Accurate assessment of grass nitrogen status based on multispectral data from two optical sensors and the critical nitrogen dilution curve
Bibliographic record
Abstract
The critical nitrogen dilution curve (CNDC) is efficient for diagnosing plant nitrogen (N) deficiency. For perennial plants, including grasses (family Poaceae), deriving CNDC is not straightforward due to in-season modulations by cuts and fertilization. Gislum et al. (2009) developed CNDC for grass species for seed production in Denmark and suggested improvements since it was not possible to calculate a % critical N concentration at biomass lower than 2 Mg ha-1. Optical sensors deployed on the field can partly answer the question of how much and when to fertilize, e.g., the Yara’s N tester (Yara International ASA, Oslo, Norway) that allows assessing plant N requirement and real-time variable-rate spread of fertilizer. Moreover, multispectral data from unmanned aerial vehicle (UAV) with their ultra-high spatial and temporal resolution can also be used to estimate crop N status (Peng et al., 2021), though high accuracy is difficult to achieve due to the dynamics and the transformation of N. Accurate N management requires establishment of a solid ‘link’ between the remote sensing data and the crop N status. Parametric regression involving models of linear or nonlinear nature has often been used for describing this link (Peng et al., 2021). Peng et al. (2021) investigated how well potato N status can be described by RS data obtained from ground, air- and spaceborne sensors using parametric and non-parametric, i.e., machine learning regression. Few previous studies have used RS to calculate the N status of grasses and predict their N requirements. The objective of this study is to estimate precisely the amount of N fertilizer needed for optimal plant growth according to N requirement and the CNDC by two optical sensors (Yara N sensor and UAV-mounted) based on machine learning method (random forest and alike). Two-year field experiment has been initiated with grass (Lolium perenne) in 2022 and 2023 (established in September 2021) on a sandy loam soil in Denmark, with four nitrogen rates (N0: 0 kg ha-1, N1: 75 kg ha-1, N2: 300 kg ha-1 and N3: 450 kg ha-1). We present initial results of the canopy multispectral reflectance and CNDC developed for the grass and provide novel insight for improving N diagnosis and management of grass in Denmark and Europe.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".