Recipient Organization
IOWA STATE UNIVERSITY
2229 Lincoln Way
AMES,IA 50011
Performing Department
PLANT PATHOLOGY, ENTOMOLOGY AND MICROBIOLOGY - CALS/AES
Non Technical Summary
Crop plants encounter many different biotic and abiotic stresses throughout their growth, and often, multiple stresses occur at once. As climate change intensifies, these combined stresses are expected to occur more frequently and prolonged. Stresses induce various chemical and physiological changes in plants that, if quantified, can provide key information on plant health status and potentially aid future management decisions. There are many kinds of data that can provide insights into how plants perceive stresses and respond to their environments, however, the methods required to generate these data are often time consuming, costly, and require specialized equipment. This project will develop integrated sensing devices that can be placed on the leaves of plants to measure the presence of stress agents and the responses of the plants as they produce molecular signals that enable them to respond to the stresses. The plant sensors will also monitor physiological metrics such as leaf water content, temperature, and humidity. The data collected from the sensors will be used to train machine learning models that will identify distinct signatures for each individual stress and responses to combined stresses. The performance of the sensors and the developed data analytics tools will be tested under climate change scenarios in order to determine how stress responses may be altered in crops in the future. At the completion of this project, it will be possible to pinpoint and differentiate individual and combined stresses using the sensors and data analytics. The versatility of this method allows it to adapt to diverse crops and stresses for fundamental research or the development of new diagnostic or management tools.
Animal Health Component
(N/A)
Research Effort Categories
Basic
100%
Applied
(N/A)
Developmental
(N/A)
Goals / Objectives
The goal of this project is to develop an integrated sensor device and accompanying data analytics using machine learning approaches that can be applied to determine signatures of individual and multiple stresses as they occur in crop plants under current and future climate scenarios.Objective 1. Optimizing individual sensors and advancing integrated multimodal sensors.Objective 2. Detecting specific stresses over time using multimodal sensors.Objective 3. Detecting multiplexed stresses using multimodal sensing.Objective 4. Multimodal sensing of multiplexed stresses in climate change conditions.
Project Methods
Objective 1. Optimizing individual sensors and advancing integrated multimodal sensors. Sensors will be designed and fabricated to accurately detect and quantify bean pod mottle virus (BPMV), dicamba herbicide, salicylic acid (SA), methyl jasmonate (MeJA), and hydrogen peroxide (H2O2) in soybean, while considering the effect of leaf temperature and pH on sensor readings. Each individual sensor will be optimized. Following this, an integrated wearable sensor will be designed and developed that can simultaneously detect BPMV, dicamba, SA, MeJA, and H2O2, in addition to leaf temperature, relative humidity (RH), and leaf water content. The methods required for sensor fabrication will incorporate the following technologies: Nanoscribe printing, flexible printed circuit boards, robotic arm-assisted coating.Objective 2. Detecting specific stresses over time using multimodal sensors. Soybean plants will be subjected to individual stresses: virus infection, drought, and herbicide damage. Sensors will be applied to control and treated plants and data will be collected. In addition, samples will be collected from the control and treated plants for independent measurements of BPMV, dicamba, SA, MeJA, and H2O2 using currently available standard assays to verify that sensor data are accurate. The sensor data will be used as input into a machine learning model that will be trained to predict the stress and the amount of stress that is being experienced by the plants.Objective 3. Detecting multiplexed stresses using multimodal sensing. Soybean plants will be subjected to combinations of two or three stresses: virus infection, drought, and herbicide damage. Sensors will be applied to control and treated plants and data will be collected. In addition, samples will be collected from the control and treated plants for independent measurements of BPMV, dicamba, SA, MeJA, and H2O2 using currently available standard assays to verify that sensor data are accurate. The sensor data will be used as input into a machine learning model that will be trained to predict the combination of stresses and the amount of each stress that is being experienced by the plants.Objective 4. Multimodal sensing of multiplexed stresses in climate change conditions. Soybean plants will be subjected to three different stress treatments: virus infection, drought, or virus + drought. These treatments will be applied in soybean plants growing in two different atmospheric CO2 levels, 420 parts per million (current CO2) and 600 parts per million (elevated CO2). Sensors will be applied to control and treated plants under both climate scenarios, and samples will be collected from the control and treated plants for independent measurements of BPMV, dicamba, SA, MeJA, and H2O2 using currently available standard assays to verify that sensor data are accurate. The machine learning models trained in Objectives 3 and 4 will be tested for their performance under the climate change scenarios.