Upgrade to Pro — share decks privately, control downloads, hide ads and more …

BIG Data and META-approaches for analysing research data and improving DECISIONS in plant disease MANAGEMENT

BIG Data and META-approaches for analysing research data and improving DECISIONS in plant disease MANAGEMENT

Talk given at an online conference on Big Data in Agriculture organized in Ecuador on 10 February 2021

Emerson M. Del Ponte

February 16, 2021
Tweet

More Decks by Emerson M. Del Ponte

Other Decks in Science

Transcript

  1. BIG Data and META-approaches for
    analysing research data and improving
    DECISIONS in plant disease MANAGEMENT
    Emerson M. Del Ponte
    Jhonatan P. Barro, Kaique S. Alves and Felipe Dalla Lana

    View full-size slide

  2. Epidemiology
    Research
    Control methods Chemicals Biological
    Genetic Cultural
    Biotechnology
    Remote sensing
    Modeling
    Machine learning
    Phytopathometry

    View full-size slide

  3. Big data
    Decision
    Soil, crops, pests,
    diseases
    RISK
    Strategic or tactical
    PDM research
    Epidemiology
    Field trials
    (Regionwide)
    Information
    Sensors
    user-input
    Storage
    Processing
    Impact
    Knowledge

    View full-size slide

  4. Digital farming
    Remote sensing
    → Field scale
    n > 5k?
    PDM research requires
    variation in disease and
    production situations → several fields
    (locations x years)
    n > 50?
    Context for BIG!
    Source: grupocultivar.com.br

    View full-size slide

  5. Coordinated efforts (industry and public)
    One or more target (disease)
    Common treatments (fungicide, biocontrol, etc.)
    Chemicals from several industries (control bias?)
    New treatments added over years, some are kept
    Disease and yield data are obtained
    The uniform trials (network)

    View full-size slide

  6. 2004
    Soybean
    Rust
    Soybean
    White mold
    2009 2011
    Soybean
    Target spot
    Wheat
    Blast & FHB
    Fungicides
    Biocontrol
    2018 2019
    Wheat
    Leaf blotches
    Wheat powdery
    mildew
    Cooperative trials

    View full-size slide

  7. Rapid response
    Yearly summaries
    Within trial data/analysis
    "Combined" analysis
    Objectives & outcomes

    View full-size slide

  8. Few (< 5) experiments
    Focus on statistical significance (P-value)
    Vote-counting approach: how many P < 0.05
    When combined, same weight is assigned to trials
    "Not good" trials are eliminated from analysis
    By tradition in academic research

    View full-size slide

  9. Three examples of our research
    Data: soybean rust in fungicide trial network
    Meta-analysis
    Yield Loss
    Meta-analysis
    Fungicide performance
    Fungicide profitability
    Monte Carlo Simulation
    Cooperative
    trial datasets
    1
    3
    2

    View full-size slide

  10. 210 trials
    57 locations
    40 fungicides
    9 seasons
    2004/05 a 2012/13

    View full-size slide

  11. Variability in intercepts and slopes
    Intercepts slopes

    View full-size slide

  12. Effect of disease pressure and onset time

    View full-size slide

  13. Conclusion 1
    Yield loss can be predicted from
    severity data and is influenced by
    onset time and severity level

    View full-size slide

  14. 250 field trials
    2004 - 2017 (14 years)
    > 30 Institutions/researchers
    Example 2: fungicide performance

    View full-size slide

  15. Exploratory results

    View full-size slide

  16. Large within-year (spatial) variation

    View full-size slide

  17. Dual premixes should be
    encouraged and single a.i. not
    recommended due to low efficacy
    Conclusion 2

    View full-size slide

  18. Example 3: premix performance

    View full-size slide

  19. Fungicide a.i. Study code Commercial
    name
    CHECK
    AZOX + BENZ
    BIXF + TFLX + PROT
    PICO + BENZ
    PICO + CYPR
    PICO + TEBU
    PYRA + EPOX + FLUX
    TFLX + CYPR
    TFLX + PROT
    Fungicide treatments

    View full-size slide

  20. Exploratory results

    View full-size slide

  21. Exploratory results

    View full-size slide

  22. 77.6 - 85.2
    81.4 - 85.6
    SBR control (%)
    Fungicidea Seasons Trials C CI
    L
    CI
    U
    BIXF + TFLX + PROT 4 115 76.80 74.39 78.98
    PICO + BENZ 4 116 74.02 71.24 76.54
    AZOX + BENZ 5 144 72.79 69.74 75.53
    PYRA + EPOX + FLUX 4 115 72.23 69.56 74.66
    TFLX + PROT 6 166 71.96 69.31 74.39
    PICO + TEBU 5 149 66.01 63.11 68.69
    TFLX + CYPR 5 143 57.89 54.68 60.88
    PICO + CYPR 6 169 56.25 53.25 59.06
    MA results
    Dalla Lana et al (2018)

    View full-size slide

  23. Dual premixes declining after 4 years, but
    triple premix still good
    Conclusion 3

    View full-size slide

  24. Example 4: economic analysis

    View full-size slide

  25. Probability distributions for Monte carlo simulations
    Severity on untreated plots
    Soybean Price (2 years)
    Interceps
    Slopes
    Yield-severity relationship

    View full-size slide

  26. Probability distributions for Monte carlo simulations
    Damage coefficients
    Empirical
    Simulated

    View full-size slide

  27. Yield response

    View full-size slide

  28. Profitability over time

    View full-size slide

  29. Profitability over time

    View full-size slide

  30. Rusty profits shiny app
    Website

    View full-size slide

  31. Conclusion 4
    A decision tool for making profit with
    fungicides taking epidemiological,
    control and economic factors into
    account

    View full-size slide

  32. Chemical breeding
    epidemiology
    Kaique Alves Felipe Dalla Lana
    Jhonatan Barro
    emersondelponte.netlify.app

    View full-size slide