Mastitis, or udder inflammation, is one of the most prevalent and costliest diseases in dairy farming. Automatic milking systems, equipped with sensors measuring mastitis indicators, have been used commercially since the 1990s. These systems are equipped with sensors that measure the cow’s health by analyzing her milk. For instance, these sensors could measure electrical conductivity, the number of immune cells, and activity of enzymes in the milk. Different algorithms have been developed to use this sensor data to alarm the farmer in the case of mastitis. However, less algorithms have been developed to help the farmer decide what to do when mastitis is found.
This thesis investigated new ways in which existing sensor data can be used to help the farmer in the decision making whether to intervene in a case of mastitis or not. The overall objective for this PhD project was to explore the potential for a decision support system in automatic milking systems supporting chronic mastitis decision-making. The thesis was based upon four scientific papers.
Paper I described that the somatic cell count (SCC) and electrical conductivity of mastitis cases, usually recover three to four weeks, if they recover. After this relatively short period, it became unlikely that a cow would recover. This means that farmers may want to intervene after 3-4 weeks when cows have consistently high SCC and/or EC because there will be a very small opportunity of spontaneous recovery.
Paper II found strong non-linearities between milk production and lactate dehydrogenase (LDH), SCC, and EC. The results showed that, at low sensor levels, almost no milk production losses were observed. The milk production losses would increase substantially after specific higher sensor values. Using these thresholds, farmers can be alerted when the milk yield production decreases substantially and that action may be needed.
Paper III showed that it was possible to forecast the progression of mastitis with a combination of recent sensor data and gradient-boosting trees. The results showed that it was possible to forecast the outcome of the disease, whether it would recover or become chronic. This forecast could help the farmer in the decision to intervene in a mastitis case when it becomes clear that a case does not recover on its own.
Finally, Paper IV estimated the economic impact of different sensor-based mastitis management strategies to show which strategy tends to decrease the cost of mastitis and chronic mastitis the most. More specifically, it estimated the economic consequences of chronic mastitis cases to show the direct impact of management failure on the economic situation of a dairy farm.
This thesis shows that it is possible to support management regarding chronic mastitis with sensors, routinely measuring SCC, EC and/or LDH. It provides the basis for a decision support system. This decision support system would be a system that could tell the farmer which cases of mastitis are chronic, are likely to become chronic, are associated with large milk production loss, and could tell the economic consequences of chronic mastitis cases.John Bonestroo obtained his doctorate from Wageningen University & Research and Swedish University of Agricultural Sciences in 2022. His industrial PhD project was in close collaboration with DeLaval International. Currently, John is working part-time as a Lecturer at Wageningen University & Research and part-time as a Farm Data Scientist at DeLaval International.