Determining the appropriate constitutive model to describe the behavior of a given material is a fundamental, yet challenging, aspect of rheology. While data-driven methods present a promising path for refining these models, a more in-depth investigation into the capabilities and limitations of emerging techniques is required. This research addresses this gap by employing Universal Differential Equations (UDEs) and differentiable physics to model viscoelastic fluids, merging conventional differential equations with neural networks to reconstruct missing terms in constitutive models. This study focuses on analyzing four viscoelastic models, Upper Convected Maxwell (UCM), Johnson–Segalman, Giesekus, and Exponential Phan–Thien–Tanner (ePTT) using synthetic datasets. The methodology was tested across different experimental conditions, including oscillatory and startup flows. Relative error analyses revealed that the UDEs framework maintains low and stable errors (below 0.3%) for the UCM, Johnson–Segalman, and Giesekus models under various conditions, while exhibiting higher but consistent errors (4%) for the ePTT model due to its strong nonlinearity. These findings highlight the potential of UDEs in fluid mechanics while also identifying critical areas for methodological improvement. Additionally, a model distillation approach was employed to extract simplified models from complex ones, emphasizing the versatility and robustness of UDEs in rheological modeling.

The application of deep learning algorithms to Earth observation (EO) in recent years has enabled substantial progress in fields that rely on remotely sensed data. However, given the data scale in EO, creating large datasets with pixel-level annotations by experts is expensive and highly time-consuming. In this context, priors are seen as an attractive way to alleviate the burden of manual labeling when training deep learning methods for EO. For some applications, those priors are readily available. Motivated by the great success of contrastive-learning methods for self-supervised feature representation learning in many computer-vision tasks, this study proposes an online deep clustering method using crop label proportions as priors to learn a sample-level classifier based on government crop-proportion data for a whole agricultural region. We evaluate the method using two large datasets from two different agricultural regions in Brazil. Extensive experiments demonstrate that the method is robust to different data types (synthetic-aperture radar and optical images), reporting higher accuracy values considering the major crop types in the target regions. Thus, it can alleviate the burden of large-scale image annotation in EO applications.

The use of priors to avoid manual labeling for training machine learning methods has received much attention in the last few years. One of the critical subthemes in this regard is Learning from Label Proportions (LLP), where only the information about class proportions is available for training the models. While various LLP training settings verse in the literature, most approaches focus on bag-level label proportions errors, often leading to suboptimal solutions. This paper proposes a new model that jointly uses prototypical contrastive learning and bag-level cluster proportions to implement efficient LLP classification. Our proposal explicitly relaxes the equipartition constraint commonly used in prototypical contrastive learning methods and incorporates the exact cluster proportions into the optimal transport algorithm used for cluster assignments. At inference time, we compute the clusters' assignment, delivering instance-level classification. We experimented with our method on two widely used image classification benchmarks and report a new state-of-art LLP performance, achieving results close to fully supervised methods.

One of the consequences of climate change is an observed increase in the frequency of extreme climate events. That poses a challenge for weather forecast and generation algorithms, which learn from historical data but should embed an often uncertain bias to create correct scenarios. This paper investigates how mapping climate data to a known distribution using variational autoencoders might help explore such biases and control the synthesis of weather fields towards scenarios with more frequent extreme weather events. We experimented using a monsoon-affected precipitation dataset from southwest India, which should give a roughly stable pattern of rainy days and ease investigating the suitability of our solution. We report compelling results showing that mapping complex weather data to a known distribution implements an efficient control for weather field synthesis towards more (or less) extreme scenarios.

Unmanned aerial vehicles (UAVs) allow on-demand imaging of orchards at an unprecedented level of detail. The automated detection of plantation rows in the images helps in the successive analysis steps, such as the detection of individual fruit trees and planting gaps, aiding producers with inventory and planting operations. Citrus trees can be planted in curved rows that form intricate geometric patterns in aerial images, requiring robust detection approaches. While deep learning methods rank among state-of-the-art methods for segmenting images with particular geometrical patterns, they struggle to hold their performance when testing data differs much from training data (e.g., image intensity differences, image artifacts, vegetation characteristics, and landscape conditions). In this letter, we propose a method to learn geometric features of orchards in UAV images and use them to improve the detection of plantation rows. First, we train a detection encoder–decoder network (DetED) to segment planting rows in RGB images. Then, with labeled data, we train an encoder–decoder correction network (CorrED) that learns to map binary masks with spurious row segmentation geometries into corrected ones. Finally, we use the CorrED network to fix geometric inconsistencies in DetED outcome. Our experiments with commercial plantations of orange trees show that the proposed CorrED postprocessing can restore missing segments of plantation rows and improve detection accuracy in testing data.

