Evaluation of the Use of the 12 Bands vs. NDVI from Sentinel-2 Images for Crop Identification.

Today, machine learning applied to remote sensing data is used for crop detection. This makes it possible to not only monitor crops but also to detect pests, a lack of irrigation, or other problems. For systems that require high accuracy in crop identification, a large amount of data is required to generate reliable models. The more plots of and data on crop evolution used over time, the more reliable the models. Here, a study has been carried out to analyse neural network models trained with the Sentinel satellite's 12 bands, compared to models that only use the NDVI, in order to choose the most suitable model in terms of the amount of storage, calculation time, accuracy, and precision. This study achieved a training time gain of 59.35% for NDVI models compared with 12-band models; however, models based on 12-band values are 1.96% more accurate than those trained with the NDVI alone when it comes to making predictions. The findings of this study could be of great interest to administrations, businesses, land managers, and researchers who use satellite image data mining techniques and wish to design an efficient system, particularly one with limited storage capacity and response times.

Model Driven Development Applied to Complex Event Processing for Near Real-Time Open Data.

Nowadays, data are being produced like never before because the use of the Internet of Things, social networks, and communication in general are increasing exponentially. Many of these data, especially those from public administrations, are freely offered using the open data concept where data are published to improve their reutilisation and transparency. Initially, the data involved information that is not updated continuously such as budgets, tourist information, office information, pharmacy information, etc. This kind of information does not change during large periods of time, such as days, weeks or months. However, when open data are produced near to real-time such as air quality sensors or people counters, suitable methodologies and tools are lacking to identify, consume, and analyse them. This work presents a methodology to tackle the analysis of open data sources using Model-Driven Development (MDD) and Complex Event Processing (CEP), which help users to raise the abstraction level utilised to manage and analyse open data sources. That means that users can manage heterogeneous and complex technology by using domain concepts defined by a model that could be used to generate specific code. Thus, this methodology is supported by a domain-specific language (DSL) called OpenData2CEP, which includes a metamodel, a graphical concrete syntax, and a model-to-text transformation to specific platforms, such as complex event processing engines. Finally, the methodology and the DSL have been applied to two near real-time contexts: the analysis of air quality for citizens' proposals and the analysis of earthquake data.