pith. sign in

arxiv: 2606.26972 · v1 · pith:6KFPHIYDnew · submitted 2026-06-25 · 📊 stat.ME

Predicting disease severity and large-scale spread from coupled severity measurements and imperfect indicators: Application to beet yellows

Baptiste Oger , C\'esar Martinez , Fran\c{c}ois Joudelat , Samuel Soubeyrand , Lionel Benoit This is my paper

Pith reviewed 2026-06-26 02:41 UTC · model grok-4.3

classification 📊 stat.ME
keywords beet yellowsdisease severityspatio-temporal modelingrandom forestshurdle modelsremote sensingzero-inflated dataepidemiological dynamics
0
0 comments X

The pith

A two-step statistical framework uses indirect indicators like satellite data to predict local disease severity and reconstruct large-scale spread while handling zero inflation and spatio-temporal structure.

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

The paper develops a two-step statistical method to predict disease severity locally and reconstruct large-scale spread by integrating direct measurements with indirect indicators. Stacked hurdle random forest models handle zero-inflated severity data in the prediction step using satellite and other indicators. A semi-parametric spatio-temporal model then reconstructs the dynamics, accounting for spatial and temporal structures. Applied to beet yellows in France from 2019 to 2023, it shows the potential to use broad-coverage but noisy data for effective disease management across plant, animal, or human health contexts.

Core claim

The authors establish that their two-step approach, consisting of stacked hurdle models based on random forests for local predictions from indirect indicators and a semi-parametric spatio-temporal model for reconstruction, successfully leverages imperfect indirect indicators to predict disease severity and dynamics while accounting for zero inflation and spatio-temporal structure in the data.

What carries the argument

The two-step framework of stacked hurdle random forest models for local severity prediction from indirect indicators, followed by a semi-parametric spatio-temporal model for large-scale reconstruction.

If this is right

  • Local severity can be predicted even with sparse direct data by using the indirect indicators.
  • Large-scale disease dynamics can be reconstructed over space and time from the local predictions.
  • The method is modular and generic, applicable to different diseases and indicator types.
  • It specifically addresses zero inflation and spatio-temporal dependencies in the observations.

Where Pith is reading between the lines

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

  • This approach might enable more frequent monitoring in resource-limited settings by supplementing field data with remote sensing.
  • The framework could be tested on human or animal diseases where similar indirect indicators are available.
  • Extensions might include uncertainty quantification in the predictions to improve reliability of the reconstructions.

Load-bearing premise

The indirect indicators contain sufficient signal to allow the stacked hurdle random forest models to produce usable local severity predictions that can then be fed into the spatio-temporal reconstruction step.

What would settle it

A field validation campaign that measures actual disease severity in locations where the model predicts high or low values and finds no agreement between predictions and measurements would falsify the central claim.

Figures

Figures reproduced from arXiv: 2606.26972 by Baptiste Oger, C\'esar Martinez, Fran\c{c}ois Joudelat, Lionel Benoit, Samuel Soubeyrand.

Figure 1
Figure 1. Figure 1: A1 to A4: Spatial distribution of observations of sugar beet yellows severity for available [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Global workflow for the stacked hurdle model. [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Each panel represents the mean relative importance (%) of each covariate for initial [PITH_FULL_IMAGE:figures/full_fig_p010_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: RMSE validation —for both initial and final learner— versus the proportion of data [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Comparison of observed values with predicted values on validation data when 20% of [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Temporal evolution of sugar beet yellows severity predicted by the spatio-temporal [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
read the original abstract

Whether in human, animal, or plant health, effective disease management requires the ability to characterize disease dynamics across space and time. In this context, integrating indirect indicators with broad spatio-temporal coverage, even when they are noisy, can provide valuable complementary information to direct measurements, which are often sparse because they are more costly or intrusive to collect. In this article, we propose a statistical framework to leverage such indirect indicators to predict disease severity at the individual or local-scale level and reconstruct large-scale disease dynamics. This two-step approach is able to account for the specific characteristics of disease severity observations, including zero inflation and spatio-temporal structure. The first step relies on a stacked hurdle model based on multiple random forests to locally predict disease severity from the available indirect indicators. In the second step a semi-parametric spatio-temporal model is used to reconstruct large-scale epidemiological dynamics over space and time from the indicators-based predictions. The proposed methodology is designed to be both generic and modular, and is illustrated by a case study in plant health. This case study focuses on the monitoring of sugar beet yellows disease in France between 2019 and 2023 by combining sparse field measurements and satellite-based remote sensing data.

