Forecasting Plant and Crop Disease: An Explorative Study on Current Algorithms

Abstract

Every year, plant diseases cause a significant loss of valuable food crops around the world. The plant and crop disease management practice implemented in order to mitigate damages have changed considerably. Today, through the application of new information and communication technologies, it is possible to predict the onset or change in the severity of diseases using modern big data analysis techniques. In this paper, we present an analysis and classification of research studies conducted over the past decade that forecast the onset of disease at a pre-symptomatic stage (i.e., symptoms not visible to the naked eye) or at an early stage. We examine the specific approaches and methods adopted, pre-processing techniques and data used, performance metrics, and expected results, highlighting the issues encountered. The results of the study reveal that this practice is still in its infancy and that many barriers need to be overcome.

Unravelling the relationships among Verticillium wilt, irrigation, and susceptible and tolerant olive cultivars

“…The best learned classifier was then evaluated on the test set and used to identify the groups that were homogeneous in terms of disease intensity index. The results were summarized as a final accuracy score, a confusion matrix, and a classification report, which are common performance measurements for machine learning classification of severity classes in several plant diseases (Fenu & Malloci, 2021).…”

Machine Learning for Plant Stress Modeling: A Perspective towards Hormesis Management

“…Yellowing is the most notable symptom of leaf senescence, and it appears due to seasonal developmental processes, pathogen attack, and abiotic stressors incidence, indicating a decrease in the photosynthetic rate [ 102 ]. Chlorophyll metabolism is regulated in a hormetic manner, and therefore it can perform as a biomarker to identify other metabolic changes resulting from low-dose stress incidence [ 103 , 104 ]. Many imaging techniques focus on detecting chlorophyll fluctuations with convenient results for biotic and abiotic stress phenotyping, such as chlorophyll fluorescence.…”

“…The persisting escalation of computing power has triggered a diversification of artificial intelligence (AI) tools to address various problems in plant science. AI algorithms are remarkably advantageous to identify and classify individual characteristics within an extensive set of experimental data, and thus they are a promising means for analyzing plant stress mechanisms [ 104 ]. Furthermore, if we consider the accumulating evidence on the hormetic behavior of plant stress responses, intelligent algorithm applications in plant stress physiology could be helpful for predicting eustress responses that fall under the low-dose stimulation model.…”

Predicting rice diseases across diverse agro-meteorological conditions using an artificial intelligence approach

“…Images were primarily used for disease classification in plants. The diseases of fruits and vegetables were more explored ( Fenu & Malloci, 2021 ). ANN is included in this article, which is one of the Artificial Intelligence methods available.…”