pith. sign in

arxiv: 2507.17869 · v3 · submitted 2025-07-23 · 📡 eess.IV · cs.CV· cs.LG

Integrating Feature Selection and Machine Learning for Nitrogen Assessment in Grapevine Leaves using In-Field Hyperspectral Imaging

Atif Bilal Asad , Achyut Paudel , Safal Kshetri , Chenchen Kang , Salik Ram Khanal , Nataliya Shcherbatyuk , Pierre Davadant , R. Paul Schreiner
show 3 more authors
Santosh Kalauni Manoj Karkee Markus Keller
This is my paper

Pith reviewed 2026-05-19 03:19 UTC · model grok-4.3

classification 📡 eess.IV cs.CVcs.LG
keywords hyperspectral imagingnitrogen estimationgrapevinefeature selectionmachine learningcanopy levelleaf levelvineyard monitoring
0
0 comments X

The pith

Ensemble feature selection identifies spectral bands for grapevine nitrogen that transfer from leaf to canopy level.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper develops an ensemble feature selection method to pick the most informative spectral bands from in-field hyperspectral images for estimating nitrogen concentration in grapevine leaves. It collects data from four cultivars across two growth stages and two seasons, testing models at both individual leaf and full canopy scales. The selected bands for Chardonnay and Pinot Noir at the leaf level transfer successfully to canopy predictions, improving or maintaining accuracy for multiple cultivars. This approach points to a practical route for using compact band sets in machine learning models to monitor vineyard nitrogen status more efficiently.

Core claim

The authors demonstrate that an ensemble feature selection framework identifies compact, physiologically meaningful spectral band combinations spanning the visible, red-edge, and near-infrared regions for nitrogen estimation within individual cultivars. At the leaf level, predictive models reach R^2 of 0.82 for Chardonnay and 0.69 for Pinot Noir. Leaf-level N-sensitive bands selected for Chardonnay and Pinot Noir transfer to the canopy level, improving or maintaining prediction accuracy across cultivars, with white cultivars showing balanced spectral contributions and red cultivars relying more on visible bands due to anthocyanin-chlorophyll interactions.

What carries the argument

Ensemble feature selection framework that reduces redundancy by selecting compact, physiologically meaningful band combinations from 400-1000 nm hyperspectral data.

If this is right

  • Leaf-level bands for Chardonnay and Pinot Noir support canopy-level predictions without major accuracy loss.
  • White cultivars balance visible, red-edge, and NIR bands while red cultivars emphasize visible bands due to anthocyanin effects.
  • Compact band sets enable more efficient machine learning for in-field nitrogen monitoring.
  • The method supports scale-consistent nitrogen assessment from leaves to canopies.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Transferable bands could reduce the need for separate calibrations when deploying sensors across different vineyard blocks.
  • Applying the approach to additional crops or regions would test whether the bands capture general traits beyond the current dataset.
  • Integration with automated platforms like drones could enable real-time nitrogen management decisions.

Load-bearing premise

The selected spectral bands reflect stable physiological relationships with nitrogen rather than correlations specific to the four cultivars, two growth stages, and two seasons studied in one region.

What would settle it

Testing the same selected bands on hyperspectral data from a new cultivar or different growing region and obtaining substantially lower R^2 values would undermine the transferability claim.

Figures

Figures reproduced from arXiv: 2507.17869 by Achyut Paudel, Atif Bilal Asad, Chenchen Kang, Manoj Karkee, Markus Keller, Nataliya Shcherbatyuk, Pierre Davadant, R. Paul Schreiner, Safal Kshetri, Salik Ram Khanal, Santosh Kalauni.

