RESUMO
Timely prediction of pathogen is important key factor to reduce the quality and yield losses. Wheat is major crop in northern part of India. In Punjab, wheat face challenge by different diseases so the study was conducted for two locations viz. Ludhiana and Bathinda. The information regarding the occurrence of Karnal bunt in 12 consecutive crop seasons (from 2009-10 to 2020-21) in Ludhiana district and in 9 crop seasons (from 2010-11 to 2018-19) in Bathinda district, was collected from the Wheat Section of the Department of Plant Breeding and Genetics at Punjab Agricultural University (PAU), located in Ludhiana. The study aims to investigate the adequacy of various methods of machine learning for prediction of Karnal bunt using meteorological data for different time period viz. February, March, 15 February to 15 March and overall period obtained from Department of Climate Change and Agricultural Meteorology, PAU, Ludhiana. The most intriguing outcome is that for each period, different disease prediction models performed well. The random forest regression (RF) for February month, support vector regression (SVR) for March month, SVR and BLASSO for 15 February to 15 March period and random forest for overall period surpassed the performance than other models. The Taylor diagram was created to assess the effectiveness of intricate models by comparing various metrics such as root mean square error (RMSE), root relative square error (RRSE), correlation coefficient (r), relative mean absolute error (MAE), modified D-index, and modified NSE. It allows for a comprehensive evaluation of these models' performance.
RESUMO
Karnal bunt (KB) of wheat incited by Tilletia indica Mitra is now gaining importance from the last few years due to its increasing incidence. Regular surveys are conducted to collect wheat grains samples from different grain markets of Punjab, India. Since weather plays a significant role in the initiation as well as the development of Karnal bunt. Thus, the variation in Karnal bunt incidence worked out and is being interpreted in relation to the prevailing environmental conditions during the most susceptible stage for the two decades (1991-92 to 2014-15) for the Punjab, India. The incidence of Karnal bunt was correlated with the weather parameters during the February and March of the corresponding year. The correlation analysis revealed the positive role of rainfall, rainy days, evening relative humidity, and Humid thermal index of March and the negative role of sunshine hours of February in the development and incidence of Karnal bunt. By using these parameters, a multiple regression model was developed and validated for forecasting the disease. The regression analysis showed a coefficient of determination of 0.77 and a D.W value of 1.88. The detailed analysis of historical data for more than two decades divulged the amount of total rainfall as well as the number of rainy days of March as the most critical factor for the Karnal bunt development. Supplementary Information: The online version contains supplementary material available at 10.1007/s42360-022-00520-w.