Remote sensing imagery from different sensors enables accurate crop monitoring and mapping, supporting efficient and sustainable agricultural practices. This paper proposes a flexible multi-modal Encoder-Decoder architecture to implement and investigate different fusion strategies for crop segmentation using synthetic-aperture radar (SAR) and optical image sequences. The trained model handles each modal individually or both, allowing us to investigate scenarios where one modal is not available. Our architecture consists of two modality-specific encoders, a shared decoder, a fusion module, and three classifiers, one for each modal and one for the fusion output. Also, we propose using a partial loss function that allows training the network with scarce ground truths. The proposed approach was evaluated in a public dataset comprising seven multitemporal SAR images and four multitemporal optical images from a tropical agricultural region in Brazil. We report results for feature and decision fusion strategies and discuss the benefits of using each of them for multi-modal crop segmentation.

Reliable crop mapping is an essential tool for agricultural monitoring and food security. In the tropics, where cloud cover massively affects optical imagery, synthetic-aperture radar (SAR) imagery emerged as a cost-effective alternative for discriminating crops in large scale agricultural regions. Recently, unsupervised deep clustering approaches have emerged as a competitive alternative in several different applications with labeling restrictions. This paper explores this literature and evaluates the feasibility of such methods applied to crop classification in a tropical region from multi-temporal SAR image sequences. We focus on the k-Means-related deep clustering methods, specifically, on Deep Embedding Clustering and Deep K-Means. We report experiments conducted on a public dataset from a tropical region with highly complex crop dynamics. In our experiments the tested unsupervised approaches managed to deliver nearly 78% of supervised counterparts for this task11The source codes are available at https:/github.com/DLoboT/Project_DL_2020.

The definition of reliable velocity functions is paramount for obtaining high-quality poststack seismic data. Velocity functions are commonly created with the interpreter interactively selecting high-energy peaks in velocity spectra and verifying if the derived velocity functions match the traveltime trajectories in the corresponding common midpoint (CMP) gathers. Modern software further allows the interpreter to apply resulting moveout corrections and verify if the desired overall flatness of reflection events is achieved. This very detailed process takes a significant amount of time, not necessarily delivering the globally optimal velocity function, and ultimately impacting the cost and duration of a typical seismic interpretation procedure. In this work, we present a hybrid regression approach based on convolutional neural networks (CNN) to speed up the velocity analysis workflow. The proposed methodology consists of an automatic initial velocity function estimation followed by a supervised refinement process that requires only a handful of gathers to be manually picked. Experiments performed on five field data sets show that the proposed methodology can not only produce human-grade velocity pickings but also outperform the interpreter in some cases, in a fraction of the time taken by the human counterpart.

Seismic interpretation is a complex procedure that depends on many and interdependent data analyses. One of the essential steps in this process is picking horizons in seismic images, which is time-consuming and prone to errors when performed manually. In this context, having a reliable horizon picking tool is fundamental for accurate seismic interpretation. Although several methods for horizon picking have been proposed in the literature and many tools made available in the industry, most require numerous iterations and manual corrections for delivering satisfactory results. In this article, we present a three-step approach that improves the robustness of horizon picking using state-of-art semantic segmentation neural networks followed by geometry-based processing of horizon points to identify and remove outliers. For the well-known Netherlands F3 Block data set, this approach allows accurate results from a few training annotated inlines and delivers geometry-consistent horizons through all the cubes. We further present results for an additional set comprising four cubes with different seismic structures to provide some robustness evidence of our approach. The results reported in this study indicate that the proposed methodology can provide a good trade-off between accuracy and time spent on manually picking horizons.

Seismic exploration is a complex process that depends on different sources of information. An essential one is seismic imaging, and much of its interpretation performance relies on high-quality processing, which is currently still very dependent on prone-to-error human mediation. Automation of such processing steps is necessary to reduce the amount of time to treat seismic data—usually months—and improve the outcome overall quality by reducing the inherent subjectivity in the process. One of the most critical steps in seismic processing is noise suppression, and ground roll is one of the most challenging and everyday noises observed in seismic prestack data. In this article, we propose a self-supervised two-step approach to attenuate ground-roll noise in seismic prestack images. First, we detect ground-roll-affected area using convolutional neural networks, and then, we filter ground-roll noise in the detected area using conditional generative adversarial networks (cGANs). For each of these steps, we propose to build paired noisy/noise-free training sets with no supervision or reference data, hence creating a self-supervised pipeline for filtering ground-roll noise. Our two-stage approach enables noise suppression in the affected area while preserving the signal in unaffected areas. In addition, we propose to refactor conventional qualitative metrics in the industry into quantitative scores disregarding any reference data to evaluate ground-roll suppression for different geologies and report reliable results compared with expert filtering.

