Wheat scab prediction method based on XGBoost algorithm

• Main Authors: LIU TAIGUO, CHEN WANQUAN, WANG ZHAOYONG, ZHANG HAO, WANG JIFENG
• Format: Patent
• Language: Chinese; English
• Published: 28.04.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention relates to the technical field of crop disease monitoring, and discloses a wheat scab prediction method based on an XGBoost algorithm. Comprising the following steps: S1, establishing a national wheat scab condition database; s2, establishing a disease monitoring point meteorological data database; s3, screening out training data sets of the three models; s4, carrying out gradient lifting training by using an XGBoost algorithm; and S5, evaluating the precision of the model. According to the wheat scab prediction method based on the XGBoost algorithm provided by the invention, the data source is multi-year multi-disease monitoring point survey data of most of wheat producing areas throughout the country, the survey data comprises meteorological data from 30 days before the flowering stage to 15 days after the flowering stage, the data precision is high, and the data volume is large. The method adopts a three-section prediction method, has the advantages of wide application range, high prediction