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 paper proposes a two-step statistical framework to predict local disease severity from imperfect indirect indicators (e.g., satellite remote sensing) while accounting for zero inflation, then reconstruct large-scale spatio-temporal disease dynamics. Step 1 uses stacked hurdle random forest models for local predictions; Step 2 feeds those predictions into a semi-parametric spatio-temporal model. The approach is presented as generic and modular and is illustrated via a case study on sugar beet yellows monitoring in France (2019–2023) that combines sparse field measurements with satellite data.

Significance. If the two-step procedure can be shown to produce usable local predictions whose errors do not materially distort the reconstructed dynamics, the framework would offer a practical way to fuse noisy broad-coverage indicators with sparse direct observations in plant and animal epidemiology. The explicit handling of zero inflation and the modular design are clear strengths; however, the absence of reported quantitative validation metrics (prediction accuracy, cross-validation scores, or comparison against direct measurements) in the abstract leaves the practical performance unassessed.

major comments (2)
  1. [Method (two-step procedure)] The manuscript provides no description of how prediction uncertainty or bias from the first-step stacked hurdle random forests is propagated into the second-step semi-parametric spatio-temporal model. Treating the RF outputs as if they were observed data risks feeding forward spatially structured residuals arising from imperfect satellite indicators or unmodeled factors, which could bias or overstate the reconstructed large-scale dynamics.
  2. [Abstract and case-study description] The abstract and method outline claim that the stacked hurdle random forests produce usable local severity predictions, yet no quantitative performance metrics, cross-validation results, or comparison against held-out field measurements are referenced. Without such evidence the central claim that the two-step approach successfully accounts for the characteristics of disease severity observations cannot be evaluated.
minor comments (2)
  1. [Step 1 description] Clarify the exact stacking procedure and how the hurdle components are combined across the multiple random forests.
  2. [Step 2 description] Specify the form of the semi-parametric spatio-temporal model (basis functions, covariance structure, or software implementation).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive review. The comments highlight important aspects of uncertainty handling and the need for explicit validation evidence. We address each point below and commit to revisions that strengthen the manuscript without altering its core claims.

read point-by-point responses

  1. Referee: [Method (two-step procedure)] The manuscript provides no description of how prediction uncertainty or bias from the first-step stacked hurdle random forests is propagated into the second-step semi-parametric spatio-temporal model. Treating the RF outputs as if they were observed data risks feeding forward spatially structured residuals arising from imperfect satellite indicators or unmodeled factors, which could bias or overstate the reconstructed large-scale dynamics.

    Authors: We agree that the manuscript does not describe propagation of prediction uncertainty or bias from the stacked hurdle random forests into the semi-parametric spatio-temporal model; the first-step outputs are used as fixed inputs. This is a genuine methodological limitation that could allow spatially structured residuals to influence the large-scale reconstruction. In the revised manuscript we will add an explicit discussion of this issue in the Methods and Discussion sections, together with a sensitivity analysis that perturbs the first-step predictions within their observed error ranges and re-runs the second-step model to quantify downstream effects on the reconstructed dynamics. revision: yes

  2. Referee: [Abstract and case-study description] The abstract and method outline claim that the stacked hurdle random forests produce usable local severity predictions, yet no quantitative performance metrics, cross-validation results, or comparison against held-out field measurements are referenced. Without such evidence the central claim that the two-step approach successfully accounts for the characteristics of disease severity observations cannot be evaluated.

