The ASTRI Mini-Array is an international project, led by the Italian National Institute for Astrophysics, whose purpose is to construct and operate an array of nine Imaging Atmospheric Cherenkov Telescopes to study gamma-ray sources at very high energy (TeV) and perform stellar intensity interferometry observations. The ASTRI Mini-Array, developed in all its hardware and software aspects, is under construction at the Teide Astronomical Observatory on Mount Teide in Tenerife (Canary Islands, Spain). The ASTRI Mini-Array will be remotely operated; such a functionality reflects in a critical work package of the entire software system to satisfy the requirements in terms of performance and security. In this context, a system that checks the outcomes of the observations to obtain prompt feedback is required.

This contribution describes the first implementation of the Online Observation Quality System (OOQS). The OOQS is part of the Supervisory Control And Data Acquisition (SCADA) software work package, that controls all the operations carried out at the observing site, like data acquisition, telescope control and monitoring, and handling alarms. The OOQS aims to execute data quality checks on the housekeeping, scientific and variance data acquired in real-time by the Cherenkov camera and Intensity Interferometry instruments and provide feedback to both SCADA and the operator about the status of the observation and to highlight abnormal conditions found by checking the results of the analysis with threshold values. This feedback is crucial to take corrective actions in the shortest time possible and maximize the outcomes of the observations. The results are stored in the Quality Archive to be visualized by the operator (during the observations) using a Human Machine Interface and for further investigations.

OOQS is developed in the context of a distributed application that exploits the Alma Common Software as a framework, which provides a distributed Component-Container model and services for components.
The prototype of the OOQS implements three main components. The first component is a Kafka consumer to manage the data stream received from the Array Data Acquisition System through Apache Kafka, which is a distributed event streaming platform. The data are encoded and decoded during the transmission using Apache Avro, a serialization data format.
The Kafka Consumer effectively handles the high data flow from the Cherenkov cameras, which can reach speeds of up to 1.15 Gb/s. The data stream is divided into batches of data written in files. The second component of the pipeline is a daemon that waits for new files and then executes a list of analyses using the Slurm workload scheduler to exploit its key features, such as parallel analyses and scalability. Finally, the results obtained by the processes are collected by the last component and stored in the Quality Archive.

AGILE is a space mission launched in 2007 to study X-ray and gamma-ray astronomy. The AGILE Team is developing new detection algorithms for Gamma-Ray Bursts (GRBs) both with classical and machine learning technologies. To train or test these algorithms, it is necessary to have a large GRB dataset, but usually, there are not enough real data available. This problem is also common for the new generation of high-energy astrophysics projects (such as COSI and CTA). It therefore becomes essential to have a system to simulate GRB data.
This work aims to develop a Deep Learning-based model for generating synthetic GRBs that closely replicate the properties and distribution of real GRBs. The dataset obtained using the trained model can then be used to develop detection algorithms both with classic techniques and with machine learning. To develop this generative model we have to take into account several complexities. The main ones are the huge different temporal behaviours of such GRBs and the lack of data making the training harder.
We propose a new method for generating GRBs. This model combines the Generative Adversarial Network (GAN) and Variational Autoencoder (VAE) to produce high-quality and structured generative results while preserving latent space structure. We also developed a loss function tailored to our dataset for the reconstruction task. To create the training dataset we extracted the light curves (LC) of GRBs presented in the Fourth Fermi-GBM Catalog using only long GRBs. This catalogue contains more than a decade of observations with a total of 3608 GRBs, captured through 12 NaI and 2 BGO detectors. In this work, we considered only the NaI detectors. We used the LCs detected by multiple sodium detectors and related to the same GRB as independent, to augment the number of samples. We filtered the LCs by removing outliers and those with missing values, ending with a total of 5964 LCs. Evaluating the distribution of the GRB duration (through the t90 parameter), we set the length of the time series at 220.
We assessed the model's performance by quantifying the dissimilarity between the histograms of count rates in synthetic and real GRBs. Additionally, we conducted quantitative analysis, employing statistics of the LCs distribution in both datasets. The results show that the synthetic LCs are generated with very similar properties to the real ones. We are working on a conditional version of our model using physical parameters of the GRBs such as the t90 or the fluence to have a more precise generation. This method can be used to generate synthetic LCs for other high-energy astronomy projects such as AGILE, CTA and COSI.