Precision Livestock Farming (PLF) relies on several technological approaches to acquire, in the most efficient way, precise and real-time data concerning production and welfare of individual animals. In this regard, in the dairy sector, PLF devices are being increasingly adopted, automatic milking systems (AMSs) are becoming increasingly widespread, and monitoring systems for animals and environmental conditions are becoming common tools in herd management. As a consequence, a great amount of daily recorded data concerning individual animals are available for the farmers and they could be used effectively for the calibration of numerical models to be used for the prediction of future animal production trends. On the other hand, the machine learning approaches in PLF are nowadays considered an extremely promising solution in the research field of livestock farms and the application of these techniques in the dairy cattle farming would increase sustainability and efficiency of the sector. The study aims to define, train, and test a model developed through machine learning techniques, adopting a Random Forest algorithm, having the main goal to assess the trend in daily milk yield of a single cow in relation to environmental conditions. The model has been calibrated and tested on the data collected on 91 lactating cows of a dairy farm, located in northern Italy, and equipped with an AMS and thermo-hygrometric sensors during the years 2016–2017. In the statistical model, having seven predictor features, the daily milk yield is evaluated as a function of the position of the day in the lactation curve and the indoor barn conditions expressed in terms of daily average of the temperature-humidity index (THI) in the same day and its value in each of the five previous days. In this way, extreme hot conditions inducing heat stress effects can be considered in the yield predictions by the model. The average relative prediction error of the milk yield of each cow is about 18% of daily production, and only 2% of the total milk production.

The study presents the objectives, methodologies and technical features of a monitoring system designed in the context of a national research project proposing innovative technical solutions for smart dairy farming in order to increase the herd productivity. The main objective of the project was to improve environment conditions and animal welfare of dairy cows and consequently enhance reproduction and production. To this regard, the system described here has a fundamental role operating as a tool for a more efficient management of the herd and of the herd housing. In fact, in the last years, animal control techniques and farm environmental monitoring have been developed, with increasing intensity, through the integration of Information Communication Technology (ICT) systems and models for the analysis and interpretation of the data collected. In this field, the Smart Monitoring System (SMS) described here could be effectively implemented in order to increase the animal welfare but at the same time increase the animal production. The integration of different type of sensors, different type of data and different type of models is at the base of the modern techniques for herd management and of the tools aiming to increase the dairy sector sustainability. The system integrates specifically designed sensor networks in a customized system architecture. It allows the acquisition of big data time series about physical and environmental conditions of the facilities hosting the cow herds starting from the collection of both indoor and outdoor environmental features, enabling a smart control of the facility, a diagnosis of the operating conditions, and early alerts in case of anomalies. The system has been developed to work in several environmental situations and is able to make the data remotely available in real time in a cloud.