Figure 1
Figure 1. Figure 1: Sample leaves used in the study were labeled using white tags (top); binary masks of the tagged [PITH_FULL_IMAGE:figures/full_fig_p009_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: RGB visualization of grapevine canopy with selected 50 [PITH_FULL_IMAGE:figures/full_fig_p010_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Distribution of measured nitrogen concentration in grapevine leaves. (a) Canopy level; (b) Leaf [PITH_FULL_IMAGE:figures/full_fig_p016_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Change in N prediction accuracy metrics (RMSE and [PITH_FULL_IMAGE:figures/full_fig_p017_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Mean reflectance spectrum of grapevine leaves (blue line) with standard deviation (gray shading) [PITH_FULL_IMAGE:figures/full_fig_p018_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Model prediction performance of nitrogen concentration (% DW) at the canopy level using the 8 [PITH_FULL_IMAGE:figures/full_fig_p021_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Model prediction performance of nitrogen concentration (% DW) at the leaf level using the 8 [PITH_FULL_IMAGE:figures/full_fig_p023_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Spectral feature selection results for nitrogen (N) prediction in grapevine leaves, comparing PLSR [PITH_FULL_IMAGE:figures/full_fig_p025_8.png] view at source ↗
read the original abstract

Nitrogen (N) is one of the most critical nutrients in winegrape production, influencing vine vigor, fruit composition, and wine quality. Because soil N availability varies spatially and temporally, accurate estimation of leaf N concentration is essential for optimizing fertilization at the individual plant level. In this study, in-field hyperspectral images (400-1000 nm) were collected from four grapevine cultivars (Chardonnay, Pinot Noir, Concord, and Syrah) across two growth stages (bloom and veraison) during the 2022 and 2023 growing seasons at both the leaf and canopy levels. An ensemble feature selection framework was developed to identify the most informative spectral bands for N estimation within individual cultivars, effectively reducing redundancy and selecting compact, physiologically meaningful band combinations spanning the visible, red-edge, and near-infrared regions. At the leaf level, models achieved the highest predictive accuracy for Chardonnay (R^2 = 0.82, RMSE = 0.19 %DW) and Pinot Noir (R^2 = 0.69, RMSE = 0.20 %DW). Canopy-level predictions also performed well, with R^2 values of 0.65, 0.72, and 0.70 for Chardonnay, Concord, and Syrah, respectively. White cultivars exhibited balanced spectral contributions across the visible, red-edge, and near-infrared regions, whereas red cultivars relied more heavily on visible bands due to anthocyanin-chlorophyll interactions. Leaf-level N-sensitive bands selected for Chardonnay and Pinot Noir were successfully transferred to the canopy level, improving or maintaining prediction accuracy across cultivars. These results confirm that ensemble feature selection captures spectrally robust, scale-consistent bands transferable across measurement levels and cultivars, demonstrating the potential of integrating in-field hyperspectral imaging with machine learning for vineyard N status monitoring.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript presents an ensemble feature selection method applied to in-field hyperspectral imaging (400-1000 nm) collected from four grapevine cultivars (Chardonnay, Pinot Noir, Concord, Syrah) at leaf and canopy scales across two growth stages and two seasons. The approach identifies compact sets of N-sensitive bands in the visible, red-edge, and NIR regions, which are then used with machine learning models to predict leaf nitrogen concentration (%DW), achieving reported R² values of 0.82 (Chardonnay leaf), 0.69 (Pinot Noir leaf), and 0.65-0.72 at canopy level, with leaf-selected bands transferred to improve or maintain canopy predictions across cultivars.

Significance. If the reported transfer of scale-consistent bands holds, the work could support practical vineyard nitrogen monitoring by reducing the dimensionality of hyperspectral data while maintaining predictive performance. Strengths include the concrete, cultivar-differentiated R² and RMSE values and the use of ensemble selection to produce physiologically interpretable band sets; these elements provide a clear basis for assessing the method's utility in precision viticulture.

