Recognizing Patterns in Geospatial Data Using Persistent Homology: A Study of Geologic Fractures

Bryant, Kathryn A.; Karimi, Bobak

doi:10.1201/9781315228396-6

Cited by 1 publication

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since its development, PH has been applied in a multitude of fields, such as the identification of cancer cells in medical imagery, e.g., [19,20], characterizing porous material, e.g., [21,22], collective behavior in biology, e.g., [23], and comparing musical pieces [24]. More recently, researchers have also realized the use of PH as an automatic detection tool for geospatial objects in the geosciences, e.g., [25,26], the social sciences, e.g., [27][28][29], and transportation [30]. We hypothesized that the PH analysis of satellite imagery can draw attention to surface features related to O&G wells.…”

Section: Introductionmentioning

confidence: 99%

Harnessing Machine Learning and Data Fusion for Accurate Undocumented Well Identification in Satellite Images

Kadeethum,

Downs

2024

Remote Sensing

View full text Add to dashboard Cite

This study utilizes satellite data to detect undocumented oil and gas wells, which pose significant environmental concerns, including greenhouse gas emissions. Three key findings emerge from the study. Firstly, the problem of imbalanced data is addressed by recommending oversampling techniques like Rotation–GaussianBlur–Solarization data augmentation (RGS), the Synthetic Minority Over-Sampling Technique (SMOTE), or ADASYN (an extension of SMOTE) over undersampling techniques. The performance of borderline SMOTE is less effective than that of the rest of the oversampling techniques, as its performance relies heavily on the quality and distribution of data near the decision boundary. Secondly, incorporating pre-trained models trained on large-scale datasets enhances the models’ generalization ability, with models trained on one county’s dataset demonstrating high overall accuracy, recall, and F1 scores that can be extended to other areas. This transferability of models allows for wider application. Lastly, including persistent homology (PH) as an additional input improves performance for in-distribution testing but may affect the model’s generalization for out-of-distribution testing. A careful consideration of PH’s impact on overall performance and generalizability is recommended. Overall, this study provides a robust approach to identifying undocumented oil and gas wells, contributing to the acceleration of a net-zero economy and supporting environmental sustainability efforts.

show abstract