Incorporating artificial intelligence in detecting crop diseases: Agricultural decision-making based on group consensus model with MULTIMOORA and evidence theory

• Published in: Crop protection Vol. 179; p. 106632
• Main Authors: Zhang, Chao, Wang, Bingjie, Li, Wentao, Li, Deyu
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.05.2024
• Subjects: Artificial intelligence; Crop diseases; decision making; decision support systems; domain; Group consensus model; Intelligent decision-making; plant protection; quantitative analysis; Quantitative evaluation; viruses; wheat; Crop diseases; Intelligent decision-making; Artificial intelligence; Quantitative evaluation; Group consensus model
• ISSN: 0261-2194; 1873-6904
• DOI: 10.1016/j.cropro.2024.106632

The continuous advancements in artificial intelligence (AI) technology are facilitating its widespread integration across various sectors, prominently within agriculture. This evolving synergy is reshaping farming practices, specifically by innovating intelligent mechanisms to monitor and combat crop diseases through intelligent decision-making. Wheat assuming particular significance on the global agricultural stage. Addressing the concerning spread of the wheat soil-borne mosaic (WSBM), this paper employs modern methodologies to gauge the severity of virus infection in wheat through quantitative evaluation. Our contribution lies in the exploration of a group consensus model method within the context of interval type-2 fuzzy sets (IT2FSs). Navigating the intricacies of decision makers (DMs) reaching consensus, we address the challenge of selecting a consensus degree threshold by introducing random variables. Experimentally determining an objective consensus degree threshold. Then, we combine the Multi-Objective Optimization by Ratio Analysis plus the full MULTIplicative form (MULTIMOORA) method with Dempster-Shafer (D-S) evidence fusion theory. This result in an evidence fusion decision-making model rooted in IT2F information, offering enhanced stability. Leveraging the MULTIMOORA method for decision-making, we then fuse the outcomes through D-S evidence fusion theory, yielding stable decision results. Subsequently, we validate the feasibility of our established decision model within the context of WSBM. In conclusion, we subject it to sensitivity and comparative analyses, comparing it with other methods. This thorough evaluation aims to validate the effectiveness and feasibility of our proposed approach, providing insights into its potential applications and contributions in the realm of agricultural decision-making. •A scheme for detecting crop diseases through artificial intelligence is proposed.•A decision-making method fusing MULTIMOORA with D-S evidence theory is explored.•An agricultural group consensus decision rule in the IT2FS context is explored.•A method to optimize the consensus process by the additional adjustment is developed.