Most fracture properties, such as orientation and density, are acquired by interpreting data obtained at the wellbores, while fracture properties between wells are typically derived from seismic data. However, this information is sparse or has low resolution leading to the study and analysis of outcrops. The data acquisition in outcrops is facilitated by its 3D representation in Digital Outcrop Models (DOM) obtained from LiDAR and Photogrammetry. It also allows virtual interpretation and fracture detection. In either case, the 3D fracture data need to be clustered in fracture sets to allow the statistical analysis necessary to upscale and resample the DFN. This clusterization is carried out by methods like k-means and fuzzy, however with caveats, like the prior definition of the number of clusters. In this work, we propose the use of agglomerative hierarchical clustering to cluster 3D fracture data obtained by a KD-Tree segmentation algorithm. Results showed that when compared to k-means, the proposed method presented more compact clusters and balance when considering Fisher’s statistics of dispersion.

Hyperspectral images often have low spatial resolution due to the sensor sizes required to capture the required spectral response. Super-resolution (SR) techniques try to mitigate this by injecting more detail in the upscaled image, either with numerical methods or deep learning and Convolution Neural Networks. In the deep learning methods, the models learn image details by inferring a high-resolution (HR) image from a synthetic low-resolution (LR) image that simulates the natural degradation of sensors by applying resampling (to reduce the image detail) and noising (to add small errors and interference). Often disregarded in the literature, the resampling method applied to generate the synthetic image can impact greatly the deep learning model training. This work, evaluate several resampling techniques to measure this impact using the Harvard hyperspectral dataset. Results showed that the Lanczos filter was the best among eight other resampling methods. The Nemenyi and Friedman ranking statistical tests also indicated that the Cubic-Spline, Bicubic, and RMS achieved good results.

Monitoring the available volume of raw water in reservoirs is essential to ensure security of supply to the population. Climate change and global warming had substantially changed the weather bringing constant droughts and unexpected rainfalls, making the correct estimation of water bodies an important matter. The technique for recognizing water bodies is called bathymetry, where by a sonar and embedded global positioning system (GPS) collect data to recreate the depth topography. However, this work is costly and exposes the assessment team to health risks. Therefore, we are proposing a prototype of a semi-automated portable bathymetry equipment to facilitate data collection and thus enable more frequent updates of reservoir volume. The objectives of this work were to construct a reduced model of a vessel and to calibrate an adapted ultrasonic sensor for depth measurement. The ultrasonic sensor mounted on an ARDUINO micro-controller was tested in the FATEC-Jahu's test tank and its readings were compared against measurements made manually. We conclude that the reduced model is stable for data collection with an operational range between 1.0 and 20.0 meters when considering a linear adjustment of the sensor readings achieving an R2 score of 0.9998.

Reservoir rocks have intrinsic properties of porosity and per-meability that make them natural hosts for hydrocarbons, and the estimation of these properties is key to simulating reser-voir models. Additionally, fractures can greatly influence the fluid flow within the reservoir. However, fracture data from reservoirs is often disregarded due to its sub-seismic scale. In this matter, analogue outcrops play an important role in Dis-crete Fracture Network (DFN) modeling which represents the fracture data in terms of their attribute distribution allowing the scaling of the fracture data to reservoir scale which is done mostly by stochastic methods. Recent works have used Gen-erative Adversarial Networks (GANs) to scale porosity data from images, and we propose its use in fracture data from images acquired from Unmanned Aerial Vehicles (UAV) em-ploying a Deep Convolutional GAN (DC-GAN). We obtained similar attribute distribution for fracture aperture showing the viability to replicate statistical behavior.

Exposed rock formations, also know as outcrops, are a great source of geological data, enabling the characterization of fracture networks that are less visible when analyzing reservoir data from seismic and well logs. Remote sensing techniques like LiDAR and UAV Photogrammetry allow the generation of Digital Outcrop Models (DOM) that provide accurate outcrop geometry enabling further investigation of fracture attributes, necessary when creating Discrete Fracture Network (DFN) models and reservoir simulation models. Besides the manual fracture interpretation in DOMs, automatic fracture plane segmentation and clusterization can provide significantly more data. However, the identification of family sets is still done visually in most cases. In this work, we develop a modification to the elbow method using spherical Fisher statistics of dispersion to determine the ideal number of clusters or fracture family sets. We employed this method to cluster fracture families in a point cloud DOM obtained from UAV-SfM processing of a flight over a carbonate outcrop in the Jandaira formation, Northeast Brazil, obtaining clusters with low dispersion values.

Carbonate outcrops are widely studied due to their character-istic analogous to oil and gas reservoirs. Analyzes made with data from these outcrops are used to assist in the description of reservoirs located at great depths. These rocky expo-sures can be easily detected in satellite images using machine learning. Considering the diversity of techniques used in the identification/classification of features on the satellite image data, this work aimed to evaluate the best machine learning technique for identifying carbonate outcrops in Landsat 8 data, considering the carbonate outcrops from the Jandaíra formation, in northeast Brazil. We employed techniques like Grid Search, cross-validation, and validation statistics like Friedman and Nemenyi. Considering the metrics F1 score and Mathews Correlation Coefficient, the MLP technique presented the best results, achieving a F1 score of 0.823, against the SVM with a F1 score of 0.810 and the Random Forest technique with a F1 score of 0.812.