    Authors: The case-study section of the full manuscript reports cross-validation results, prediction accuracy metrics, and direct comparisons against held-out field measurements for the stacked hurdle random forest models. These quantitative results are not summarized in the abstract. We will revise the abstract to include the key performance figures (e.g., cross-validated AUC for the hurdle component and RMSE for severity predictions) so that the claim of usable local predictions is immediately supported by evidence. revision: yes

Circularity Check

0 steps flagged

No significant circularity; standard two-step predictive pipeline on external data

full rationale

The described methodology trains stacked hurdle random forests on indirect indicators (e.g., satellite data) to generate local severity predictions, then feeds those outputs into a separate semi-parametric spatio-temporal model for large-scale reconstruction. This is a conventional data-driven workflow with no self-definitional steps, no fitted parameters renamed as predictions, and no load-bearing self-citations or uniqueness theorems that reduce the central claim to its own inputs. The approach remains self-contained against external benchmarks and does not exhibit any of the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no details on free parameters, axioms, or invented entities; all entries are therefore unknown.

pith-pipeline@v0.9.1-grok · 5763 in / 1115 out tokens · 41630 ms · 2026-06-26T02:41:58.677026+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

88 extracted references · 79 canonical work pages

  1. [1]

    Journal of Statistical Distributions and Applications , author =

    A comparison of zero-inflated and hurdle models for modeling zero-inflated count data , volume =. Journal of Statistical Distributions and Applications , author =. 2021 , keywords =. doi:10.1186/s40488-021-00121-4 , abstract =

    work page doi:10.1186/s40488-021-00121-4 2021

  2. [2]

    PLOS Neglected Tropical Diseases , author =

    Hybrid. PLOS Neglected Tropical Diseases , author =. 2024 , keywords =. doi:10.1371/journal.pntd.0012599 , abstract =

    work page doi:10.1371/journal.pntd.0012599 2024

  3. [3]

    Remote Sensing Letters , author =

    Contextual land-cover classification: incorporating spatial dependence in land-cover classification models using random forests and the. Remote Sensing Letters , author =. 2010 , pages =. doi:10.1080/01431160903252327 , abstract =

    work page doi:10.1080/01431160903252327 2010

  4. [4]

    PeerJ , author =

    Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables , volume =. PeerJ , author =. 2018 , pages =. doi:10.7717/peerj.5518 , abstract =

    work page doi:10.7717/peerj.5518 2018

  5. [5]

    Journal of Agricultural, Biological and Environmental Statistics , author =

    Longitudinal. Journal of Agricultural, Biological and Environmental Statistics , author =. 2025 , keywords =. doi:10.1007/s13253-025-00686-6 , abstract =

    work page doi:10.1007/s13253-025-00686-6 2025

  6. [6]

    Building predictive models in R using the caret package

    Building. Journal of Statistical Software , author =. 2008 , pages =. doi:10.18637/jss.v028.i05 , abstract =

    work page doi:10.18637/jss.v028.i05 2008

  7. [7]

    Statistical Science , author =

    Statistical. Statistical Science , author =. 2019 , pages =

    2019

  8. [8]

    Computers and Electronics in Agriculture , author =

    A random forest-based algorithm for data-intensive spatial interpolation in crop yield mapping , volume =. Computers and Electronics in Agriculture , author =. 2021 , keywords =. doi:10.1016/j.compag.2021.106094 , abstract =

    work page doi:10.1016/j.compag.2021.106094 2021

  9. [9]

    Probst, M

    Hyperparameters and tuning strategies for random forest , volume =. WIREs Data Mining and Knowledge Discovery , author =. 2019 , keywords =. doi:10.1002/widm.1301 , abstract =

    work page doi:10.1002/widm.1301 2019

  10. [10]

    Engineering Applications of Artificial Intelligence , author =

    Dealing with zero-inflated data:. Engineering Applications of Artificial Intelligence , author =. 2025 , keywords =. doi:10.1016/j.engappai.2025.110339 , abstract =

    work page doi:10.1016/j.engappai.2025.110339 2025

  11. [11]

