Combining the analysis of socioeconomic and ecological networks with geographic information systems (GIS) one can map and evaluate how these interconnected networks can contribute to the management and maintenance of the coastal resources quality and ecosystem services considering the spatial heterogeneity in a socio-ecological scenario. We tried this in areas located in the southern portion of the Rio de Janeiro state coast – Brazil. The aim of this paper is to show the potential application of multilayer networks on ecosystem-based management, ecology and conservation biology. The available data were categorized from each municipality based on information about the existing socioeconomic activities and previous surveys of biota and environmental resources uses. In addition, an initial map of ecosystem services was generated as a method to link both subsystems: socio-economic and ecological. Finally, we discuss the use of our approach in decision making and governance to explore a more sustainable future development in this field and area.

The paper introduces the Oil-Slick Hub (OSH), a computational platform to facilitate the data visualization of a large database of petroleum signatures observed on the surface of the ocean with synthetic aperture radar (SAR) measurements. This Internet platform offers an information search and retrieval system of a database resulting from >20 years of scientific projects that interpreted ~15 thousand offshore mineral oil “slicks”: natural oil “seeps” versus operational oil “spills”. Such a Digital Mega-Collection Database consists of satellite images and oil-slick polygons identified in the Gulf of Mexico (GMex) and the Brazilian Continental Margin (BCM). A series of attributes describing the interpreted slicks are also included, along with technical reports and scientific papers. Two experiments illustrate the use of the OSH to facilitate the selection of data subsets from the mega collection (GMex variables and BCM samples), in which artificial intelligence techniques—machine learning (ML)—classify slicks into seeps or spills. The GMex variable dataset was analyzed with simple linear discriminant analyses (LDAs), and a three-fold accuracy performance pattern was observed: (i) the least accurate subset (~65%) solely used acquisition aspects (e.g., acquisition beam mode, date, and time, satellite name, etc.); (ii) the best results (>90%) were achieved with the inclusion of location attributes (i.e., latitude, longitude, and bathymetry); and (iii) moderate performances (~70%) were reached using only morphological information (e.g., area, perimeter, perimeter to area ratio, etc.). The BCM sample dataset was analyzed with six traditional ML methods, namely naive Bayes (NB), K-nearest neighbors (KNN), decision trees (DT), random forests (RF), support vector machines (SVM), and artificial neural networks (ANN), and the most effective algorithms per sample subsets were: (i) RF (86.8%) for Campos, Santos, and Ceará Basins; (ii) NB (87.2%) for Campos with Santos Basins; (iii) SVM (86.9%) for Campos with Ceará Basins; and (iv) SVM (87.8%) for only Campos Basin. The OSH can assist in different concerns (general public, social, economic, political, ecological, and scientific) related to petroleum exploration and production activities, serving as an important aid in discovering new offshore exploratory frontiers, avoiding legal penalties on oil-seep events, supporting oceanic monitoring systems, and providing valuable information to environmental studies.

Hydrogen is taking a significant lead as a complementary energy carrier. One of the most significant structural challenges in the hydrogen supply chain is storing large volumes to ensure stability between generation, delivery, and utilization. In this context, geological storage in salt caverns stands out as the most promising technology. Salt caverns mined by leaching have unique physicochemical characteristics such as negligible permeability under high gas pressures (avoiding leakage), self-healing, higher levels of stability, and stress safety shield due to the creep phenomenon. Also, it allows higher injection and withdrawal ratios of Hydrogen, meeting cycles between demand and production, a minor need for cushion gas, and more controllable construction from the point of view of monitoring and tightness. At the end of the operational life of the storage system, the cushion gas can be extracted just by injecting brine into the cavern. This article presents a geomechanical case study of hydrogen storage in salt caverns in a speculative geological site within the boundary limits found in evaporite basins (Moriak 2008, 2012). It will also be presented the design of caverns in the same geological site to store natural gas with high content of CO2. It will demonstrate the patented technology of gravitational separation of natural gas and CO2 that occurs inside the salt caverns, as the density of the CO2 is larger than the natural gas (Costa, 2018).