Differently form RGB photos, multi-frame acquisitions of hyperspectral data are unfeasible due to the pushbroom mechanisms of hyperspectral sensors. Therefore, 3D digi-tal surface models including good quality hyperspectral in-formation are available only by integrating 2D images to the point cloud generated using photogrametric cameras or laser scanners. However, geometric differences presented by sen-sor mechanisms resulting in varied perspectives of the same objects present on the scene deeply harm the spatial registration, and thus, the post integration procedure. In this paper we suggest a pre-processing step aiming to adjust objects to the same geometric perspective in order to later integrate the RGB cloud mesh to the hyperspectral data in a more efficient manner. We firstly build the RGB point cloud for later simu-lating the same perspective of push-broom sensor generating a RGB orthomosaic similar to the hyperspectral image. Pre-liminary results indicate an increasing in the number of tie points when registering is performed using the resulting syn-thetic sampling compared to the registration of original data.

Oil and gas reservoirs are well studied in petroleum engineering, using seismic data to estimate fluid flow and well placement. However, seismic data cannot capture fractures due to their scale, and fractures may affect rock porosity and permeability. Consequently, rock fracture segmentation and quantification from aerial images of analogous outcrops can input essential information into those studies. This paper presents a new method, namedinteractive Forest Growing(iFG), for fracture segmentation. The image is initially segmented into superpixels, defining a superpixel graph. The user selects seed superpixels, a path-cost threshold, and fractures are delineated by growing one optimum-path tree from each seed with path costs limited to the selected threshold. iFG considerably increases efficiency while reducing human effort in fracture segmentation compared to pixel-by-pixel manual annotation. We evaluate iFG with three specialists and against aninteractive Region Growing(iRG) method using 15 images to measure bias in user interpretations, verify efficiency gain over a similar approach, and generate a dataset with consolidated annotation for future work. The experiments show that iFG reduces user interventions from 19% to 33% compared to iRG, users with more experience in fracture analysis complete segmentation 4-5 times faster, and segmentation effectiveness is independent of user experience since the average F1 scores between users uing both methods ranged from 0.966 to 0.979, allowing us to create a consolidated segmentation.

The present study explores the capabilities of a low-cost and standard drone for the generation of a mixed dataset processed as an orthophotomosaic, and surface exposure mesh over the inaccessible wave-washed Wildlife Refuge of Ilha dos Lobos in the southern Brazilian coast. The area comprises an important Marine Protected Area used as a seasonal resting refuge of South American sea lions and fur seals that is continuously washed by wave actions, restricting human access for conventional field mapping. The results have estimated a total surface exposure of the island of 20,806.8 m2, which is an increase of 14.01 % on the total area relative to the most exposed single survey done so far. In futures works, these results will provide data for the geological characterization of the island, which will increase the information on the environment given support to the Wildlife Refuge of Ilha dos Lobos management plan.

Fractures affect the intrinsic properties of permeability and porosity of reservoir geobodies, making its network characterization an important task for fluid flow modeling. Direct acquisition of data on reservoirs is labor-intensive and generally produces sparse information. Thus, the study of analogue outcrops with similar characteristics is often carried out by using unmanned aerial vehicle image acquisition and digital photogrammetry. However, the accurate automatic recognition of the fractures network over the outcrop images remains a challenge. Image segmentation methods based on convolution neural networks (CNNs) were successfully applied in medicine, biology, and other areas, however, not yet in geological fracture detection. This work proposes the validation of two popular CNNs - Segnet and Unet - for pixel-to-pixel segmentation targeting fracture detection. Initial results showed acceptable scores of the metrics mean intersection over union (mIoU) and dice intersection (F1) in both CNNs.

Very high spatial resolution data seems to reach its maximum for orbital images due to unavoidable atmospheric interactions. At the same time, special hyperspectral cameras are being developed to operate on-board manned or unmanned aircrafts at a fixed optics, which prevents its using for imaging near objects in laboratory conditions. Both limitations can only be surpassed by using super-resolution principles. In this paper, we present a multi-looking approach for enhancing the spatial resolution of images acquired by systems that exhausted their natural ability to provide finer images. The method exploits multiple image takes with controlled spatial differences to produce a higher resolution output. Experiments with static hyperspectral sensor and synthetic data have proven the approach is sound and robust to many applications (e.g., rock samples).

The Total Electron Content (TEC) derived from Global Navigation Satellite System (GNSS) data processing has been used as a tool for monitoring earthquakes. The purpose of this study is to bring an alternative approach to the prediction of earthquakes and to determine their magnitudes based on Artificial Neural Networks (ANN) and ionospheric disturbances. For this, the Vertical Total Electron Content (VTEC) data from the National Oceanic and Atmosphere Administration (NOAA) were used to train the ANN. Results show that the ANN process achieved an accuracy of 85.71% in validation assessment to predict Tres Picos Mw=8.2 earthquake from 1:30 UTC to 04:00 UTC, approximately 3 hours before the seismic event. For magnitude classification, the ANN achieved an accuracy of 94.60%. The Matthews Correlation Coefficient (MCC) which takes into account all true/false positives and negatives was also evaluated and showed promising results.

One of the main difficulties in the inspection of Bridges/Viaducts by observation is inaccessibility or lack of access throughout the structure. Mapping using remote sensors on Unmanned Aerial Vehicles (UAVs) or by means of laser scanning can be an interesting alternative to the engineer as it can enable more detailed analysis and diagnostics. Such mapping techniques also allow the generation of realistic 3D models that can be integrated in Virtual Reality (VR) environments. In this sense, we present the ImSpector, a system that uses realistic 3D models generated by remote sensors embedded in UAVs that implements a virtual and immersive environment for inspections. As a result, the system provides the engineer a tool to carry out field tests directly at the office, ensuring agility, accuracy and safety in bridge and viaduct inspections.