Chawade, Aakash
- Department of Plant Breeding, Swedish University of Agricultural Sciences
Review article2024Peer reviewedOpen access
Shubhika, Shubhika; Patel, Pradeep; Singh, Rickwinder; Tripathi, Ashish; Prajapati, Sandeep; Rajput, Manish Singh; Verma, Gaurav; Rajput, Ravish Singh; Pareek, Nidhi; Saratale, Ganesh Dattatraya; Chawade, Aakash; Choure, Kamlesh; Vivekanand, Vivekanand
Agriculture provides basic livelihood for a large section of world's population. It is the oldest economic activity in India, with two third of Indian population involved in crop production. India is second largest producer of rice and biggest exporter globally, with rice which is most common staple crop consumed in country. However, there are several challenges for paddy production including small production yield, soil quality, seed quality, huge volume of water needed and biotic stress. Of these, biotic stress drastically affects yield and susceptibility to other diseases in paddy production. It is caused by pathogens such as bacteria, viruses, fungi, nematodes, all of which severely affect growth and productivity of paddy crop. To mitigate these challenges, infected crops are identified, detected, classified, categorized, and prevented according to their respective suffering disease by using conventional methods which are not effective and efficient for growth of paddy crop. Thus, use of artificial intelligence (AI) and a smart agriculture-based Internet of Things (IoT) platform could be effective for detecting the biotic stresses in very less time or online mode. For this, deep learning, and convolutional neural networks (CNN) multi-structured layer approach were used for diagnosing disease in rice plants. Different models and classifiers of CNN were used for detecting disease by processing high-spectral images and using logistic and mathematical formulation methods for classification of biotic paddy crop stresses. Continuous monitoring of stages of infection in paddy crop can be achieved using real-time data. Thus, use of AI has made diagnosing paddy crop diseases much easier and more efficient.
Biotic stress; Paddy; Artificial intelligence; Convolutional neural network; Agriculture
Plant Stress
2024, Volume: 14, article number: 100592Publisher: ELSEVIER
Agricultural Science
DOI: https://doi.org/10.1016/j.stress.2024.100592
https://res.slu.se/id/publ/132693