Prediction of short-distance aerial movement of Phakopsora pachyrhizi urediniospores using machine learning

Authors: WEN, LIWEI - University Of Illinois; Bowen, Charles; Hartman, Glen

Submitted to: Phytopathology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/8/2017
Publication Date: 10/1/2017
Citation: Wen, L., Bowen, C.R., Hartman, G.L. 2017. Prediction of short-distance aerial movement of Phakopsora pachyrhizi urediniospores using machine learning. Phytopathology. 107:1187-1198.

Interpretive Summary: Dispersal of fungal spores by wind is the primary means of spread for the fungus causing soybean rust. In this research, we focused on the short distance movement of spores from within the soybean canopy and up to 61 m from field-grown rust-infected soybean plants. Environmental variables were used to develop and compare models to describe deposition of spores collected in passive and active traps. All four models tested identified distance of trap from source, humidity, temperature, wind direction, and wind speed as the five most important variables influencing short distance movement of spores. Overall, we found that using multiple machine learning techniques identified the most important variables to make the most accurate predictions of movement of spores found a short distance from the source. This information is important to scientists studying the epidemiology of plant diseases and others interested in the biology of aerial movement of microbes.

Technical Abstract: Dispersal of urediniospores by wind is the primary means of spread for Phakopsora pachyrhizi, the cause of soybean rust. Our research focused on the short distance movement of urediniospores from within the soybean canopy and up to 61 m from field-grown soybean rust infected plants. Environmental variables were used to develop and compare models including the least absolute shrinkage and selection operator regression, zero-inflated Poisson/regular Poisson regression, random forest, and neural network to describe deposition of urediniospores collected in passive and active traps. All four models identified distance of trap from source, humidity, temperature, wind direction, and wind speed as the five most important variables influencing short distance movement of urediniospores. The random forest model provided the best predictions, explaining 76.1% and 86.8% of the total variation in the passive- and active-trap datasets, respectively. The prediction accuracy based on the correlation coefficient (r) between predicted values and the true values were 0.83 (P < 0.0001) and 0.94 (P < 0.0001) for the passive- and active-trap datasets, respectively. Overall, we found that using multiple machine learning techniques identified the most important variables to make the most accurate predictions of movement of P. pachyrhizi urediniospores found a short distance from the source.