    Annales de l'Institut Henri Poincaré, Probabilités et Statistiques , author =

    Trees, forests, and impurity-based variable importance in regression , volume =. Annales de l'Institut Henri Poincaré, Probabilités et Statistiques , author =. 2023 , keywords =. doi:10.1214/21-AIHP1240 , abstract =

    work page doi:10.1214/21-aihp1240 2023

  12. [12]

    Journal of Agricultural, Biological and Environmental Statistics , author =

    Zero-. Journal of Agricultural, Biological and Environmental Statistics , author =. 2023 , keywords =. doi:10.1007/s13253-022-00516-z , abstract =

    work page doi:10.1007/s13253-022-00516-z 2023

  13. [13]

    Journal of Applied Ecology , author =

    Modelling the incidence of virus yellows in sugar beet in the. Journal of Applied Ecology , author =. 1998 , pages =. doi:10.1046/j.1365-2664.1998.355340.x , abstract =

    work page doi:10.1046/j.1365-2664.1998.355340.x 1998

  14. [14]

    Journal of Statistical Software , author=

    ranger:. Journal of Statistical Software , author =. 2017 , keywords =. doi:10.18637/jss.v077.i01 , abstract =

    work page doi:10.18637/jss.v077.i01 2017

  15. [15]

    International Journal of Environmental Research and Public Health , author =

    Spatial and. International Journal of Environmental Research and Public Health , author =. 2015 , keywords =. doi:10.3390/ijerph120910536 , abstract =

    work page doi:10.3390/ijerph120910536 2015

  16. [16]

    Research Journal of Agriculture and Biological Sciences , author =

    Evaluating water stress influence on growth and photosynthetic pigments of two sugar beet varieties , volume =. Research Journal of Agriculture and Biological Sciences , author =. 2008 , pages =

    2008

  17. [17]

    Biometrical Journal , author =

    Zero-inflated spatio-temporal models for disease mapping , volume =. Biometrical Journal , author =. 2017 , keywords =. doi:10.1002/bimj.201600120 , abstract =

    work page doi:10.1002/bimj.201600120 2017

  18. [18]

    2015 , pmid =

    Statistica Sinica , author =. 2015 , pmid =. doi:10.5705/ss.2013.212w , abstract =

    work page doi:10.5705/ss.2013.212w 2015

  19. [19]

    WIREs Computational Statistics , author =

    Zero-inflated modeling part. WIREs Computational Statistics , author =. 2022 , keywords =. doi:10.1002/wics.1540 , abstract =

    work page doi:10.1002/wics.1540 2022

  20. [20]

    Plant Pathology , author =

    New insights into virus yellows distribution in. Plant Pathology , author =. 2021 , keywords =. doi:10.1111/ppa.13306 , abstract =

    work page doi:10.1111/ppa.13306 2021

  21. [21]

    Pathogens , author =

    Virus. Pathogens , author =. 2022 , keywords =. doi:10.3390/pathogens11080885 , abstract =

    work page doi:10.3390/pathogens11080885 2022

  22. [22]

    Plant Pathology , author =

    The effects of beet yellows virus on the growth and physiology of sugar beet (. Plant Pathology , author =. 1999 , keywords =. doi:10.1046/j.1365-3059.1999.00307.x , abstract =

    work page doi:10.1046/j.1365-3059.1999.00307.x 1999

  23. [23]

    Precision Agriculture , author =

    Spectral signatures of sugar beet leaves for the detection and differentiation of diseases , volume =. Precision Agriculture , author =. 2010 , keywords =. doi:10.1007/s11119-010-9180-7 , abstract =

    work page doi:10.1007/s11119-010-9180-7 2010

  24. [24]

    Field Crops Research , author =

    Effects of beet yellows virus and beet mild yellowing virus on leaf area dynamics of sugar beet (. Field Crops Research , author =. 1999 , keywords =. doi:10.1016/S0378-4290(98)00155-5 , abstract =

    work page doi:10.1016/s0378-4290(98)00155-5 1999

  25. [25]

