Francisco Fábio de Araújo Ponte

The development and application of predictive models to distinguish seepage slicks from oil spills are challenging, since Synthetic Aperture Radars (SAR) detect these events as dark spots on the sea surface. Traditional Machine Learning (ML) has been used to discriminate the Oil Slick Source (OSS) as natural or anthropic assuming that the samples employed to train and test the models in the source domain (D_S) follow the same statistical distribution of unknown samples to be predicted in the target domain (D_T). When such assumptions are not held, Transfer Learning (TL) allows the extraction of knowledge from validated models and the prediction of new samples, thus improving performances even in scenarios never seen before. A database with 26 geometric features extracted from 6279 validated oil slicks was used to develop predictive models in the Gulf of Mexico (GoM) and its Mexican portion (GMex). Innovatively, these well-trained models were applied to predict the OSS of unknown events in the GoM, the American (GAm) portion of the GoM, and in the Brazilian continental margin (BR). When the D_S and D_T domains are similar, the TL and generalization are null, being equivalent to the usual ML. However, when domains are different but statically related, TL outdoes ML (58.91%), attaining 87% of global accuracy when using compatible SAR sensors in the D_S and D_T domains. Conversely, incompatible SAR sensors produce domains statistically divergent, causing negative transfers and generalizations. From an operational standpoint, the evidenced generalization capacity of these models to recognize geometric patterns across different geographic regions using TL may allow saving time and budget, avoiding the collection of validated and annotated new training samples, as well as the models re-training from scratch. When looking for new exploratory frontiers, automatic prediction is a value-added product that strengthens the knowledge-driven classifications and the decision-making processes. Moreover, the prompt identification of an oil spill can speed up the response actions to clean up and protect sensitive areas against oil pollution.

The amount of data from geochemical analysis using samples collected in oil wells grows simultaneously to the investment in the exploration and production sector. On the other hand, the treatment and interpretation of these results are still very dependent on experts and demand time. With the generation of extensive databases, data mining presents itself as a good alternative to explore them through statistical methods and computational algorithms, providing technological differential and agility to the system. In an experimental way, with data from 200 oils from the Potiguar Basin, these tools were implemented, with the consequent suggestion of a workflow that would, in the end, return a reasonable accuracy in predicting their genetic classification. Using multidimensional scaling (MDS) and clustering (dendrogram and k-means types) from 60 initial attributes, the optimal set was reduced to 26. Applying Machine Learning, 92.50% of median accuracy were obtained in the Decision Tree algorithm, 95.00% in Random Forest and 87.50% in Artificial Neural Network. Comparing to an analysis previously presented at the pertinent literature, the benefits in terms of efficiency can be realized with the adoption of the methodology herein proposed. Keywords: Organic geochemistry; Data Mining; Multivariate Statistics; Workflow.

Distinguishing between natural and anthropic oil slicks is a challenging task, especially in the Gulf of Mexico, where these events can be simultaneously observed and recognized as seeps or spills. In this study, a powerful data analysis provided by machine learning (ML) methods was employed to develop, test, and implement a classification model (CM) to distinguish an oil slick source (OSS) as natural or anthropic. A robust database containing 4916 validated oil samples, detected using synthetic aperture radar (SAR), was employed for this task. Six ML algorithms were evaluated, including artificial neural networks (ANN), random forest (RF), decision trees (DT), naive Bayes (NB), linear discriminant analysis (LDA), and logistic regression (LR). Using RF, the global CM achieved a maximum accuracy value of 73.15. An innovative approach evaluated how external factors, such as seasonality, satellite configurations, and the synergy between them, limit or improve OSS predictions. To accomplish this, specific classification models (SCMs) were derived from the global ones (CMs), tuning the best algorithms and parameters according to different scenarios. Median accuracies revealed winter and spring to be the best seasons and ScanSAR Narrow B (SCNB) as the best beam mode. The maximum median accuracy to distinguish seeps from spills was achieved in winter using SCNB (83.05). Among the tested algorithms, RF was the most robust, with a better performance in 81% of the investigated scenarios. The accuracy increment provided by the well-fitted models may minimize the confusion between seeps and spills. This represents a concrete contribution to reducing economic and geologic risks derived from exploration activities in offshore areas. Additionally, from an operational standpoint, specific models support specialists to select the best SAR products and seasons for new acquisitions, as well as to optimize performances according to the available data.