major comments (2)
  1. [Abstract] Abstract and Results: The central claim of successful transfer of leaf-level bands (selected for Chardonnay and Pinot Noir) to canopy-level predictions for Concord and Syrah rests on data from a single region over two seasons and two stages; without an independent test set or explicit analysis separating shared environmental covariances (e.g., canopy architecture or soil background) from physiological signals, the scale-invariance interpretation remains vulnerable to dataset-specific correlations.
  2. [Methods] Methods and Results: Predictive accuracies (e.g., R² = 0.82 for Chardonnay leaf level) are reported after ensemble feature selection on the same spectral dataset, yet no details are provided on whether nested cross-validation or hold-out sets were used to separate band selection from model evaluation; this directly affects the reliability of the post-selection performance figures that underpin the transfer claim.
minor comments (2)
  1. [Results] Add sample sizes per cultivar and growth stage, along with standard errors or confidence intervals on the reported R² and RMSE values, to allow readers to gauge statistical robustness.
  2. [Methods] Clarify the precise criteria and thresholds used in the ensemble feature selection (e.g., how many bands are retained per ensemble member) and whether these are treated as tunable hyperparameters.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback. We address each major comment below, clarifying our approach where possible and outlining revisions to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract and Results: The central claim of successful transfer of leaf-level bands (selected for Chardonnay and Pinot Noir) to canopy-level predictions for Concord and Syrah rests on data from a single region over two seasons and two stages; without an independent test set or explicit analysis separating shared environmental covariances (e.g., canopy architecture or soil background) from physiological signals, the scale-invariance interpretation remains vulnerable to dataset-specific correlations.

    Authors: We acknowledge the limitation of collecting data from a single experimental vineyard, which is typical for detailed in-field hyperspectral campaigns. The study design incorporates four cultivars, two growth stages, and two seasons to introduce variability in physiological and environmental conditions. The successful transfer of leaf-selected bands to canopy predictions across both white and red cultivars, with maintained or improved accuracy, provides supporting evidence that the bands capture N-related physiological signals rather than purely site-specific correlations. We will revise the Discussion to include an explicit analysis of potential confounding factors such as canopy architecture and soil background, and we will add a limitations paragraph acknowledging the need for multi-site validation in future studies. revision: partial

  2. Referee: [Methods] Methods and Results: Predictive accuracies (e.g., R² = 0.82 for Chardonnay leaf level) are reported after ensemble feature selection on the same spectral dataset, yet no details are provided on whether nested cross-validation or hold-out sets were used to separate band selection from model evaluation; this directly affects the reliability of the post-selection performance figures that underpin the transfer claim.

    Authors: We appreciate this observation and agree that the Methods section requires greater clarity on the validation strategy. Our analysis used a nested cross-validation framework in which ensemble feature selection was conducted exclusively within the inner training folds, with model evaluation performed on the outer test folds to avoid selection bias. We will revise the Methods to explicitly describe this nested procedure, specify the number of folds, and include a schematic or pseudocode illustrating the separation between band selection and performance reporting. revision: yes

Circularity Check

0 steps flagged

No significant circularity; empirical ML pipeline remains self-contained

full rationale

The paper presents an empirical study: ensemble feature selection identifies bands from leaf-level spectra of two cultivars, those bands are then used as inputs to train ML models on canopy spectra, and accuracies are reported for the resulting fits. No equations or steps reduce a claimed prediction to the selection step by construction, nor does any result rely on a self-citation chain that itself lacks independent verification. The transfer claim is an experimental observation on held-out cultivar/stage data rather than a definitional identity. Standard ML practices here do not trigger any of the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

2 free parameters · 1 axioms · 0 invented entities

The central claim rests on empirical correlations between selected hyperspectral bands and measured nitrogen content derived from field-collected data rather than first-principles physics or chemistry.

free parameters (2)
  • Ensemble feature selection thresholds
    Thresholds and combination rules for selecting the final compact band sets from multiple selectors.
  • Machine learning model hyperparameters
    Hyperparameters of the regression models used to map selected bands to nitrogen concentration.
axioms (1)
  • domain assumption Leaf and canopy reflectance in 400-1000 nm contains information linearly or non-linearly related to nitrogen concentration
    Core premise of hyperspectral nutrient sensing invoked throughout the study design and interpretation.

pith-pipeline@v0.9.0 · 5930 in / 1397 out tokens · 36617 ms · 2026-05-19T03:19:35.263346+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

48 extracted references · 48 canonical work pages

  1. [1]

    write newline

    " write newline "" before.all 'output.state := FUNCTION n.dashify 't := "" t empty not t #1 #1 substring "-" = t #1 #2 substring "--" = not "--" * t #2 global.max substring 't := t #1 #1 substring "-" = "-" * t #2 global.max substring 't := while if t #1 #1 substring * t #2 global.max substring 't := if while FUNCTION word.in bbl.in ":" * " " * FUNCTION f...

