Options
Gillespie, Gary D.
Preferred name
Gillespie, Gary D.
Official Name
Gillespie, Gary D.
Research Output
Now showing 1 - 3 of 3
- PublicationThe Potential for Hydrolysed Sheep Wool as a Sustainable Source of Fertiliser for Irish AgricultureSuppressed wool prices in Ireland over the last number of years has led to situations where the cost of shearing animals is greater than the wools’ value, leading to net losses per animal for farmers. Populations of sheep in Ireland and nutrient values of wool from literature sources were used to determine the quantity of nutrients that could be produced on an annual basis using hydrolysis techniques. Results of this study suggest that up to 15.8% of the nitrogen required to produce Ireland’s cereal crops can be met annually using hydrolysed sheep wool in an economically feasible manner along with considerable amounts of sulphur, zinc, and copper. Most of the cost associated with the process is the purchasing of wool from farmers at an economically favourable level for farmers. Based on the spatial distribution of these animals, the town of Athlone is the most suitable location for a processing facility.
195Scopus© Citations 4 - PublicationCan machine learning classification methods improve the prediction of leaf wetness in North-Western Europe compared to established empirical methods?Leaf wetness is an important input parameter into disease prediction models. The use of machine learning algorithms for the classification of leaf wetness measurements from 30 meteorological stations in North Western Europe during the period of January 2014 to October 2018 was assessed in this study. The accuracy of the empirical models utilised within in this study was enhanced by increasing the relative humidity threshold from 90% to 92%. Increasing the relative humidity threshold led to an average increase in the classification accuracy of 1.12%. The use of machine learning classification algorithms consistently provided more accurate results for the prediction of leaf wetness when compared to the empirical models that were studied with an average increase in the classification accuracy of 4.85%. The sub-division of the data into regional subsets had a greater effect on the accuracy of the models than the temporal sub-division of the data. Machine learning classification techniques performed well compared with previously established empirical models for the prediction of leaf wetness. Further improvements in the algorithms are possible, making the techniques studied here a viable research tool.
153Scopus© Citations 4 - PublicationEstimating the current area of European tillage systems occupied by tramlines and a potential approach for the cultivation of this underutilised areaThe global population is growing by 200,000 people per day. In order to provide enough food for this growing populous sustainable intensification methods need to be adopted. The use of technology, and in particular UAVs, may be one of these methods. The use of UAVs for the completion of agricultural tasks such as fertilising and spraying may negate the need for tramlines in European tillage systems. In the present study the amount of land currently occupied by tramlines was determined in an effort to ascertain the potential amount of combinable crop products that could be achieved if this area was utilised. The results of this study found that 3.42% of a field with a 24 m bout width is occupied by tramlines. By using this area for the cultivation of crops an additional 8.14 Mt worth €1.43 billion could be produced. This additional product could provide enough calories to feed 29.5 million people per year.
162Scopus© Citations 3