SHAP values resulted in different interpretations of the contributions of the features. Finally, we generated a model capable of aiding in mapping karstified zones and used an extremely important technique to promote the understanding of complex models and to allow greater cooperation between experts in the geosciences and results generated through deep learning techniques.

BANKING MEMBERS:
Externa à Instituição - MICHELLE CHAVES KURODA AVANSI - UNICAMP
Interno - 1451214 - ADERSON FARIAS DO NASCIMENTO
Interno - 350640 - FRANCISCO HILARIO REGO BEZERRA