    work page

  2. [2]

    , author Hruska, J

    author Adao, T. , author Hruska, J. , author Padua, L. , author Bessa, J. , author Peres, E. , author Morais, R. , author Sousa, J.J. , year 2017 . title Hyperspectral imaging: A review on uav-based sensors, data processing and applications for agriculture and forestry . journal Remote sensing volume 9 , pages 1110

    work page 2017

  3. [3]

    , author Plaza, A

    author Bioucas-Dias, J.M. , author Plaza, A. , author Camps-Valls, G. , author Scheunders, P. , author Nasrabadi, N. , author Chanussot, J. , year 2013 . title Hyperspectral remote sensing data analysis and future challenges . journal IEEE Geoscience and Remote Sensing Magazine volume 1 , pages 6--36 . :10.1109/MGRS.2013.2244672

    work page doi:10.1109/mgrs.2013.2244672 2013

  4. [4]

    , author Spiering, B.A

    author Carter, G.A. , author Spiering, B.A. , year 2001 . title Leaf spectral reflectance and chlorophyll content: A multivariate analysis . journal Remote Sensing of Environment volume 75 , pages 212--223

    work page 2001

  5. [5]

    , author Bates, T

    author Chancia, R. , author Bates, T. , author Vanden Heuvel, J. , author van Aardt, J. , year 2021 . title Assessing grapevine nutrient status from unmanned aerial system (uas) hyperspectral imagery . journal Remote Sensing volume 13 , pages 4489

    work page 2021

  6. [6]

    , author Kim, M.S

    author Chappelle, E.W. , author Kim, M.S. , author McMurtrey III, J.E. , year 1992 . title Ratio analysis of reflectance spectra (rars): an algorithm for the remote estimation of the concentrations of chlorophyll a, chlorophyll b, and carotenoids in soybean leaves . journal Remote sensing of environment volume 39 , pages 239--247

    work page 1992

  7. [7]

    , year 1989

    author Curran, P.J. , year 1989 . title Remote sensing of foliar chemistry . journal Remote sensing of environment volume 30 , pages 271--278

    work page 1989

  8. [8]

    , author Paul, M

    author Debnath, S. , author Paul, M. , author Rahaman, D.M. , author Debnath, T. , author Zheng, L. , author Baby, T. , author Schmidtke, L.M. , author Rogiers, S.Y. , year 2021 . title Identifying individual nutrient deficiencies of grapevine leaves using hyperspectral imaging . journal Remote Sensing volume 13 , pages 3317

    work page 2021

  9. [9]

    , author Du, B

    author Dong, Y. , author Du, B. , author Zhang, L. , author Zhang, L. , year 2017 . title Dimensionality reduction and classification of hyperspectral images using ensemble discriminative local metric learning . journal IEEE Transactions on Geoscience and Remote Sensing volume 55 , pages 2509--2524

    work page 2017

  10. [10]

    , year 1989

    author Evans, J.R. , year 1989 . title Photosynthesis and nitrogen relationships in leaves of c3 plants . journal Oecologia volume 78 , pages 9--19

    work page 1989

  11. [11]

    , author Zhao, J

    author Fan, L. , author Zhao, J. , author Xu, X. , author Liang, D. , author Yang, G. , author Feng, H. , author Yang, H. , author Wang, Y. , author Chen, G. , author Wei, P. , year 2019 . title Hyperspectral-based estimation of leaf nitrogen content in corn using optimal selection of multiple spectral variables . journal Sensors volume 19 , pages 2898

    work page 2019

  12. [12]

    , author Qiu, H.L

    author Gamon, J.A. , author Qiu, H.L. , author Sanchez-Azofeifa, A. , year 2007 . title Ecological applications of remote sensing at multiple scales . publisher CRC Press

    work page 2007

  13. [13]

    , author O'Donnell, C.P

    author Gowen, A.A. , author O'Donnell, C.P. , author Cullen, P.J. , author Downey, G. , author Frias, J.M. , year 2007 . title Hyperspectral imaging--an emerging process analytical tool for food quality and safety control . journal Trends in food science & technology volume 18 , pages 590--598

    work page 2007

  14. [14]

