Other symptoms may include the development of “blackleg” in infected plants which results in weaker plants and lower productivity ( Santos et al., 2016). phaseolina pathogen may occur at any growth stage whereas symptoms often appear after the midseason or at maturity i.e., growth stage R7 where yellowing of the leaves and yellow pods can be observed ( Hartman et al., 2016). (2010) described that the disease is dispersed by infected plant residues, wind, and soil. Moreover, sclerotia and chlamydospores structures enable the fungus to survive in the soil for a longer period ( Katan, 2017). phaseolina to adapt across various climatic conditions ( Ambrosio et al., 2015). A wide range of physiological, morphological, and pathogenic diversity enables M. It is an extremely robust soil-borne fungus that damages several crops i.e., cotton, grains, oilseeds, legumes, jute along with fruits and vegetable plants ( Ambrosio et al., 2015 Sun et al., 2016). Macrophomina phaseolina (Tassi) Goid causes rot diseases in about 700 plant species. Recent statistics have confirmed that there is a decline of worldwide crop yields by 14% worldwide due to plant diseases, weeds and insects, and hence, early detection of diseases is of a key importance to prevent disease spread and reduce damage to crop production ( Martinelli et al., 2015). Plant diseases are the lead causes of extensive economic losses in the agricultural industry around the world. The production of global crops has to be doubled by 2050 to meet the increasing needs of the world’s population ( Khalili et al., 2019).
The collected dataset and source code can be found in. Moreover, our analysis demonstrated the importance of including physiological featured in the learning. Our findings supported the applicability of ML especially GBT for charcoal rot disease prediction in a real environment. Gradient Tree Boosting (GBT) was the best performing classifier which obtained 96.25% and 97.33% in terms of sensitivity and specificity. All developed ML models were performed better than 90% in terms of accuracy.
A hybrid set of physiological and morphological features were suggested as inputs to the ML models. In this paper, several ML techniques were developed and examined for prediction of charcoal rot disease in soybean for a cohort of 2,000 healthy and infected plants.
ML methods can be applied to detect plant diseases, prior to the full appearance of symptoms. Machine learning (ML) techniques have recently gained substantial traction across numerous domains. Prediction of this disease in soybeans is very tedious and non-practical using traditional approaches. Charcoal rot disease is one of the most severe threats to soybean productivity.
Macrophomina phaseolina (Tassi) Goid, as one of the main causes of charcoal rot disease, suppresses the plant productivity significantly.