The characterization of the subsurface is paramount for the exploration and production life cycle and, more specifically, for the identification of potential hydrocarbon accumulations. In recent years, the oil and gas industry has increased its interest in applying machine learning to accelerate the seismic interpretation process, which is regarded as a time-consuming and human-centered task. Although machine learning has been successfully used in many applications ranging from stratigraphic segmentation to salt dome detection, a usual bottleneck is the need for a large amount of high-quality annotated data. To overcome this, data augmentation approaches are commonly used, and one of the most powerful is synthetic data generation. In addition, sketch-based synthetic seismic images can be used to support image retrieval applications to help oil companies leverage petabytes of seismic data sets. In this context, this letter investigates the generation of synthetic seismic images based on sketches using generative adversarial networks (GANs). To the best of our knowledge, this is the first work to propose such an approach. Experiments with five different sketch types in a public seismic data set indicate that realistic seismic images can be synthesized using rather simple sketches.

Speech recognition technologies in the visual domain currently can only identify words and sentences in still images. Identifying visemes (i.e., the smallest visual units of spoken text) is useful when there are no language models or dictionaries available, which is often the case for languages besides English; however, it is a challenge, as temporal information cannot be extracted. In parallel, previous works demonstrated that exploring data acquired simultaneously under multiple views can improve the recognition accuracy in comparison to single-view data. For many different applications, however, most of the available audio-visual datasets are obtained from a single view, essentially due to acquisition limitations. In this work, we address viseme recognition in still images and explore the synthetic generation of additional views to improve overall accuracy. For that, we use Generative Adversarial Networks (GANs) trained with synthetic data and map from mouth images acquired in a single arbitrary view to frontal and side views - in which the face is rotated vertically at approximately 30°, 45°, and 60°. Then, we use a state-of-art Convolutional Neural Network for classifying the visemes and compare its performance when training only with the original single-view images versus training with the additional views artificially generated by the GANs. We run experiments using three audiovisual corpora acquired under different conditions (GRID, AVICAR, and OuluVS2 datasets) and our results indicate that the additional views synthesized by the GANs are able to improve the viseme recognition accuracy on all tested scenarios.

The synthesis of realistic data using deep learning techniques has greatly improved the performance of classifiers in handling incomplete data. Remote sensing applications that have profited from those techniques include translating images of different sensors, improving the image resolution and completing missing temporal or spatial data such as in cloudy optical images. In this context, this letter proposes a new deep-learning-based framework to synthesize missing or corrupted multispectral optical images using multimodal/multitemporal data. Specifically, we use conditional generative adversarial networks (cGANs) to generate the missing optical image by exploiting the correspondent synthetic aperture radar (SAR) data with a SAR-optical data from the same area at a different acquisition date. The proposed framework was evaluated in two land-cover applications over tropical regions, where cloud coverage is a major problem: crop recognition and wildfire detection. In both applications, our proposal was superior to alternative approaches tested in our experiments. In particular, our approach outperformed recent cGAN-based proposals for cloud removal, on average, by 7.7% and 8.6% in terms of overall accuracy and F1-score, respectively.

Noisy traces, gaps in coverage, or irregular/inadequate trace spacing are common problems in both land and marine surveys, possibly hindering the geological interpretation of an area of interest. This problem has been typically addressed in the literature using prestack data; however, prestack data are not always available. As an alternative, poststack interpolations may aid the geological interpretation by increasing the spatial density of a seismic section and can also be used to reconstruct entire sections by interpolating neighboring traces, reducing field costs. In this letter, we evaluate the performance of conditional Generative Adversarial Networks (cGANs) as an interpolation tool for improving seismic data resolution on a public poststack seismic data set and compare our results with the traditional cubic interpolation. To perform the comparisons, we used structural similarity (SSIM), mean squared error (mse), and local binary patterns (LBPs) texture descriptor. The results show that cGANs outperform traditional algorithms by up to 72% and that the texture descriptor was able to better capture image similarities, producing results more coherent with the visual perception.

