The AQUALIPIG project seeks the investigation of Artificial Intelligence in a real experimental pig farm where the use of an innovative technology, electrolysis, is validated in its use for the sanitization of drinking water for pigs in the fattening phase.
The objective of the project, therefore, must implicitly include the design and development of a data capture and processing system based on artificial intelligence that allows comparing normal production data with that of drinking water treatment with ActivH2O. ActivH2O is a patented technology based on electrolysis, which eliminates viruses and bacteria from the water without adding chemicals and which generates a natural oxidant that remains in the water for several weeks, acting on the biofilm and thus protecting it from possible recontamination.
Validating a new water sanitization strategy and applying AI to the process is a totally innovative and novel step in that there are no actions that offer conclusive results in this regard to date. The information that has been found, after an extensive analysis of the state of the art, refers to very preliminary experimental studies and under very controlled conditions; The study presented seeks, for the first time, to carry out studies under experimental farm conditions, in pig farms that will allow the proper assessment of the results found and their direct extrapolation to real production conditions.
In addition, the incorporation of artificial intelligence will allow taking into account not only historical but also parameterized variables in two groups. On the one hand, data related to production will be collected and analyzed, which will be classified in terms of feed consumption and by weight. On the other hand, data related to the state of health will be collected and analyzed, which will be classified into mortality rates and necessary veterinary interventions (use of drugs, outbreaks, etc.). With all this, data processing and the extraction of conclusive results will be allowed, leading to the optimization of decision-making throughout the process while allowing robust conclusions to be reached.
