Grantee Research Project Results
Final Report: SprayCast: Mitigating Pesticide Drift through High Resolution Forecasting, Modeling, and Optimization
EPA Contract Number: 68HERC23C0007Title: SprayCast: Mitigating Pesticide Drift through High Resolution Forecasting, Modeling, and Optimization
Investigators: Ball, Kenneth
Small Business: Geometric Data Analytics, Inc.
EPA Contact: Richards, April
Phase: II
Project Period: October 21, 2022 through October 20, 2024
Project Amount: $399,127
RFA: Small Business Innovation Research (SBIR) Phase II (2023) Recipients Lists
Research Category: SBIR - Air , SBIR - Homeland Security , SBIR - Sustainability , SBIR - Air Quality
Description:
Purpose of Research. Off target pesticide spray drift is an economically and environmentally significant problem. Off target drift can damage susceptible crops, orchards, and apiaries, induce herbicide resistant weed development, damage native pollinator habitats, create human-health related pesticide exposure hazards, and create economic, social, and legal strife as a result of exposure incidents.
SprayCast uses mathematical and statistical techniques to provide more accurate and easily accessible forecasts of drift related weather conditions and actual drift potential in real time to pesticide applicators. SprayCast is meant to facilitate communication among stakeholders, improve visibility into drift potential, and ultimately provide a more reliable tool to quantify and mitigate risk of off-target drift.
Description of Conducted Research. During the second phase of our SBIR project, we have built a deployable software service and API that delivers, in real-time, forecasts and quantified uncertainty of drift related weather conditions. We have also produced an internal data analysis pipelining tool that enables rigorous and rapid iteration of forecast and analysis models. We have developed and validated Bayesian inference models for wind speeds and have verified a novel approach to high spatial resolution forecasting of inversion conditions. Our developed software and algorithms are compatible with our previously developed models of droplet drift that incorporate wind speed, application height, temperature, humidity, and droplet sizes to predict and describe drift potentials.
Summary/Accomplishments (Outputs/Outcomes):
Findings and Results. Our software service is rapidly deployable, responsive, and scalable to commercial applications. We have found that we can produce locally meaningful high resolution forecasts that characterize uncertainty in surface wind speeds and provide high resolution inversion forecasts. Our service supports both forecasting and, critically, retrospective analyses. SprayCast bridges an information gap between real time applications and future analysis and adjudication of drift incidents by providing a uniform and consistently available reference of spray relevant conditions.
Verification Reports. We engaged with a variety of stakeholders, especially pesticide application experts, regulators, climatologists, agricultural chemical industry representatives, and insurance industry experts. The forecasts that SprayCast processes were found to be more reliable on average than nearest neighbor official weather station data in a localized data validation experiment. SprayCast models are trained and cross-validated on a very large and meticulously cleaned and preprocessed observational dataset.
Conclusions:
Commercial Applications of the Research. Pesticide drift is an enormous and expensive problem for applicators, equipment manufacturers, regulators, and agrochemical manufacturers. SprayCast is an easy to use product with a user interface and API that can support commercial stakeholder needs at a variety of levels. SprayCast clearly improves upon standard practice for pesticide drift risk assessment and can provide value by reducing actual incidents of contamination and driving commercial use towards pesticides whose standard formulations and label requirements are directly integrated into the SprayCast product. SprayCast offers value propositions to agricultural/chemical application insurers, agrochemical companies, and state level pesticide programs.
SBIR Phase I:
Topological Simplification and Machine Learning for Real-time Prediction of Off-target Pesticide | Final ReportThe perspectives, information and conclusions conveyed in research project abstracts, progress reports, final reports, journal abstracts and journal publications convey the viewpoints of the principal investigator and may not represent the views and policies of ORD and EPA. Conclusions drawn by the principal investigators have not been reviewed by the Agency.