Visual Speech Recognition is the ability to interpret spoken text using video information only. To address such task automatically, recent works have employed Deep Learning and obtained high accuracy on the recognition of words and sentences uttered in controlled environments, with limited head-pose variation. However, the accuracy drops for multi-view datasets and when it comes to interpreting isolated mouth shapes, such as visemes, the values reported are considerably lower, as shorter segments of speech lack temporal and contextual information. In this work, we evaluate the applicability of synthetic datasets for assisting recognition of visemes in real-world data acquired under controlled and uncontrolled environments, using GRID and AVICAR datasets, respectively. We create two large-scale synthetic 2D datasets based on realistic 3D facial models - with near-frontal and multi-view mouth images. We perform experiments that indicate that a transfer learning approach using synthetic data can get higher accuracy than training from scratch using real data only, on both scenarios.

Recently, Deep Learning-based methods have obtained high accuracy for the problem of Visual Speech Recognition. However, while good results have been reported for words and sentences, recognizing shorter segments of speech, like phones, has proven to be much more challenging due to the lack of temporal and contextual information. In this work, we address the problem of recognizing visemes, that are the visual equivalent of phonemes-the smallest distinguishable sound unit in a spoken word. Viseme recognition has application in tasks such as lip synchronization, but acquiring and labeling a viseme dataset is complex and time-consuming. We tackle this problem by creating a large-scale synthetic 2D dataset based on realistic 3D facial models, automatically labelled. Then, we extract real viseme images from the GRID corpus-using audio data to locate phonemes via forced phonetic alignment and the registered video to extract the corresponding visemes-and evaluate the applicability of the synthetic dataset for recognizing real-world data.

In recent years, with the popularization of deep learning frameworks and large datasets, researchers have started parallelizing their models in order to train faster. This is crucially important, because they typically explore many hyperparameters in order to find the best ones for their applications. This process is time consuming and, consequently, speeding up training improves productivity. One approach to parallelize deep learning models followed by many researchers is based on weak scaling. The minibatches increase in size as new GPUs are added to the system. In addition, new learning rates schedules have been proposed to fix optimization issues that occur with large minibatch sizes. In this paper, however, we show that the recommendations provided by recent work do not apply to models that lack large datasets. In fact, we argument in favor of using strong scaling for achieving reliable performance in such cases. We evaluated our approach with up to 32 GPUs and show that weak scaling not only does not have the same accuracy as the sequential model, it also fails to converge most of time. Meanwhile, strong scaling has good scalability while having exactly the same accuracy of a sequential implementation.

Having dense and regularly sampled data is becoming increasingly important in seismic processing. However, due to physical or financial constraints, seismic data sets can be often undersampled. Occasionally, these data sets may also present bad or dead traces the geoscientist must deal with. Many works have tackled this problem using prestack data and can be classified in three main categories: wave-equation, domain transform, and prediction-error-filter methods. In this letter, we assess the performance of a conditional generative adversarial network for the interpolation problem in poststack seismic data sets. To the best of our knowledge, this is the first work to evaluate a deep learning approach in this context. Quantitative and qualitative evaluations of our experiments indicate that deep networks may present an interesting alternative to classical methods.

The vast amount of data obtained from current remote sensing data acquisition technologies represents a wealth of useful and affordable geospatial data for policy and decision makers. However, the consequent computational cost of analyzing these data may become prohibitive. This letter extends previous efforts in exploiting distributed processing to speed up the image interpretation process. In this letter, we propose and evaluate a mechanism to exploit task parallelism in addition to data parallelism. Experiments conducted on cloud computing infrastructure, following an object-based interpretation model, demonstrated that substantial performance gains can be obtained with the proposed mechanism.

Advances in remote sensors are providing exceptional quantities of large-scale data with increasing spatial, spectral and temporal resolutions, raising new challenges in its analysis, e.g. those presents in classification processes. This work presents the architecture of the InterIMAGE Cloud Platform (ICP): Data Mining Package; a tool able to perform supervised classification procedures on huge amounts of data, on a distributed infrastructure. The architecture is implemented on top of the MapReduce framework. The tool has four classification algorithms implemented taken from WEKA's machine learning library, namely: Decision Trees, Naïve Bayes, Random Forest and Support Vector Machines. The SVM classifier was applied on datasets of different sizes (2 GB, 4 GB and 10 GB) for different cluster configurations (5, 10, 20, 50 nodes). The results show the tool as a potential approach to parallelize classification processes on big data.