    Phytopathology® , author =

    Hyperspectral. Phytopathology® , author =. 2023 , keywords =. doi:10.1094/PHYTO-03-22-0086-R , abstract =

    work page doi:10.1094/phyto-03-22-0086-r 2023

  26. [26]

    Remote Sensing of Environment , author =

    Estimating leaf chlorophyll content in sugar beet canopies using millimeter- to centimeter-scale reflectance imagery , volume =. Remote Sensing of Environment , author =. 2017 , keywords =. doi:10.1016/j.rse.2017.06.008 , abstract =

    work page doi:10.1016/j.rse.2017.06.008 2017

  27. [27]

    Sugar Tech , author =

    Chlorophyll. Sugar Tech , author =. 2023 , keywords =. doi:10.1007/s12355-022-01184-6 , abstract =

    work page doi:10.1007/s12355-022-01184-6 2023

  28. [28]

    1996 , pages =

    Remote Sensing of Environment , author =. 1996 , pages =. doi:10.1016/S0034-4257(96)00067-3 , abstract =

    work page doi:10.1016/s0034-4257(96)00067-3 1996

  29. [29]

    Bouasria, Abdelkrim and Rahimi, Abdelmejid and El Mjiri, Ikram and Namr, Khalid Ibno and Ettachfini, El Mostafa and Bounif, Mohammed , month = nov, year =. Use of. 2021. doi:10.1109/IEEECONF53624.2021.9668059 , abstract =

    work page doi:10.1109/ieeeconf53624.2021.9668059 2021

  30. [30]

    Agronomy , author =

    Estimating. Agronomy , author =. 2023 , keywords =. doi:10.3390/agronomy13112743 , abstract =

    work page doi:10.3390/agronomy13112743 2023

  31. [31]

    Journal of Agricultural, Biological and Environmental Statistics , author =

    A class of models for large zero-inflated spatial data , volume =. Journal of Agricultural, Biological and Environmental Statistics , author =. 2025 , keywords =. doi:10.1007/s13253-024-00619-9 , abstract =

    work page doi:10.1007/s13253-024-00619-9 2025

  32. [32]

    Efficient estimation for flexible spatial zero-inflated models with environmental applications , url =

    Shen, Chung-Wei and Hsu, Bu-Ren and Hsu, Chia-Ming and Chen, Chun-Shu , month = sep, year =. Efficient estimation for flexible spatial zero-inflated models with environmental applications , url =. doi:10.48550/arXiv.2509.13054 , abstract =

    work page doi:10.48550/arxiv.2509.13054

  33. [33]

    Wilson, Tyler and McDonald, Andrew and Galib, Asadullah Hill and Tan, Pang-Ning and Luo, Lifeng , year =. Beyond. Proceedings of the 28th. doi:10.1145/3534678.3539464 , abstract =

    work page doi:10.1145/3534678.3539464

  34. [34]

    Modelling and interpreting disease progress in time , isbn =

    Xu, Xiangming , editor =. Modelling and interpreting disease progress in time , isbn =. The. 2006 , doi =

    2006

  35. [35]

    Phytopathology Research , author =

    Analysis and simulation of plant disease progress curves in. Phytopathology Research , author =. 2021 , keywords =. doi:10.1186/s42483-021-00098-7 , abstract =

    work page doi:10.1186/s42483-021-00098-7 2021

  36. [36]

    Syarif, Iwan and Indiarto, Dito Hafizh and Prasetyaningrum, Ira and Badriyah, Tessy and Satriyanto, Edi , month = oct, year =. Corn. 2018. doi:10.1109/iCAST1.2018.8751583 , abstract =

    work page doi:10.1109/icast1.2018.8751583 2018

  37. [37]

    Computational Management Science , author =

    Non-. Computational Management Science , author =. 2006 , keywords =. doi:10.1007/s10287-005-0006-4 , abstract =

    work page doi:10.1007/s10287-005-0006-4 2006

  38. [38]