    , author Schjoerring, J

    author Hansen, P. , author Schjoerring, J. , year 2003 . title Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression . journal Remote sensing of environment volume 86 , pages 542--553

    work page 2003

  15. [15]

    , et al., year 2020

    author Hennessy, D. , et al., year 2020 . title Hyperspectral imaging for plant disease detection and plant phenotyping . journal Trends in Plant Science volume 25 , pages 1000--1016

    work page 2020

  16. [16]

    , author Colvin, T

    author Jaynes, D. , author Colvin, T. , author Karlen, D. , author Cambardella, C. , author Meek, D. , year 2001 . title Nitrate loss in subsurface drainage as affected by nitrogen fertilizer rate . journal Journal of environmental quality volume 30 , pages 1305--1314

    work page 2001

  17. [17]

    , author Lalonde, M

    author Kalacska, M. , author Lalonde, M. , author Moore, T. , year 2015 . title Estimation of foliar chlorophyll and nitrogen content in an ombrotrophic bog from hyperspectral data: Scaling from leaf to image . journal Remote Sensing of Environment volume 169 , pages 270--279

    work page 2015

  18. [18]

    , author Diverres, G

    author Kang, C. , author Diverres, G. , author Achyut, P. , author Karkee, M. , author Zhang, Q. , author Keller, M. , year 2023 . title Estimating soil and grapevine water status using ground based hyperspectral imaging under diffused lighting conditions: Addressing the effect of lighting variability in vineyards . journal Computers and Electronics in Ag...

    work page 2023

  19. [19]

    , author Diverres, G

    author Kang, C. , author Diverres, G. , author Karkee, M. , author Zhang, Q. , author Keller, M. , year 2024 . title Assessing grapevine water status through fusion of hyperspectral imaging and 3d point clouds . journal Computers and Electronics in Agriculture volume 226 , pages 109488

    work page 2024

  20. [20]

    , year 2020

    author Keller, M. , year 2020 . title The Science of Grapevines . edition 3 ed., publisher Elsevier Academic Press , address London, UK

    work page 2020

  21. [21]

    , author Hrazdina, G

    author Keller, M. , author Hrazdina, G. , year 1998 . title Interaction of nitrogen availability during bloom and light intensity during veraison. ii. effects on anthocyanin and phenolic development during grape ripening . journal American Journal of Enology and Viticulture volume 49 , pages 341--349

    work page 1998

  22. [22]

    , author Ji, M

    author Liu, L. , author Ji, M. , author Buchroithner, M. , year 2017 . title Combining partial least squares and the gradient-boosting method for soil property retrieval using visible near-infrared shortwave infrared spectra . journal Remote Sensing volume 9 , pages 1299

    work page 2017

  23. [23]

    , author Townsend, P.A

    author Liu, N. , author Townsend, P.A. , author Naber, M.R. , author Bethke, P.C. , author Hills, W.B. , author Wang, Y. , year 2021 . title Hyperspectral imagery to monitor crop nutrient status within and across growing seasons . journal Remote Sensing of Environment volume 255 , pages 112303

    work page 2021

  24. [24]

    , author Grafton, M

    author Lyu, H. , author Grafton, M. , author Ramilan, T. , author Irwin, M. , author Sandoval, E. , year 2023 . title Assessing the leaf blade nutrient status of pinot noir using hyperspectral reflectance and machine learning models . journal Remote Sensing volume 15 , pages 1497

    work page 2023

  25. [25]

    , author Gong, C

    author Ma, W. , author Gong, C. , author Hu, Y. , author Meng, P. , author Xu, F. , year 2013 . title The hughes phenomenon in hyperspectral classification based on the ground spectrum of grasslands in the region around qinghai lake , in: booktitle International Symposium on Photoelectronic Detection and Imaging 2013: Imaging Spectrometer Technologies and...

    work page 2013

  26. [26]

    , author Liland, K.H

    author Mehmood, T. , author Liland, K.H. , author Snipen, L. , author Sæbø, S. , year 2012 . title A review of variable selection methods in partial least squares regression . journal Chemometrics and Intelligent Laboratory Systems volume 118 , pages 62--69 . https://www.sciencedirect.com/science/article/pii/S0169743912001542, :https://doi.org/10.1016/j.c...

