Figure 5 - uploaded by Markus Möller
Content may be subject to copyright.
Drought stress between stem elongation and booting (SEB; late vegetative phase) for moderate (< 50 % P AW C), severe (< 30 % P AW C) and extreme (<10 % P AW C) stress intensities. Mean occurrence (A, D, G) describes the average number of days above the respective thresholds between 1995 and 2019 at the municipality level. Estimated coefficients (B, E, H) describes the WI x SCR regression coefficients of equation 1 for each SCR. Non-significant values are given in dark grey. Significant values are given in red (negative effect) or blue (positive effect). The regression coefficients and p-values are displayed in the tables Appendix C.16, Appendix C.17, Appendix C.18. Mean yield effects (C, F, I) describes the average yield change in dt ha −1 per municipality between 1995 and 2019. The median values below each map refer to the median of all municipality's/SCR with significant effects on the respective index.
Similar publications
A pot experiment was conducted to study the Morphological Characterization analysis of seven tomato genotypes under drought stress conditions for the traits i.e., Plant height, Number of Clusters Per Plant, Number of Flowers Per Clusters, Number of Fruits Per Plant, Average Fruits Weight and Yield Per Plant. Contrary to irrigated crops, drought-str...
The combined effects of increasing sulfur (S) fertilization rates and drought stress on the yield and compositional parameters of spring wheat on Chernozem soil were studied. In a greenhouse pot experiment, increasing S doses (22.4, 28, 56 kg S/ha) were used with a constant nitrogen (N) dose (112 kg N/ha), resulting in different N:S ratios (1:0.2;...
Sorghum (Sorghum bicolor) is a vital crop known for its resilience to drought, making it a promising candidate for cultivation in water-scarce regions. This study assessed the impact of water stress on the flowering phenology and yield attributes of twenty sorghum genotypes over two rabi seasons (2021-22 and 2022-23) under both rainfed and irrigate...
Citations
Detailed and accurate statistics on crop productivity are key to inform decision-making related to sustainable food production and supply ensuring global food security. However, annual and high-resolution crop yield data provided by official agricultural statistics are generally lacking. Earth observation (EO) imagery, geodata on meteorological and soil conditions, as well as advances in machine learning (ML) provide huge opportunities for model-based crop yield estimation in terms of covering large spatial scales with unprecedented granularity. This study proposes a novel yield estimation approach that is bottom-up scalable from parcel to administrative levels by leveraging ML-ensembles, comprising of six regression estimators (base estimators), and multi-source geodata, including EO imagery. To ensure the approach’s robustness, two ensemble learning techniques are investigated, namely meta-learning through model stacking and majority voting. ML-ensembles were evaluated multi-annually and crop-specifically for three major winter crops, namely winter wheat (WW), winter barley (WB), and winter rapeseed (WR) in two German federal states, covering 140,000 to 155,000 parcels per year. ML-ensembles were evaluated at the parcel and district level for two German federal states against official yield reports, ranging from 2019 to 2022, based on metrics such as coefficient of determination (RSQ) and normalized root mean square error (nRMSE). Overall, the most robustly performing ensemble learning technique was majority voting yielding RSQ and nRMSE values of 0.74, 13.4% for WW, 0.68, 16.9% for WB, and 0.66, 14.1% for WR, respectively, through cross-validation at parcel level. At the district level, majority voting reached RSQ and nRMSE ranges of 0.79–0.89, 7.2–8.1% for WW, 0.80–0.84, 6.0–9.9% for WB, and 0.60–0.78, 6.1–10.4% for WR, respectively. Capitalizing on ensemble learning-based majority voting, examples of unprecedented high-resolution crop yield maps at spatial resolution are presented. Implementing a scalable yield estimation approach, as proposed in this study, into crop yield reporting frameworks of public authorities mandated to provide official agricultural statistics would increase the spatial resolution of annually reported yields, eventually covering the entire cropland available. Such unprecedented data products delivered through map services may improve decision-making support for a variety of stakeholders across different spatial scales, ranging from parcel to higher administrative levels.