    Applied Mathematics & Optimization , author =

    Analysis of a. Applied Mathematics & Optimization , author =. 2022 , keywords =. doi:10.1007/s00245-022-09858-z , abstract =

    work page doi:10.1007/s00245-022-09858-z 2022

  39. [39]

    Journal of Computational and Applied Mathematics , author =

    Modeling plant virus propagation with seasonality , volume =. Journal of Computational and Applied Mathematics , author =. 2019 , keywords =. doi:10.1016/j.cam.2018.06.022 , abstract =

    work page doi:10.1016/j.cam.2018.06.022 2019

  40. [40]

    , month = may, year =

    Lawson, Andrew B. , month = may, year =. Bayesian

  41. [41]

    ISPRS International Journal of Geo-Information , author =

    A. ISPRS International Journal of Geo-Information , author =. 2024 , keywords =. doi:10.3390/ijgi13030097 , abstract =

    work page doi:10.3390/ijgi13030097 2024

  42. [42]

    Spatial Statistics , author =

    A spatiotemporal geostatistical hurdle model approach for short-term deforestation prediction , volume =. Spatial Statistics , author =. 2017 , keywords =. doi:10.1016/j.spasta.2017.06.003 , abstract =

    work page doi:10.1016/j.spasta.2017.06.003 2017

  43. [43]

    GeoInformatica , author =

    Spatio-temporal prediction of crop disease severity for agricultural emergency management based on recurrent neural networks , volume =. GeoInformatica , author =. 2018 , keywords =. doi:10.1007/s10707-017-0314-1 , abstract =

    work page doi:10.1007/s10707-017-0314-1 2018

  44. [44]

    Environmental Technology & Innovation , author =

    Modeling spatiotemporal distribution of yellow rust wheat pathogen using machine learning algorithms:. Environmental Technology & Innovation , author =. 2024 , keywords =. doi:10.1016/j.eti.2024.103865 , abstract =

    work page doi:10.1016/j.eti.2024.103865 2024

  45. [45]

    Theoretical and Applied Climatology , author =

    Comparison of linear, generalized additive models and machine learning algorithms for spatial climate interpolation , volume =. Theoretical and Applied Climatology , author =. 2024 , pages =. doi:10.1007/s00704-023-04725-5 , abstract =

    work page doi:10.1007/s00704-023-04725-5 2024

  46. [46]

    Annual Review of Public Health , author =

    A. Annual Review of Public Health , author =. 2012 , pages =. doi:10.1146/annurev-publhealth-031811-124655 , abstract =

    work page doi:10.1146/annurev-publhealth-031811-124655 2012

  47. [47]

    Agriculture , author =

    Prediction of. Agriculture , author =. 2021 , keywords =. doi:10.3390/agriculture11111079 , abstract =

    work page doi:10.3390/agriculture11111079 2021

  48. [48]

    Spatial Statistics , author =

    Modeling infectious disease dynamics:. Spatial Statistics , author =. 2022 , keywords =. doi:10.1016/j.spasta.2022.100691 , abstract =

    work page doi:10.1016/j.spasta.2022.100691 2022

  49. [49]

    Spatial Information Research , author =

    Exploring vegetation indices adequate in detecting twister disease of onion using. Spatial Information Research , author =. 2020 , keywords =. doi:10.1007/s41324-019-00297-7 , abstract =

    work page doi:10.1007/s41324-019-00297-7 2020

  50. [50]

    Canadian Journal of Remote Sensing , author =

    Experimental assessment of the. Canadian Journal of Remote Sensing , author =. 2009 , pages =. doi:10.5589/m09-010 , abstract =

    work page doi:10.5589/m09-010 2009

  51. [51]

    Phytopathology® , author =

    Opportunities and. Phytopathology® , author =. 2025 , keywords =. doi:10.1094/PHYTO-11-24-0359-FI , abstract =

    work page doi:10.1094/phyto-11-24-0359-fi 2025

  52. [52]