The west side of the Antarctic Peninsula (AP) has shown great variability since the middle of the last century characterized by warming mainly because of the oceanic and atmospheric effects such as the disintegration of floating ice and the strength of westerly winds. Here, we used two climatic databases (reanalysis from 1979 to 2020 and surface stations from 1947 to 2020) to investigate trends in extreme air temperatures and wind components in the oceanic region between 55° S and 70° S in the west (75° W) and in the east sector (45° W) and over the AP (60° W). Non-parametric statistical trend tests and extreme value approaches are used. A set of annual, monthly, and seasonal series are fitted. The extremal index is applied to measure the degree of independence of monthly excesses over a threshold considered extreme events. Increasing trends are verified in the annual and monthly temperature and wind series. The greatest trends are observed for seasonal series from reanalysis without change-point in summer and winter. Decreasing trends are observed for maximum temperature in summer and positive trends mainly for the westerly winds over the AP. But in winter, the maximum temperature shows an increasing trend also over the AP. Most of reanalysis seasonal minimum temperature and wind components as well as maximum and minimum temperatures from stations present increasing trends with change-point but tend to stability after the breakpoints. The generalized distribution (GEV) is used to fit temperatures and westerly wind between South America (SA) and north of the AP. The 100-year return levels exceed the maximum value of the maximum temperature in Esperanza and maximum westerly winds at several grid points. Pareto and Poison distributions are applied for the maximum temperatures from stations and the 100-year return levels are not exceeded. Our findings show significant positive trends for monthly wind components near the SA in the region of the westerly winds whose changes in position influence directly the SAM, which modifies the atmospheric patterns in the South Hemisphere (SH). A predominance of seasonal warming is identified, which may impact the climate with consequences not only locally but also in other regions.

In a world of energy transition and net zero pledges, low-carbon energy solutions are central in the fight against climate change. Hydrogen plays a key role in a clean energy future, but there are still economic and infrastructural challenges to be overcome. Hydrogen storage in large volumes is one of the value chains current limitations. This paper presents a feasibility study of an offshore blue or green hydrogen storage in salt caverns created by leaching, within potentially identifiable salt deposits extent of the Gulf of Mexico coastline (US). In this case study, the hydrogen station will have caverns to store hydrogen and some caverns to dispose of CO2 from the blue hydrogen (Carbon Capture and Storage – CCS technology). The construction design includes a fixed platform for the H2 HUB and a jack-up platform for drilling. It presents the conceptual design of wells for leaching the caverns and hydrogen injection and withdrawal cycles.

This article presents a geomechanical appraisal of green hydrogen (H2) storage in salt caverns opened by solution mining as a technical contribution to carbon footprint reduc-tion. The location of the salt cavern is speculative, within possible limits to be found in the salt deposits in the Gulf of Mexico of the USA, as the aim is to demonstrate the technical feasibility of the concept. It presents the conceptual design of the wells used for the so-lution mining of the caverns and the operation cycle of injection and withdrawal of hydrogen. The contribution of the study presented stems from the methodology adopted in the simulation of the geomechanical structural behavior of the salt cavern and in its design for storing hydrogen, which has thermomechanical properties more complex than natural gas. The numerical simulation considers the nonlinear physical viscoelastic and elasto-plastic phenomena, with different constitutive laws for representing the geomechanical behavior of geomaterials. The constitutive laws based on deformation mechanisms are used (multi-mechanisms of deformation -M.D.) to simulate the creep of the salt rock. The article also presents a protocol for sizing the caverns, considering more than 40 years of experience in the design of conventional and solution mining of rock salt. It presents the concept of admissible halite creep strain and safety factors necessary to establish a stress belt that avoids hydrogen leaks at all stages of cavern construction and hydrogen storage. Using this methodology, the authors found that the cavern studied (220 m in height and 95 m in diameter) can hold 11,968,000 kg of working hydrogen.(c) 2022 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

The tropical climate of the metropolitan region of Rio de Janeiro is especially susceptible to air pollutants such as Ozone and Particulate Matter, which are directly connected to serious cardiopulmonary illnesses.The goals of the present work were: to explore the local meteorological data to find useful patterns among the information and to exam the performance of an ensemble model of Recurrent Neural Networks on the prediction of daily maximum pollutant levels.The analyzed dataset is provided by the Rio de Janeiro local government and it is composed by hourly-levels for pollutants and meteorological features from eight different locations.The Spearman correlation test among the variables of different stations showed that adjacent locations have similar data, with values up to 95% of correlation depending on the examined variable.The experiments showed that the ensemble model has superior performance to simpler models in 3 out of 4 studied scenarios.

