Sub-field detection of cereal yield losses and its causes using Sentinel-2 time series and weather data

Weather extremes severely affect agricultural production and threaten food security worldwide. Throughout the growing season, crops can experience various degrees of weather stress whereby multiple stressors could occur simultaneously or intermittently. For large spatial extents, it is difficult to estimate actual crop damage merely through field experiments or crop models. Remote sensing can help to detect crop damage and estimate lost yield due to weather extremes over large spatial extents, but current RS-based studies usually focus on a single stress or event. We propose a novel scalable method to predict in-season yield losses at the sub-field level and attribute these losses to different weather extremes. To assess our method’s potential, we conducted a proof-of-concept case study on winter cereal paddocks in South Australia using data from 2017 to 2022. To detect crop growth anomalies throughout the growing season, we aligned a two-band Enhanced Vegetation Index (EVI2) time series from Sentinel-2 with thermal time derived from gridded meteorological data. The deviation between the expected and observed EVI2 time series was defined as the Crop Damage Index (CDI). We assessed the performance of the CDI within specific phenological windows to predict yield loss. Finally, by comparing instances of substantial increase in CDI with different extreme weather indicators, we explored which (combinations of) extreme weather events were likely responsible for the experienced yield reduction. We found that the use of thermal time diminished the temporal deviation of EVI2 time series between years, resulting in the effective construction of typical stress-free crop growth curves. Thermal-time-based EVI2 time series resulted in better prediction of yield reduction than those based on calendar dates. Yield reduction could be predicted before grain-filling (approximately two months before harvest) with an R² of 0.83 for wheat and 0.91 for barley. The combined analysis of CDI curves and extreme weather indices allowed for timely detection of weather-related causes of crop damage, which also captured the spatial variations of crop damage attribution at sub-field level. Our approach can help to improve early assessment of crop damage and understand weather causes of such damage, thus informing strategies for crop protection.