    Field Crops Research , author =

    Remote sensing to detect plant stress induced by. Field Crops Research , author =. 2011 , keywords =. doi:10.1016/j.fcr.2011.02.007 , abstract =

    work page doi:10.1016/j.fcr.2011.02.007 2011

  53. [53]

    National Science Review , author =

    Challenges and opportunities in remote sensing-based crop monitoring: a review , volume =. National Science Review , author =. 2023 , pages =. doi:10.1093/nsr/nwac290 , abstract =

    work page doi:10.1093/nsr/nwac290 2023

  54. [54]

    Entomologia Generalis , author =

    Producing sugar beets without neonicotinoids:. Entomologia Generalis , author =. doi:10.1127/entomologia/2022/1511 , abstract =

    work page doi:10.1127/entomologia/2022/1511 2022

  55. [55]

    Geocarto International , author =

    Enhancing maize streak virus detection: a comparative analysis of. Geocarto International , author =. 2025 , keywords =. doi:10.1080/10106049.2025.2480701 , abstract =

    work page doi:10.1080/10106049.2025.2480701 2025

  56. [56]

    European Journal of Agronomy , author =

    Optimisation of the correlation between normalised difference vegetation index and sugar beet yield using multispectral remote sensing data , volume =. European Journal of Agronomy , author =. 2025 , keywords =. doi:10.1016/j.eja.2025.127820 , abstract =

    work page doi:10.1016/j.eja.2025.127820 2025

  57. [57]

    Agronomy , author =

    Recognition of. Agronomy , author =. 2022 , keywords =. doi:10.3390/agronomy12010014 , abstract =

    work page doi:10.3390/agronomy12010014 2022

  58. [58]

    Detection of grapevine yellows using multispectral imaging , copyright =. Remote. 2024 , doi =

    2024

  59. [59]

    Journal of Agrometeorology , author =

    Spectral reflectance characteristics of healthy and yellow mosaic virus infected soybean (. Journal of Agrometeorology , author =. 2013 , pages =. doi:10.54386/jam.v15i1.1435 , abstract =

    work page doi:10.54386/jam.v15i1.1435 2013

  60. [60]

    Spatial and Spatio-temporal Epidemiology , author =

    Review of methods for space–time disease surveillance , volume =. Spatial and Spatio-temporal Epidemiology , author =. 2010 , keywords =. doi:10.1016/j.sste.2009.12.001 , abstract =

    work page doi:10.1016/j.sste.2009.12.001 2010

  61. [61]

    Stochastic Environmental Research and Risk Assessment , author =

    Spatio-temporal data mining in ecological and veterinary epidemiology , volume =. Stochastic Environmental Research and Risk Assessment , author =. 2017 , keywords =. doi:10.1007/s00477-016-1374-8 , abstract =

    work page doi:10.1007/s00477-016-1374-8 2017

  62. [62]

    Tropical Plant Pathology , author =

    Plant disease severity estimated visually: a century of research, best practices, and opportunities for improving methods and practices to maximize accuracy , volume =. Tropical Plant Pathology , author =. 2022 , keywords =. doi:10.1007/s40858-021-00439-z , abstract =

    work page doi:10.1007/s40858-021-00439-z 2022

  63. [63]

    Plant Disease , author =

    Disease. Plant Disease , author =. 2023 , keywords =. doi:10.1094/PDIS-12-21-2734-RE , abstract =

    work page doi:10.1094/pdis-12-21-2734-re 2023

  64. [64]

    Epidemics , author =

    Thirteen challenges in modelling plant diseases , volume =. Epidemics , author =. 2015 , keywords =. doi:10.1016/j.epidem.2014.06.002 , abstract =

    work page doi:10.1016/j.epidem.2014.06.002 2015

  65. [65]

    Frontiers in Environmental Science , author =

    A hybrid modeling approach to simulating foot-and-mouth disease outbreaks in. Frontiers in Environmental Science , author =. 2015 , keywords =. doi:10.3389/fenvs.2015.00017 , abstract =

    work page doi:10.3389/fenvs.2015.00017 2015

  66. [66]