Social media has become integral to human interaction, providing a platform for communication and expression. However, the rise of hate speech on these platforms poses significant risks to individuals and communities. Detecting and addressing hate speech is particularly challenging in languages like Portuguese due to its rich vocabulary, complex grammar, and regional variations. To address this, we introduce TuPy-E, the largest annotated Portuguese corpus for hate speech detection. TuPy-E leverages an open-source approach, fostering collaboration within the research community. We conduct a detailed analysis using advanced techniques like BERT models, contributing to both academic understanding and practical applications

A few decades ago, the classification of ships by means of their acoustics signature depended on the trained ears of SONAR system operators. With the advances of machine and deep learning techniques, new methods of classification were proposed in order to assist the operator to identify and classify the acoustic event. In this scenario, this paper presents a passive SONAR classification method based on Cyclostationary Analysis and Convolutional Neural Networks. The Spectral Coherence of the ship-radiated noise was extract, and served as input for a modified MobileNetV2 Convolutional Neural Network classifier. The method was benchmarked in two different dataset and was able to discriminate different classes. In parallel, another three classifiers based on Support Vector Machine were developed. Comparison with previous articles that used the same database was made, as well as, an evaluation of noise immunity was conducted. It was observed that the proposed method presented higher accuracy, even for low signal-to-noise ratios.

Sea-surface petroleum pollution is observed as “oil slicks” (i.e., “oil spills” or “oil seeps”) and can be confused with “look-alike slicks” (i.e., environmental phenomena, such as low-wind speed, upwelling conditions, chlorophyll, etc.) in synthetic aperture radar (SAR) measurements, the most proficient satellite sensor to detect mineral oil on the sea surface. Even though machine learning (ML) has become widely used to classify remotely-sensed petroleum signatures, few papers have been published comparing various ML methods to distinguish spills from look-alikes. Our research fills this gap by comparing and evaluating six traditional techniques: simple (naive Bayes (NB), K-nearest neighbor (KNN), decision trees (DT)) and advanced (random forest (RF), support vector machine (SVM), artificial neural network (ANN)) applied to different combinations of satellite-retrieved attributes. 36 ML algorithms were used to discriminate “ocean-slick signatures” (spills versus look-alikes) with ten-times repeated random subsampling cross validation (70-30 train-test partition). Our results found that the best algorithm (ANN: 90%) was >20% more effective than the least accurate one (DT: ~68%). Our empirical ML observations contribute to both scientific ocean remote-sensing research and to oil and gas industry activities, in that: (i) most techniques were superior when morphological information and Meteorological and Oceanographic (MetOc) parameters were included together, and less accurate when these variables were used separately; (ii) the algorithms with the better performance used more variables (without feature selection), while lower accuracy algorithms were those that used fewer variables (with feature selection); (iii) we created algorithms more effective than those of benchmark-past studies that used linear discriminant analysis (LDA: ~85%) on the same dataset; and (iv) accurate algorithms can assist in finding new offshore fossil fuel discoveries (i.e., misclassification reduction).

No Brasil, os cidadãos podem fazer denúncias de irregularidades na Administração Pública. Porém, para serem apuradas, essas denúncias precisam de uma análise prévia. Essa análise é custosa e considera outras informações que não estão nos textos das denúncias. Sendo assim, o objetivo dessa pesquisa é desenvolver um modelo de classificação de denúncias que é composto pela combinação de outros dois modelos: um baseado em um conjunto de dados estruturados, que são obtidos a partir de elementos extraídos dos textos das denúncias e complementados com informações de bases de dados externas e outro obtido pelo processamento direto dos textos das denúncias.

Abstract. The practical feasibility of neural networks models for data assimilation using local observations data in the WRF model for the Rio de Janeiro metropolitan region in Brazil is evaluated. Surface and multi-level variables retrieved from airport meteorological stations are used: air temperature, relative humidity, and wind (speed and direction). Also, 6-hour forecast from WRF high-resolution simulations are used – domain centered in the Rio de Janeiro city with nested grids of 8 and 2.6 km. Periods of 168 h from 2015–2019 are used with 6 h and 12 h assimilation cycles for surface and upper-air data, respectively, applied to 6-hour forecast fields. The observed data (interpolated to grid points close to airport locations and influence computed in its surroundings) and short-range forecasts are used as input for training model and the 3D-Var analysis on 6-hour forecast fields for each grid point is used as target variable. The neural network models are built using two different approaches: WEKA mul- tilayer perceptron model and TensorFlow’s deep learning implementation. The year of 2019 is used as an independent dataset for forecast validation from the trained models. Results employing 6-hour forecast fields with neural network models are able to emulate the 3D-Var results for surface and multi-level variables, with better results for the NN-TensoFlow implementation. The main result refers to CPU time reduction enabled by the neural networks models, reducing the data assimilation CPU-time by 121 times and 25 times for NN-TensorFlow and NN-WEKA, respectively, in comparison to the 3D-Var method under the same hardware configurations.

