Skip to main content
ARS Home » Plains Area » Mandan, North Dakota » Northern Great Plains Research Laboratory » Research » Research Project #442981

Research Project: Developing Remote Sensing and Image Processing Tools for North Dakota Agricultural and Rangeland Applications

Location: Northern Great Plains Research Laboratory

Project Number: 3064-21660-004-030-S
Project Type: Non-Assistance Cooperative Agreement

Start Date: Sep 1, 2022
End Date: Apr 30, 2027

Objective:
(1) Application of remote sensing imagery for forage and field crop biomass prediction; (2) cereal and broad leaf crops disease assessment through foliar image processing and other field image processing tools; and (3) assessment of circular bioeconomy (CBE) in crop and rangeland applicable to North Dakota.

Approach:
Objective 1: Remotely sensed (satellite, phenocam, and UAV) images can be utilized to assess the biomass production of forages and field crops with machine learning (ML) models. Specific activities include (1) collect historical remotely sensed imaging data from various sources of selected fields of known biomass data collection; (2) perform a literature search to understand the range of applications of remote sensing in agricultural and rangeland scenarios; (3) develop simple methods of assessment (e.g., statistical models) and determine their effectiveness; (4) develop and train ML models based on various influencing parameters (image, soil, and weather); and (5) develop web-based user-friendly tool using HTML and javascript for stakeholder consumption. Objective 2: Foliar diseases affect cereal crops (e.g., barley) and broadleaf (e.g., iron deficiency chlorosis (IDC) in soybean) crops significantly and measuring the extent of damage quickly helps manage the impact. Image processing and analysis can be applied to develop such a rapid assessment tool. Specific activities include: (1) conduct a literature review of foliar diseases on cereal and broad leaf crops and understand the various management strategies; (2) collect field images at different scales (leaf, subplot, and whole); (3) develop methodologies of rapid disease assessment; (4) develop ML and deep learning (DL) models to assess the disease severity; (5) other field problem specific image processing tools such as weed identification, stand count, grazing evaluation, and other LTAR projects relevant image processing applications will be performed by undergraduate interns; and (5) develop web-based tool for visualization and deployment. Objective 3: The CBE of crop and rangeland production is the future technology of agricultural and rangeland sustainability, which aims to improve the ecosystem. Though the methods may not be profitable, in the short run, but will ensure long-term benefits (e.g., no-till agriculture). Incentives were provided by different agencies to systems that employ CBE therefore assessment of this systems approach is key. The specific activities include: (1) perform a literature search to understand the various aspects of CBE applicable to crop and forage production; (2) develop CBE systems analysis (simple and elaborate) and apply to study cases with existing fields; (3) conduct scenario analysis to evaluate the benefits of CBE; and (4) develop tools to determine the benefits and visualize the results at a different level of adoption of CBE strategies.