    Tropical Medicine and Infectious Disease , author =

    Spatiotemporal. Tropical Medicine and Infectious Disease , author =. 2022 , keywords =. doi:10.3390/tropicalmed7090232 , abstract =

    work page doi:10.3390/tropicalmed7090232 2022

  67. [67]

    Annual Review of Phytopathology , author =

    Remote. Annual Review of Phytopathology , author =. 2020 , pages =. doi:10.1146/annurev-phyto-010820-012832 , abstract =

    work page doi:10.1146/annurev-phyto-010820-012832 2020

  68. [68]

    Frontiers in Veterinary Science , author =

    Complex. Frontiers in Veterinary Science , author =. 2019 , keywords =. doi:10.3389/fvets.2019.00153 , abstract =

    work page doi:10.3389/fvets.2019.00153 2019

  69. [69]

    Syndromic

    Getsova, Zhikva and Rangelova, Vanya , month = dec, year =. Syndromic. doi:10.20944/preprints202512.2139.v1 , abstract =

    work page doi:10.20944/preprints202512.2139.v1

  70. [70]

    IEEE Transactions on Geoscience and Remote Sensing , author =

    Spectral–. IEEE Transactions on Geoscience and Remote Sensing , author =. 2022 , keywords =. doi:10.1109/TGRS.2022.3177935 , abstract =

    work page doi:10.1109/tgrs.2022.3177935 2022

  71. [71]

    International Journal of Remote Sensing , author =

    Densely connected deep random forest for hyperspectral imagery classification , volume =. International Journal of Remote Sensing , author =. 2019 , pages =. doi:10.1080/01431161.2018.1547932 , abstract =

    work page doi:10.1080/01431161.2018.1547932 2019

  72. [72]

    Pavlyshenko, Bohdan , month = aug, year =. Using. 2018. doi:10.1109/DSMP.2018.8478522 , abstract =

    work page doi:10.1109/dsmp.2018.8478522 2018

  73. [73]

    , month = jul, year =

    Lawson, Andrew B. , month = jul, year =. Statistical

  74. [74]

    Phytopathology® , author =

    Factor. Phytopathology® , author =. 2025 , keywords =. doi:10.1094/PHYTO-01-25-0014-FI , abstract =

    work page doi:10.1094/phyto-01-25-0014-fi 2025

  75. [75]

    Compartmental

    Brauer, Fred , editor =. Compartmental. Mathematical. 2008 , doi =

    2008

  76. [76]

    Mathematical Biosciences , author =

    Some discrete-time. Mathematical Biosciences , author =. 1994 , pages =. doi:10.1016/0025-5564(94)90025-6 , abstract =

    work page doi:10.1016/0025-5564(94)90025-6 1994

  77. [77]

    Agriculture , author =

    Neonicotinoid. Agriculture , author =. 2020 , keywords =. doi:10.3390/agriculture10100484 , abstract =

    work page doi:10.3390/agriculture10100484 2020

  78. [78]

    Pest Management Science , author =

    Neonicotinoid concentrations in arable soils after seed treatment applications in preceding years , volume =. Pest Management Science , author =. 2014 , pmid =. doi:10.1002/ps.3836 , abstract =

    work page doi:10.1002/ps.3836 2014

  79. [79]

    Ecotoxicology , author =

    Neonicotinoids in bees: a review on concentrations, side-effects and risk assessment , volume =. Ecotoxicology , author =. 2012 , keywords =. doi:10.1007/s10646-012-0863-x , abstract =

    work page doi:10.1007/s10646-012-0863-x 2012

  80. [80]

    Chemosphere , author =

    Human exposure to neonicotinoid insecticides and the evaluation of their potential toxicity:. Chemosphere , author =. 2018 , keywords =. doi:10.1016/j.chemosphere.2017.10.149 , abstract =

    work page doi:10.1016/j.chemosphere.2017.10.149 2018

Showing first 80 references.