O ordenamento jurídico brasileiro permite que qualquer cidadão faça denúncias sobre irregularidades que estejam acontecendo na Administração Pública. No entanto, o volume de informações presentes nos textos das denúncias torna o seu tratamento muito custoso. Dessa forma, surge a necessidade de métodos de sumarização capazes de resumir os textos das denúncias. O objetivo desse artigo é propor e avaliar duas estratégias de sumarização de denúncias: uma baseada no modelo de linguagem BERT e outra em frequência de palavras. O estudo concluiu que, para o propósito em questão, os resumos gerados pelo modelo BERT eram melhores que os gerados pela frequência de palavras.

The impacts of aviation on the climate contribute not only to regional but also global climate change because of emissions of carbon dioxide (CO2), nitrogen oxides (NOx), water vapour, sulphates and soot. Aviation is suffering a large increase in recent years and as result there is a consequent increase in emissions of these air pollutants. Air pollution is definitely one of the most significant effects of aviation's impact on the climate, but regional environmental changes caused by an airport situated in specific areas are also a challenge for this transport sector. The identification of the trajectories of these pollutants leads to the implementation of measures to mitigate their harmful effects. The highest exposure levels of air pollution in airports and near them are found in the Landing and Take-off (LTO) cycle responsible for negative impacts on air quality. The city of Rio de Janeiro situated in the coastal area of the Southeast region of Brazil, has two major airports; an International airport and one for domestic flights. Both are near the Guanabara Bay (GB), in Metropolitan Region of Rio de Janeiro (MRRJ). In this research, the pollutant trajectories emitted by these two airports are verified, using the Brazilian Regional Atmospheric Modelling System (BRAMS) to generate wind fields in the MRRJ. The pollutant trajectories are calculated from the wind fields, using a 3D kinematic trajectories Lagrangian model. Atmospheric instability indices are tested from the BRAMS simulations to verify the days with more stable atmospheric conditions in winter month, being the Total Totals index (TT) more appropriate for the purpose of this study. Results show that the cities of Rio de Janeiro and Duque de Caxias, in the western side of the MRRJ, are critical points continually affected by pollutant transport because of the prevailing meteorological conditions, harming the air quality in the region. These models captured the influence of meso and large scale systems, showing the dependence of daily and seasonal variations in the trajectories of pollutants and, therefore, they are important tools in decision-making for the control of emissions, contributing to better management of urban air quality. At a time of great demand, it is essential to create solutions focused in long-term prosperity of aicraft transport and they must be synchronized with standards of environmental protection.

The southeastern Brazilian coast is a vulnerable region to the development of severe storms, mainly caused by the passage of cold fronts and extratropical cyclones. In the last decades, there has been an increase in the occurrence of subtropical cyclones. This study investigates trends and climatic variations, analyzing surface meteoceanographic series at six grid points from the reanalysis databases of ERA-Interim and ERA5 (European Center for Medium-Range Weather Forecasts (ECMWF)) from 1979 to 2018 over the ocean region bounded, approximately, at 18°S, 25°S, and 37ºW, 45ºW (between the states of Espírito Santo, Rio de Janeiro, and São Paulo). Non-parametric statistical tests and the generalized extreme value distribution are employed for annual, seasonal, and daily maxima/minima. The numbers of occurrence of extreme values, as well as the extremal index, are also estimated in order to better understand the behavior of extremes. Annual maximum sea-surface temperature anomalies of the ERA-Interim databases show very low negative values, mainly at the beginning of measurements (between 1979 and 1982), leading to high positive trend values. The results are compared to the updated data from ERA5 which have anomalies that are more homogeneous with positive trends but without statistical significance. The other meteorological series of the ERA-Interim does not present discrepancies. Only the maximum anomalies of air temperature have significant annual and seasonal positive trends at grid points near the coast of Rio de Janeiro and São Paulo. Despite that the analyses for pressure and wind speed anomalies do not indicate significant trends, they present increases in the interdecadal pattern of the numbers of occurrence of extreme percentiles for almost every grid point. Return levels for 10, 25, 50, 75, and 100 years are estimated at each grid point, and many maximum/minimum peaks are close to the return levels for 100-year return periods. The extremal index suggests average cluster sizes associated with no predominance of clustering for the extreme percentiles, which represents weak dependence between the exceedances. These results characterize some independence between extreme meteorological events such as the event that has been taking place in the region. The occurrence of maximum daily wind speed peaks calculated in austral spring, whose values exceeded the previous ones, is identified at three grid points near the southeast Brazilian coast, caused by the passage of the subtropical cyclone "Deni," which occurred in November 2016.

