Machine learning-based detection of frost events in wheat plants from infrared thermography

Shammi, Sayma; Sohel, Ferdous; Diepeveen, Dean; Zander, Sebastian; Jones, M. G. K.

doi:10.1016/j.eja.2023.126900

Cited by 6 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Field control experiment can directly analyze the physiological and ecological mechanism of spring frost damage, but this method overlooks the compound influence of other factors and fails to reflect the actual conditions in the natural environment [7]. Recent advancements have seen the application of hyperspectral techniques and image-based computational learning techniques in field control experiments [17][18][19]. Despite providing valuable insights, these studies are confined to field trials and cannot be broadly applied to largescale crop monitoring due to instrument limitations and complex atmospheric conditions.…”

Section: Introductionmentioning

confidence: 99%

Monitoring and Mapping Winter Wheat Spring Frost Damage with MODIS Data and Statistical Data

Chen,

Liu,

Lei

et al. 2023

Plants

View full text Add to dashboard Cite

Spring frost is an extreme temperature event that poses a significant threat to winter wheat production and consequently jeopardizes food security. In the context of climate change, the accelerated phenology of winter wheat due to global warming advances the frost-sensitive stage, thereby escalating the risk of spring frost damage. Present techniques for monitoring and assessing frost damage heavily rely on meteorological data, controlled field experiments and crop model simulations, which cannot accurately depict the actual disaster situation for winter wheat. In this study, we propose a novel method that utilizes remote sensing index and statistical data to ascertain the spatial distribution of spring frost damage to winter wheat and evaluate the extent of damage. This method was employed to monitor and assess the spring frost damage event that occurred in Shandong province from 3 to 7 April 2018. The result shows that beginning on 3 April, the daily minimum temperature in western Shandong Province dropped significantly (decreased by 17.93 °C), accompanied by precipitation. The daily minimum temperature reached the lowest on 7 April (−1.48 °C). The growth of winter wheat began to be inhibited on 3 April 2018, and this process persisted until 13 April. Subsequently, the impact of spring frost damage on winter wheat ceased and growth gradually resumed. The affected area of winter wheat spanned 545,000 mu with an accuracy rate of 89.72%. Severely afflicted areas are mainly located in the cities of Jining, Zaozhuang, Dezhou, Heze, Liaocheng, Jinan and Tai’an in western Shandong province, and the yield reduction rates were 5.27~12.02%. Our monitoring results were consistent with the distribution of county-level winter wheat yield in 2018 in Shandong province, the daily minimum temperature distribution during spring frost and severely afflicted areas reported by the news. This method proves effective in delineating the spatial distribution of agricultural disasters and monitoring the extent of disaster damage. Furthermore, it can provide reliable information of disaster area and geospatial location for the agricultural department, thereby aiding in disaster damage assessment and post-disaster replanting.

show abstract