Skip to main content
ARS Home » Plains Area » Sidney, Montana » Northern Plains Agricultural Research Laboratory » Pest Management Research » Research » Research Project #446434

Research Project: Modeling Mormon Cricket Centers of Endemism with Geospatial Artificial Intelligence (GeoAI) Analysis of Spatiotemporal Distribution Data

Location: Pest Management Research

Project Number: 3032-22000-019-004-I
Project Type: Interagency Reimbursable Agreement

Start Date: Jul 1, 2024
End Date: Jun 30, 2025

Objective:
Mormon cricket outbreaks typically originate on rangeland where infestations can result in substantial forage losses and cause major damage when they migrate into crops. The upsurge of Mormon crickets in the Western U.S. in this century was one of the most severe on record. For example, 12.3 million acres were infested in Nevada in 2004, six times the Nevada acres infested in 1939 during another historic outbreak. Mormon crickets are also a traffic hazard and impede tourism. The Mormon cricket invasion of Elko, Nevada in 2023 appeared on multiple national news outlets. Recent research has demonstrated that Mormon cricket half-lives in the egg stage exceed seven years at high elevations, and thus identification of multi-generational egg beds is imperative to understanding from whence Mormon cricket outbreaks emerge. This project will utilize existing presence/absence and density data for Mormon crickets across 12 western U.S. states to evaluate the role of topography and other environmental factors to provide endemic centers from which Mormon cricket outbreaks emanate. The proposed project in collaboration with the University of Colorado at Boulder leverages recent discoveries on egg persistence in egg banks and thermal requirements for Mormon crickets embryo development that result in synchronized hatching of multiple generations. Deep learning methods will combine multispectral imagery, derived environmental data sets, and novel uncertainty-aware approaches to facilitate model training and identify the distinctive signature of Mormon cricket habitat as well as local variation in Mormon cricket density over the observed period of record. Successful completion of this one year project will produce a forecasting application constructed as a web-based toolbox, software package, or library for continued use in outbreak forecasting beyond the lifecycle of the project.

Approach:
ARS will utilize recent results on the effects of temperature on Mormon cricket development through their complete life cycle across the elevational and latitudinal range of the insect to model the pest’s population biology. ARS researcher has active research in the role of drought in embryonic development, hatching, and mortality, which will also contribute to interpreting findings from the proposed AI modeling. In addition, ARS's data on near surface air and soil for over ten years at western rangeland sites in Utah and Colorado will also be utilized to inform the AI modeling. ARS will assist in compiling and interpreting data and AI models of major environmental parameters and investigate the duration that Mormon crickets remain in egg beds by continuing to monitor hatching in areas with high variability in soil microclimates.