The e-sic system aims to centralize requests for access to information addressed to the Brazilian Federal Executive. However, the volume of requests received can be an impediment to responses to those requests. The purpose of this article is to create an automatic classifier for these requests. For that, they were analyzed as architectures of the Convolutional Neural Network (CNN) and of Long Short Term Memory (LSTM), as well as a combination of these two architectures in order to identify the best architectures to this problem. The metrics used to evaluate the results were the area under curve roc and accuracy, and the error function used was cross entropy. The study concluded that the CNN network performed the best. Thus, the main contribution of this article is the identification of the most appropriate network architecture for classifying texts of interaction between citizens and government written in Portuguese.

Web Application Firewalls penalizes everyone, including latency in all requests, whether they are malicious or not. Several studies have reported the benefits of using Machine Learning to extract new rules to detect malware and malicious web requests. However, comparing the metrics of the models with their use of computational resources remains to be accomplished. This work aims to show a distributed WAF architecture, using ML classifiers as one of its components. Instead of having an enforcement point that analyzes the complete HTTP protocol for violations in this architecture, we have a trained classifier to detect them. The first part of this work verifies the viability of using classifiers based on their metrics, such as accuracy and recall. We analyze two datasets and make comparisons about their use. The second part of this paper compares ML models' prediction processing time and a rules-based engine's processing time. The classifiers used in this paper had a processing time of about 18x less than a rule-based engine. We also show that a classifier can find errors in the classification of a dataset generated by a WAF based on rules. We present samples and experimental codes to show the difference in approaches.

Linear discriminant analysis (LDA) is a mathematically robust multivariate data analysis approach that is sometimes used for surface oil slick signature classification. Our goal is to rank the effectiveness of LDAs to differentiate oil spills from look-alike slicks. We explored multiple combinations of (i) variables (size information, Meteorological-Oceanographic (metoc), geo-location parameters) and (ii) data transformations (non-transformed, cube root, log10). Active and passive satellite-based measurements of RADARSAT, QuikSCAT, AVHRR, SeaWiFS, and MODIS were used. Results from two experiments are reported and discussed: (i) an investigation of 60 combinations of several attributes subjected to the same data transformation and (ii) a survey of 54 other data combinations of three selected variables subjected to different data transformations. In Experiment 1, the best discrimination was reached using ten cube-transformed attributes: ~85% overall accuracy using six pieces of size information, three metoc variables, and one geo-location parameter. In Experiment 2, two combinations of three variables tied as the most effective: ~81% of overall accuracy using area (log transformed), length-to-width ratio (log- or cube-transformed), and number of feature parts (non-transformed). After verifying the classification accuracy of 114 algorithms by comparing with expert interpretations, we concluded that applying different data transformations and accounting for metoc and geo-location attributes optimizes the accuracies of binary classifiers (oil spill vs. look-alike slicks) using the simple LDA technique.

Abstract The impact of the data assimilation process of air temperature and relative humidity from surface meteorological stations and sounding at airports in the terminal area of Rio de Janeiro is evaluated using the Weather Research and Forecast Data Assimilation system. Synthetic data of temperature, relative humidity and wind are generated in the locations of airport sensors by applying a white-noise perturbation in the forecast data. Results show a positive overall impact of the assimilation process with the removal of part of the noise in the observation data but keeping the effect of local conditions in the later timesteps of the simulation. In addition, with the assimilation process there is a global reduction of the error between the analysis data and the observation data. In the future, a neural network will be trained to emulate the data assimilation process to speed-up the assimilation process in the WRF model.

According to data from the last National Health Survey (PNS), conducted in 2013 by the Brazilian Institute of Geography and Statistics (IBGE) in partnership with the Ministry of Health, 7.6% of people aged 18 and over received diagnosis of depression. Therefore, based on this research, the purpose of this study was to identify factors that may be relevant to a possible diagnosis of depression, using machine learning techniques. The binary logistic regression model was chosen as the machine learning technique, with progressive and regressive methods for selecting variables and a model built by the researcher, generating seven different models. The model’s performance evaluation was made by comparing some metrics such as Cox-Snell R2 and Nagelkerke R2, which presented remarkably close results. Based on these models, 37 explanatory variables were selected which were applied to a new logistic regression model. The results showed that some variables significantly increased the chance of a positive diagnosis of depression as well as some variables were indicative of a reduction in the chances of this diagnosis.