Weather based forewarning of wheat diseases using artificial neural networks under Punjab conditions

Simple item page
dc.contributor.advisorSandhu, Sarabjot Kaur
dc.contributor.authorShubham Anand
dc.date.accessioned2024-01-03T09:51:20Z
dc.date.available2024-01-03T09:51:20Z
dc.date.issued2023
dc.description.abstractThe field experiments were carried out at the Research Experiment Farm, Department of Climate Change and Agricultural Meteorology, Punjab Agricultural University, Ludhiana and Regional Research Station, Gurdaspur during rabi seasons of 2021-22 and 2022-23. The experiment was laid out in Split Plot Design with three wheat varieties viz., PBW 725, HD 2967 and HD 3086 sown on different dates (14th-15th October, 8th-9th November and 3rd-4th December) with two microclimate modification levels M1 (recommended irrigation) and M2 (additional water sprays) with four replications. The micrometeorological parameters viz., photosynthetically active radiation (PAR) and relative humidity within crop canopy were recorded at different phenological stages. Weekly observations on severity of yellow rust, brown rust, foliar blight and incidence of Karnal bunt at harvest were determined under different treatments. Among the three different sowing dates, the yellow rust severity in variety HD 2967 was reported to be highest (56.14%, 56.17%) at Ludhiana and Gurdaspur (56.75%, 58.42%) in early sowing under M2 than other treatments during rabi 2021-22 and 2022-33, respectively. The brown rust severity was higher (65.44%, 68.21%) at Ludhiana and Gurdaspur (61.76%, 63.5%) in early sowing under M2 than other treatments during rabi 2021-22 and 2022-33, respectively. It was observed that early date of sowing (15th October) recorded higher foliar blight severity (28.52%, 29.35%) at Ludhiana and Gurdaspur (21.69%, 30.65%) in variety HD 3086 in M2 than other treatments during rabi 2021-22 and 2022-23. The Karnal bunt disease incidence was relatively higher at Ludhiana (17.9% and 11.6%) and Gurdaspur (21.4% and 15.9%) in variety PBW 725 under M2 during normal sowing than other treatments during both the years of study, respectively. From correlation coefficient and regression analysis, it was concluded that temperature (maximum and minimum), sunshine hours and rainfall were observed as key parameters in spread of wheat diseases. Grain yield during rabi 2021-22 and rabi 2022-23 were higher in early sowing (43.3q/ha, 48.1 q/ha) at Ludhiana and Gurdaspur (44.5 q/ha, 50.8 q/ha) than other dates of sowing during both the years under study. In variety x microclimate modification levels treatments, grain yield was higher (43.1q/ha, 47.2q/ha) at Ludhiana and Gurdaspur (44.0 q/ha, 50.2 q/ha) in variety PBW 725 under M1 than other treatments during both years under study. Early date of sowing recorded more yield losses followed by late and normal sowing and losses were more at Gurdaspur as compared to Ludhiana. Average yield losses during rabi 2022-23 were higher i.e. 5.6% and 7.1% as compared to 1.6% and 2.3% during rabi 2021-22 at Ludhiana and Gurdaspur, respectively. From in vitro study, it was observed that urediniospore germination of pathotypes of Puccinia striiformis and Puccinia triticina was maximum at 15°C and 20°C, respectively at pH 7.0 and 1250 lux light intensity. So, if high temperatures along with sunny days prevail rust can flourish in wheat fields. 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 for forewarning of Karnal bunt. From the CART analysis, it can be inferred that maximum yellow rust severity can occur if >9.2 sunshine hours/day and >9.1oC minimum temperature occurs or, dew point temperature is >14oC and mean temperature is <15oC or dew point temperature is < 14oC and humid thermal index is <2.4.
dc.identifier.citationShubham Anand (2023). Weather based forewarning of wheat diseases using artificial neural networks under Punjab conditions (Unpublished Ph.D. Dissertation). Punjab Agricultural University, Ludhiana, Punjab, India.
dc.identifier.urihttps://krishikosh.egranth.ac.in/handle/1/5810205381
dc.keywordsWheat
dc.keywordsYellow rust
dc.keywordsBrown rust
dc.keywordsFoliar blight
dc.keywordsKarnal bunt
dc.keywordsForewarning models
dc.language.isoEnglish
dc.pages191
dc.publisherPunjab Agricultural University
dc.research.problemWeather based forewarning of wheat diseases using artificial neural networks under Punjab conditions
dc.subAgricultural Meteorology
dc.themeWeather based forewarning of wheat diseases using artificial neural networks under Punjab conditions
dc.these.typePh.D
dc.titleWeather based forewarning of wheat diseases using artificial neural networks under Punjab conditions
dc.typeThesis
Files
Collections
Thesis