Rice Science

Rice Science

• Experimental Technique • Previous Articles    

Accelerating Wild Rice Disease-Resistant Germplasm Exploration: Artificial Intelligence (AI)-Powered Wild Rice Blast Disease Level Evaluation and Disease-Resistance Identification

  1. Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, China; National Agriculture Science Data Center, Beijing 100081, China; National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya 572024, China; College of Agronomy and Biotechnology, China Agricultural University, Beijing 100193, China; Yazhouwan National Laboratory, Sanya 572025, China; School of Breeding and Multiplication, Sanya Institute of Breeding and Multiplication, Hainan University, Sanya 572025, China; School of Tropical Agriculture and Forestry, Hainan University, Haikou 570228, China; China National Rice Research Institute, Hangzhou 311401, China; Sanya Agriculture and Rural Bureau, Sanya 572000, China; Institute of Crop Science, Chinese Academy of Agricultural Sciences, Beijing 100081, China; Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China; #These authors contributed equally to this work
  • Contact: ZHANG Jianhua; ZHENG Xiaoming ; HU Lin
  • Supported by:

    This study was supported by the National Key Research and Development Program of China (Grant Nos. 2022YFF0711805, 2022YFF0711801, and 2021YFF0704204), the Project of Sanya Yazhou Bay Science and Technology City (Grant No. SCKJ-JYRC-2023-45), the National Natural Science Foundation of China (Grant Nos. 31971792 and 32160421) , the Innovation Project of the Chinese Academy of Agricultural Sciences (CAAS) (Grant Nos. CAAS-ASTIP-2024-AII and ZDXM23011), the Special Fund of Chinese Central Government for Basic Scientific Research Operations in Commonweal Research Institutes (Grant No. JBYW-AII-2024-05), and the Nanfan special project, CAAS (Grant No. YBXM2312).

PDF

Abstract: Accurate evaluation of disease levels in wild rice materials and disease-resistance identification are critical for developing rice varieties resistant to blast disease. However, existing evaluation methods face limitations that hinder progress in breeding. To address these challenges, we propose an artificial intelligence (AI)-powered method for evaluating blast disease levels and resistance identification in wild rice. A lightweight segmentation model for diseased leaves and lesions was developed, incorporating an improved federated learning approach to enhance robustness and adaptability. Based on the segmentation results and resistance identification technical specifications, wild rice materials were evaluated into 10 disease levels (L0 to L9), further enabling disease-resistance identification by multiple replicates of the same materials. The method was successfully implemented on augmented reality glasses for real-time, first-person evaluation. Additionally, high-speed scanner and edge computing devices were integrated to enable continuous, precise, and dynamic evaluation. Experimental results demonstrate the outstanding performance of the proposed method, achieving effective segmentation of diseased leaves and lesions with only 0.22 M parameters and 5.3 G floating-point operations per second (FLOPs), with a mean average precision (mAP@0.5) of 96.3%. The accuracy of disease level evaluation and disease -resistance identification reached 99.7%, with a practical test accuracy of 99.0%, successfully identifying three highly resistant wild rice materials. This method provides strong technical support for efficiently identifying materials resistant to wild rice blast disease and resistance breeding efforts.

Key words: wild rice, germplasm resource, rice blast disease, crop disease level evaluation, disease-resistance identification