    work page doi:10.1016/j.chemolab.2012.07.010 2012

  27. [27]

    , author Yang, C

    author Moghimi, A. , author Yang, C. , author Marchetto, P.M. , year 2018 . title Ensemble feature selection for plant phenotyping: a journey from hyperspectral to multispectral imaging . journal IEEE Access volume 6 , pages 56870--56884

    work page 2018

  28. [28]

    , author Moghimi, A

    author Omidi, R. , author Moghimi, A. , author Pourreza, A. , author El-Hadedy, M. , author Eddin, A.S. , year 2020 . title Ensemble hyperspectral band selection for detecting nitrogen status in grape leaves , in: booktitle 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA) , pp. pages 286--293

    work page 2020

  29. [29]

    , author Brown, J

    author Paudel, A. , author Brown, J. , author Upadhyaya, P. , author Asad, A.B. , author Kshetri, S. , author Davidson, J.R. , author Grimm, C. , author Thompson, A. , author Sallato, B. , author Whiting, M.D. , et al., year 2025 . title Machine vision-based assessment of fall color changes in apple leaves and its relationship with nitrogen concentration ...

    work page 2025

  30. [30]

    , author Pourreza, A

    author Peanusaha, S. , author Pourreza, A. , author Kamiya, Y. , author Fidelibus, M.W. , author Chakraborty, M. , year 2024 . title Nitrogen retrieval in grapevine (vitis vinifera l.) leaves by hyperspectral sensing . journal Remote Sensing of Environment volume 302 , pages 113966

    work page 2024

  31. [31]

    , author Chen, D

    author Peng, X. , author Chen, D. , author Zhou, Z. , author Zhang, Z. , author Xu, C. , author Zha, Q. , author Wang, F. , author Hu, X. , year 2022 . title Prediction of the nitrogen, phosphorus and potassium contents in grape leaves at different growth stages based on uav multispectral remote sensing . journal Remote Sensing volume 14 , pages 2659

    work page 2022

  32. [32]

    , author Filella, I

    author Pe \ n uelas, J. , author Filella, I. , author Biel, C. , author Serrano, L. , author Save, R. , year 1993 . title The reflectance at the 950--970 nm region as an indicator of plant water status . journal International journal of remote sensing volume 14 , pages 1887--1905

    work page 1993

  33. [33]

    , author Louarn, G

    author Prieto, J.A. , author Louarn, G. , author Perez Pena, J. , author Ojeda, H. , author Simonneau, T. , author Lebon, E. , year 2012 . title A leaf gas exchange model that accounts for intra-canopy variability by considering leaf nitrogen content and local acclimation to radiation in grapevine (vitis vinifera l.) . journal Plant, cell & environment vo...

    work page 2012

  34. [34]

    , author Kereszturi, G

    author Pullanagari, R. , author Kereszturi, G. , author Yule, I. , year 2016 . title Mapping of macro and micro nutrients of mixed pastures using airborne aisafenix hyperspectral imagery . journal ISPRS Journal of Photogrammetry and Remote Sensing volume 117 , pages 1--10

    work page 2016

  35. [35]

    , author Verrelst, J

    author Rivera-Caicedo, J.P. , author Verrelst, J. , author Mu \ n oz-Mar \' , J. , author Camps-Valls, G. , author Moreno, J. , year 2017 . title Hyperspectral dimensionality reduction for biophysical variable statistical retrieval . journal ISPRS journal of photogrammetry and remote sensing volume 132 , pages 88--101

    work page 2017

  36. [36]

    , year 2005

    author Robinson, J.B. , year 2005 . title Critical plant tissue values and application of nutritional standards for practical use in vineyards. . publisher American Society for Enology and Viticulture , address Davis . p. pages 61–68

    work page 2005

  37. [37]

    , author Grossi, D

    author Rustioni, L. , author Grossi, D. , author Brancadoro, L. , author Failla, O. , year 2018 . title Iron, magnesium, nitrogen and potassium deficiency symptom discrimination by reflectance spectroscopy in grapevine leaves . journal Scientia Horticulturae volume 241 , pages 152--159

    work page 2018

  38. [38]

