Resume

Summary

Data scientist with 8+ years of experience applying predictive modeling, Bayesian statistics, and geospatial analysis to global agricultural R&D and commercial decision-making. Proven record of leading projects from inception to implementation, delivering reproducible analytics pipelines that replace manual workflows, accelerate product advancement, and inform high-stakes go/no-go decisions across North & South America, Europe, and Asia.

Keywords

predictive modeling | algorithms | multivariate optimization | geospatial modeling | assay optimization | deep learning | experimental design | Bayesian decision making | data storytelling | technical writing | interactive dashboards | project execution | project ownership | execution decision | data-guided assay pipelines | cross-indication | decision guided business intelligence | data science best practices | stakeholder communication | logistics modeling | Python | Linux system administration | AWS | Docker | Jupyter | Shiny | Microsoft Office Suite

Experience

Syngenta

April 2024 - curent

Data Scientist

  • Lead global analytics across North and South America, Europe, and Asia for sunflower, soy, and corn pipelines, delivering reproducible Python, R, and SQL data products in AWS/Snowflake that replace Excel workflows and accelerate breeder advancement decisions.

  • Designed and deployed a sequential Bayesian hierarchical modeling framework (Stan/brms) to better reflect pipeline realities and improve product performance estimation for targeted R&D initiatives.

  • Partner with R&D, commercial, plant breeders, and data engineering teams to translate raw agronomic, genomic, and sales data into decision-ready products, influencing strategic go/no-go calls for new corn varieties.

  • Developed predictive models for genomic-based sales forecasting and disease susceptibility; delivered 5–6 proofs-of-concept, with 1–3 adopted in production, earning strong senior management support.

  • Built foundational infrastructure for a four-person, startup-style data science team, introducing AWS-hosted storage, automated pipelines, Git-based workflows, and coding best practices to replace manual spreadsheets.

  • Applied advanced machine learning (random forest, gradient boosting, GAMs, mixed models) to complex agronomic, pathology, genomic, and sales datasets, informing decisions at both breeder and executive levels.

  • Introduced novel statistical and optimization algorithms (linear mixed models, Bayesian modeling) to prototype scalable solutions for global product pipeline efficiency, with the potential to become organization-wide standards.

AgBiome

June 2022 - March 2024

Data Scientist

  • Effectively communicating data insights across the company: from early-discovery pipeline to commercial sales of AgBiome Products through constructing interactive dashboards, whitepapers, and compelling visualizations.

  • Spearhead the development of AgBiome’s digital twin for 30+ projects, decreasing lead generation time by 200% through the integration of predictive modeling, data science, and physical screens.

  • Engineer multivariate-optimization algorithms, leading to a 250% improvement in screening efficiency for insecticidal, herbicidal, biostimulant, and biomining applications.

  • Develop geospatial machine learning algorithms, increasing the diversity of AgBiome’s microbial library by targeted sampling strategies, providing novel resources for research.

  • Pioneer novel predictive modeling, which led to a 250% efficiency in assay optimization for various indications.

  • Lead nationwide environmental sampling trips increasing microbial diversity by targeting priority genera, contributing to the enrichment of AgBiome’s microbial resources.

  • Develop data science infrastructure, optimizing system performance, and enhancing data processing efficiency, resulting in quicker insight delivery while maintaining reproducibility.

  • Lead, manage, and execute on contract research organizations interactions from environmental permitting to chemical and genomic analyses.

North Carolina State University

June 2021 - June 2022

Post-Doctoral Researcher

  • Applied spatial models to predict pest population dynamics throughout North America, utilizing 1900+ pest monitoring traps spanning 40+ years of data, resulting in accurate predictive and forecast models.

  • Engineered a robust data pipeline to seamlessly integrate extensive pest monitoring data, facilitating data-driven decision-making of pest population forecasting.

  • Designed and conducted experiments to analyze the impact of cover crop on soil moisture in sorghum fields using non-linear models based on sensor data.

  • Contributed to the development of pesticide efficiency in sorghum and sweet potatoes, enhancing agricultural practices.

  • Successfully presented ongoing and completed projects, both orally and in written form, with multiple articles under preparation and stakeholder presentations.

  • Advised 4+ graduate students on coding techniques and statistical analyses, ensuring high-quality research.

  • Shared programming and statistical modeling expertise with peers and students, implementing innovative statistical approaches.

