RESUMEN:

Introduction, The framework has been implemented as an DSS for agricultural irrigation, nutrient  and crop management. Results have been obtained for resource allocation using a multi-objective  optimization problem solved by a numerical method. Gradient and Hessian have been analyzed in  order to verify the convergence of the method.  

Methodology: For the framework integration, various types of data were aggregated from satellite  images, from the UAV, from IoT and sensor networks in the field, from the laboratory, from Geographic  Information Systems and from weather stations, among others. The information was sorted, cleaned,  normalized, time-series synchronized and feature-engineered in order to prepare it for analysis via  the Digital Twin. 

Results, The results of PlaSmA (Platform for Smart Agriculture), for Quantum-Inspired precision  agriculture. We develop a model to supports agricultural decision-making by integrating information  from satellite remote sensing, UAVs, IoTs, Digital Twins, predictive models and optimization models and two mathematical tools have been designed and evaluated for the assessment of agricultural  performance. 

In summary, the framework PlaSmA, based on a DSS to support agricultural decisions for irrigation,  nutrient application, crop monitoring and use of resources in general, has been developed and tested  by means of a set of computational experiments. Thus, the integration of information from various  sources of data in the framework of a DSS for precision agriculture has been addressed, as well as  the use of a set of Digital Twins synchronized with the physical agricultural system to be studied, and  the use of a set of predictive models. 

Keywords: Digital Twins, Platform for Smart Agriculture (PlaSmA), Precision Agriculture, Quantum Inspired, Remote Sensing (Satellite).