    , author Lee, J

    author Schreiner, R.P. , author Lee, J. , author Skinkis, P.A. , year 2013 . title N, p, and k supply to pinot noir grapevines: Impact on vine nutrient status, growth, physiology, and yield . journal American Journal of Enology and Viticulture volume 64 , pages 26--38

    work page 2013

  39. [39]

    , author Batra, N

    author Sharma, S. , author Batra, N. , author et al. , year 2019 . title Comparative study of single linkage, complete linkage, and ward method of agglomerative clustering , in: booktitle 2019 international conference on machine learning, big data, cloud and parallel computing (COMITCon) , organization IEEE . pp. pages 568--573

    work page 2019

  40. [40]

    , author Gamon, J.A

    author Sims, D.A. , author Gamon, J.A. , year 2003 . title Estimation of vegetation water content and photosynthetic tissue area from spectral reflectance: a comparison of indices based on liquid water and chlorophyll absorption features . journal Remote sensing of environment volume 84 , pages 526--537

    work page 2003

  41. [41]

    , year 1991

    author Smart, R. , year 1991 . title Canopy microclimate implications for nitrogen effects on yield and quality , in: booktitle Proceedings of the International Symposium on Nitrogen in Grapes and Wine: Seattle, Washington, Usa 18-19 june 1991 , organization American Society for Enology and Viticulture, ASEV . pp. pages 90--101

    work page 1991

  42. [42]

    , author Zioziou, E

    author Thomidis, T. , author Zioziou, E. , author Koundouras, S. , author Karagiannidis, C. , author Navrozidis, I. , author Nikolaou, N. , year 2016 . title Effects of nitrogen and irrigation on the quality of grapes and the susceptibility to botrytis bunch rot . journal Scientia Horticulturae volume 212 , pages 60--68

    work page 2016

  43. [43]

    title Press release

    author USDA, NASS , year 2024 . title Press release . https://www.nass.usda.gov/Statistics_by_State/Idaho/Publications/Census_Press_Releases/2024/FRUIT.pdf

    work page 2024

  44. [44]

    , author Dienes-Nagy, \'A

    author Verdenal, T. , author Dienes-Nagy, \'A . , author Spangenberg, J. , author Zufferey, V. , author Spring, J.L. , author Viret, O. , author Marin-Carbonne, J. , author Van Leeuwen, C. , year 2021 . title Understanding and managing nitrogen nutrition in grapevine: A review . journal Oeno one volume 55

    work page 2021

  45. [45]

    , author Ecarnot, M

    author Vigneau, N. , author Ecarnot, M. , author Rabatel, G. , author Roumet, P. , year 2011 . title Potential of field hyperspectral imaging as a non destructive method to assess leaf nitrogen content in wheat . journal Field Crops Research volume 122 , pages 25--31

    work page 2011

  46. [46]

    , author Zhao, C.j

    author Xu, X.g. , author Zhao, C.j. , author Wang, J.h. , author Zhang, J.c. , author Song, X.y. , year 2014 . title Using optimal combination method and in situ hyperspectral measurements to estimate leaf nitrogen concentration in barley . journal Precision Agriculture volume 15 , pages 227--240

    work page 2014

  47. [47]

    , author Huang, Y

    author Yao, X. , author Huang, Y. , author Shang, G. , author Zhou, C. , author Cheng, T. , author Tian, Y. , author Cao, W. , author Zhu, Y. , year 2015 . title Evaluation of six algorithms to monitor wheat leaf nitrogen concentration . journal Remote Sensing volume 7 , pages 14939--14966

    work page 2015

  48. [48]

    , author Wang, Q

    author Zou, X. , author Wang, Q. , author Chen, Y. , author Wang, J. , author Xu, S. , author Zhu, Z. , author Yan, C. , author Shan, P. , author Wang, S. , author Fu, Y. , year 2025 . title Fusion of convolutional neural network with xgboost feature extraction for predicting multi-constituents in corn using near infrared spectroscopy . journal Food Chemi...

    work page 2025