Abstract Monitoring solar phenomena, such as sunspots and active regions, is crucial for ensuring astronaut safety, telecommunications reliability, and predicting terrestrial events like auroras. Traditional methods for detecting these phenomena have limitations in accuracy and baseline maintenance. This paper presents a novel deep learning object detection method that leverages multispectral image data from satellites to enhance the detection of "sunspots" and active regions. Utilizing images from the SDO satellite and annotations from the DeepSDO dataset, we constructed a new dataset composed of aligned observations from HMI Ic, AIA 211\,\AA, and AIA 335\,\AA. We adapted and developed a stock YOLOv5-based model capable of handling and fusing any number of input images. Two fusion methodologies, early and late fusion, and three different fusion modules --- CatFuse (simple concatenation), CBAMC (CBAM-based module), and TransEnc (transformer encoder) --- were implemented and tested. Our critical evaluation of the models, supported by statistical analysis, proved the developed models to be statistically significantly different among themselves at a p-value of 0.05, and helped us to identify the best-performing model: CatFuse with early fusion, which achieved a [email protected]:0.95 of 0.52 and a [email protected] of 0.94. This result was marginally better than the best baseline (YOLOv5 with a single HMI image) and comparable to other state-of-the-art models, demonstrating a modest but consistent improvement of multispectral image fusion for this task.

Space weather refers to the dynamic conditions in the solar system, particularly the interactions between the solar wind -a stream of charged particles emitted by the Sun -and the Earth's magnetic field and atmosphere.Accurate space weather forecasting is crucial for mitigating potential impacts on satellite operations, communication systems, power grids, and astronaut safety.However, existing solar wind coronal models like MULTI-VP require substantial computational resources.This paper proposes a Physics-Informed Neural Network (PiNN) as a faster yet accurate alternative that respects physical laws.PiNNs blend physics and data-driven techniques for rapid and reliable forecasts.Our studies show that PiNNs can reduce computation times and deliver forecasts comparable to MULTI-VP, offering an expedited and dependable solar wind forecasting approach.

Solar wind forecasting is a core component of Space Weather, a field that has been the target of many novel machine-learning approaches. The continuous monitoring of the Sun has provided an ever-growing ensemble of observations, facilitating the development of forecasting models that predict solar wind properties on Earth and other celestial objects within the solar system. This enables us to prepare for and mitigate the effects of solar wind-related events on Earth and space. The performance of some simulation-based solar wind models depends heavily on the quality of the initial guesses used as initial conditions. This work focuses on improving the accuracy of these initial conditions by employing a Recurrent Neural Network model. The study’s findings confirmed that Recurrent Neural Networks can generate better initial guesses for the simulations, resulting in faster and more stable simulations. In our experiments, when we used predicted initial conditions, simulations ran an average of 1.08 times faster, with a statistically significant improvement and reduced amplitude transients. These results suggest that the improved initial conditions enhance the numerical robustness of the model and enable a more moderate integration time step. Despite the modest improvement in simulation convergence time, the Recurrent Neural Networks model’s reusability without retraining remains valuable. With simulations lasting up to 12 h, an 8% gain equals one hour saved per simulation. Moreover, the generated profiles closely match the simulator’s, making them suitable for applications with less demanding physical accuracy.

Refactoring software can be hard and time-consuming. Several refactoring tools assist developers in reaching more readable and maintainable code. However, most of them are characterized by long feedback loops that impoverish their refactoring experience. We believe that we can reduce this problem by focusing on the concept of Live Refactoring and its main principles: the live recommendation and continuous visualization of refactoring candidates, and the immediate visualization of results from applying a refactoring to the code. Therefore, we implemented a Live Refactoring Environment that identifies, suggests, and applies Extract Method refactorings. To evaluate our approach, we carried out an empirical experiment. Early results showed us that our refactoring environment improves several code quality aspects, being well received, understood, and used by the experiment participants. The source code of our tool is available on: https://github.com/saracouto1318/LiveRef. Its demonstration video can be found at: https://youtu.be/_jxx21ZiQ0o.

Automated Program Repair (APR) is an area of research focused on the automatic generation of bug-fixing patches. Current APR approaches present some limitations, namely overfitted patches and low maintainability of the generated code. Several works are tackling this problem by attempting to come up with algorithms producing higher quality fixes. In this experience paper, we explore an alternative. We believe that by using existing low-cost APR techniques, fast enough to provide real-time feedback, and encouraging the developer to work together with the APR inside the IDE, will allow them to immediately discard proposed fixes deemed inappropriate or prone to reduce maintainability. Most developers are familiar with real-time syntactic code suggestions, usually provided as code completion mechanisms. What we propose are semantic code suggestions, such as code fixes, which are seldom automatic and rarely real-time. To test our hypothesis, we implemented a Visual Studio Code extension (named pAPRika), which leverages unit tests as specifications and generates code variations to repair bugs in JavaScript. We conducted a preliminary empirical study with 16 participants in a crossover design. Our results provide evidence that, although incorporating APR in the IDE improves the speed of repairing faulty programs, some developers are too eager to accept patches, disregarding maintenance concerns.

The continuous spreading of the Internet-of-Things across application domains, aided by the continuous growth on the number of devices and systems that are Internet-connected, created both a rise in the complexity of these systems and made noticeable a lack of human resources with the expertise to design, develop and maintain them. Recent works try to mitigate these issues by creating solutions that abstract the complexity of the systems, such as using visual programming languages. Node-RED, as one of the most common solutions for the visual development IoT systems, stills has several limitations, such as the lack of observability and inadequate debugging mechanisms. In this work, we address some of these limitations by enhancing Node-RED with new features that improve the user's system development, debugging, and understanding tasks. We proceed to empirically evaluate the impact of these enhancements, concluding that, overall, such enhancements reduce the development time and the number of failed attempts to deploy the system.

In this work, we propose a method for extending Node-RED to allow the automatic decomposition and partitioning of the system towards higher decentralization. We provide a custom firmware for constrained devices to expose their resources, as well as new nodes and modifications in the Node-RED engine that allow automatic orchestration of tasks. The firmware is responsible for low-level management of health and capabilities, as well as executing MicroPython scripts on demand. Node-RED then takes advantage of this firmware by (1) providing a device registry allowing devices to announce themselves, (2) generating MicroPython code from dynamic analysis of flow and nodes, and (3) automatically (re-)assigning nodes to devices based on pre-specified properties and priorities. A mechanism to automatically detect abnormal run-time conditions and provide dynamic self-adaptation was also explored. Our solution was tested using synthetic home automation scenarios, where several experiments were conducted with both virtual and physical devices. We then exhaustively measured each scenario to allow further understanding of our proposal and how it impacts the system’s resiliency, efficiency, and elasticity.

Aspect Oriented Programming (AOP) is a powerful programming technique with the objective of improving modularity by encapsulating crosscutting concerns. The nature of AOP makes it prone to unexpected and harmful interactions between the different components of a system. The claim behind this PhD is that unit tests can be used to detect these interactions. In this paper we explain how these can be accomplished. A brief state of the art, work plan and a support tool (drUID) are also presented.