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

Slide 1

Slide 1 text

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

Slide 2

Slide 2 text

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

Slide 3

Slide 3 text

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

Slide 4

Slide 4 text

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

Slide 5

Slide 5 text

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)

Slide 6

Slide 6 text

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

Slide 7

Slide 7 text

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

Slide 8

Slide 8 text

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

Slide 9

Slide 9 text

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

Slide 10

Slide 10 text

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

Slide 11

Slide 11 text

Variability in intercepts and slopes Intercepts slopes

Slide 12

Slide 12 text

Effect of disease pressure and onset time

Slide 13

Slide 13 text

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

Slide 14

Slide 14 text

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

Slide 15

Slide 15 text

Exploratory results

Slide 16

Slide 16 text

v v

Slide 17

Slide 17 text

Large within-year (spatial) variation

Slide 18

Slide 18 text

MA Results

Slide 19

Slide 19 text

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

Slide 20

Slide 20 text

Example 3: premix performance

Slide 21

Slide 21 text

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

Slide 22

Slide 22 text

Exploratory results

Slide 23

Slide 23 text

Exploratory results

Slide 24

Slide 24 text

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)

Slide 25

Slide 25 text

No content

Slide 26

Slide 26 text

No content

Slide 27

Slide 27 text

No content

Slide 28

Slide 28 text

No content

Slide 29

Slide 29 text

No content

Slide 30

Slide 30 text

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

Slide 31

Slide 31 text

Example 4: economic analysis

Slide 32

Slide 32 text

Start

Slide 33

Slide 33 text

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

Slide 34

Slide 34 text

Probability distributions for Monte carlo simulations Damage coeﬃcients Empirical Simulated

Slide 35

Slide 35 text

Yield response

Slide 36

Slide 36 text

No content

Slide 37

Slide 37 text

No content

Slide 38

Slide 38 text

Proﬁtability over time

Slide 39

Slide 39 text

Proﬁtability over time

Slide 40

Slide 40 text

Rusty proﬁts shiny app Website

Slide 41

Slide 41 text

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

Slide 42

Slide 42 text

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