Vita Antoniuk

Advances in satellite- and drone-based technologies, such as increased spatio-temporal and spectral resolution, in combination with improved computational algorithms, including machine learning, have proven to be useful tools altogether in assessing crop nitrogen (N) status and facilitating precision agriculture. However, it remains challenging to accurately determine in-season crop N status and detach split fertilization from residual soil N prone to losses during (gaseous emissions) and after the growth season (leaching). We conducted a three-year potato field experiment on sandy soil in Denmark (Peng et al. 2021) and determined single-shot in-season plant N uptake (PNU), concentration (PNC) and N nutrition index (NNI; based on the critical N dilution curve). Multispectral data obtained by spaceborne- (Sentinel-2), air- (unmanned aerial vehicle, UAV) and ground (handheld Rapidscan) platforms were correlated with the measured variables, with random forest machine learning regression achieving very high prediction accuracy of < 10kg N ha-1 uncertainty. We also measured nitrate concentration in the soil solution at the end of the root zone, and these measurements showed on average consistently lower values for the split- (16-42 ppm) compared to the full (20-57 ppm) fertilization strategy, with reductions reaching 37% at the peak of the leaching season in November. The approach of accurately detecting plant N requirement and supplying fertilization accordingly, which leaves little substrate of reactive N pool in the soil during and after the growth season is promising for the smart farming industry in the struggle to limit nitrous oxide emissions and N leaching by keeping soil nitrate concentration at low levels. More work should also be done on bridging N deficiency from other abiotic stresses, especially drought, in order to further improve N application recommendation.