Arizona State University

September 2016 - May 2021

Graduate Student Researcher

  • Led international teams from three continents constructing predictive non-linear models promoting crop protection strategies in Australia, Africa, and Southwest Asia.

  • Implemented a data pipeline that integrated long term insect pest population survey data from federal and four state level agricultural entities.

  • Collaborated with seven coauthors on machine learning projects investigating how locust plagues are impacted by climate change resulting in a published scientific research article.

  • Constructed scripts relating insect pest population dynamics to remotely sensed data via Google Earth Engine.

  • Facilitated workshops with 100+ participants identifying the governmental structure of locust management internationally.

  • Provided statistical and programming expertise to four published scientific articles integrating diverse research fields to inform crop protection globally.

  • Advised 15+ undergraduate and graduate students and professionals on advanced statistical and coding techniques.

Technical Skills

Programming Languages: Python, R, Java, SQL

Selected Libraries: NumPy, pandas, geopandas, scikit-learn, PyTorch, tensorflow, statsmodels, tidymodels, glmer, glmmTMB, lme4, mgcv, caret, randomForest, sf, sp, raster, shiny, data.table, ggplot2, dplyr, lubridate

Version Control: Git, GitHub, GitLab

Writing: LaTex, markdown, R markdown, Quarto

GIS: Google Earth Engine, QGIS, ArcGIS

Cloud Computing: Amazon Web Services, Linux system administration

Scientific Publications

Lawton, D., Learned, J., Waters, C., Toole, I., Thompson, N., Hales, C., Adriaansen, C., Deveson, T., Simpson, S. J., & Cease, A. (2025). Exploring nutrient availability and herbivorous insect population dynamics across multiple scales. Oikos, first published 12 March 2025. https://doi.org/10.1111/oik.11189

Lawton, D., Huseth, A. S., Kennedy, G. G., and 41 more authors (2022). Pest population dynamics are related to a continental overwintering gradient. Proceedings of the National Academy of Sciences, 119(37), e2203230119. https://doi.org/10.1073/pnas.2203230119

Humphreys J, Srygley R., Lawton D, Hudson A., Branson D (2022). Grasshoppers exhibit asynchrony and spatial non-stationarity in response to the El Niño/Southern and Pacific Decadal Oscillations, Ecological Modelling, 471, 110043. https://doi.org/10.1016/j.ecolmodel.2022.110043

Lawton D., Deveson T., Piou C., Spessa A., Waters C. and Cease A.. (2022) Seeing the locust in the swarm: acknowledging spatiotemporal hierarchy improves insect outbreak models. Ecography, 2022, 02. https://doi.org/10.1111/ecog.05763

Lawton D., Le Gall, M., Waters, C., Cease, A. J. (2021) Mismatched diets: defining the nutritional landscape of grasshopper communities in a variable environment. Ecosphere, 12(3), e03409. https://doi.org/10.1002/ecs2.3409

Lawton, D., Waters, C., Le Gall, M., & Cease, A. (2020). Woody vegetation remnants within pastures influence locust distribution: Testing bottom-up and top-down control. Agriculture, Ecosystems & Environment, 296, 106931. https://doi.org/10.1016/j.agee.2020.106931

Wang B., Deveson E., Waters C., Spessa A., Lawton D., Feng P., and Liu D. (2019) Future climate change likely to reduce the Australian plague locust (Chortoicetes terminifera) seasonal outbreaks. Science of the Total Environment, 668, 947-957. https://doi.org/10.1016/j.scitotenv.2019.02.439

Lawton, D., Parlindungan, D., Pratama, P., Aswin, P., Jundara, P., Darmawan, R., Ruyani, A., Matthews E. C., Somers, A. (2018) Living amoung water montiors: an exploratory study of an urban water monitor (Varanus salvator) population in Bengkulu, Indonesia. Biawak, 12(10)

Education

Arizona State University
PhD in Environmental Life Sciences
- Dissertation: What Causes a Locust Swarm: A Hierarchical Patch Dynamics Approach
- Acquired $60,000+ in research grant funding for research in Australia

Tempe, AZ
May 2021

University of North Carolina at Greensboro
B.S. in Biology - Thesis: Urbanization effects on leaf mining densities and leaf damage of white oak (Quercus alba) in Guilford County, North Carolina
- Acquired $8,000 in funding for six month research trip to Sumatra, Indonesia

Greensboro, NC
December 2015