The calibration and execution of large hydrological models, such as SWAT (soil and water assessment tool), developed for large areas, high resolution, and huge input data, need not only quite a long execution time but also high computation resources. SWAT hydrological model supports studies and predictions of the impact of land management practices on water, sediment, and agricultural chemical yields in complex watersheds. The paper presents the gSWAT application as a web practical solution for environmental specialists to calibrate extensive hydrological models and to run scenarios, by hiding the complex control of processes and heterogeneous resources across the grid based high computation infrastructure. The paper highlights the basic functionalities of the gSWAT platform, and the features of the graphical user interface. The presentation is concerned with the development of working sessions, interactive control of calibration, direct and basic editing of parameters, process monitoring, and graphical and interactive visualization of the results. The experiments performed on different SWAT models and the obtained results argue the benefits brought by the grid parallel and distributed environment as a solution for the processing platform. All the instances of SWAT models used in the reported experiments have been developed through the enviroGRIDS project, targeting the Black Sea catchment area.

Recently a new Grid-based software platform was developed to allow remote sensing image processing for preventing disasters like river floods and forest fires. While several innovative components were presented in research papers in the last year, this paper presents a state-of-the-art of the whole platform and exposes the novelty elements that distinguish it from other similar approaches.

Near-Earth Asteroids represent potential threats to human life because their trajectories may bring them in the proximity of the Earth. Monitoring these objects could help predict future impact events, but such efforts are hindered by the large numbers of objects that pass in the Earth’s vicinity. Additionally, there is also the problem of distinguishing asteroids from other objects in the night sky, which implies sifting through large sets of telescope image data. Within this context, we believe that employing machine learning techniques could greatly improve the detection process by sorting out the most likely asteroid candidates to be reviewed by human experts. At the moment, the use of machine learning techniques is still limited in the field of astronomy and the main goal of the present paper is to study the effectiveness of deep convolutional neural networks for the classification of astronomical objects, asteroids in this particular case, by comparing some of the well-known deep convolutional neural networks, including InceptionV3, Xception, InceptionResNetV2 and ResNet152V2. We applied transfer learning and fine-tuning on these pre-existing deep convolutional networks, and from the results that we obtained, the potential of using deep convolutional neural networks in the process of asteroid classification can be seen. The InceptionV3 model has the best results in the asteroid class, meaning that by using it, we lose the least number of valid asteroids.