Can 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 leaf measurements from 30 meteorological stations in North Western Europe during period January 2014 to October 2018 was assessed this study. accuracy empirical models utilised within study enhanced by increasing relative humidity threshold 90% 92%. Increasing led average increase 1.12%. consistently provided more accurate results when compared that were studied with 4.85%. sub-division data regional subsets had a greater effect on than temporal data. Machine techniques performed well previously established wetness. Further improvements are possible, making here viable research tool.