Skip to main content
ARS Home » Southeast Area » Mississippi State, Mississippi » Crop Science Research Laboratory » Genetics and Sustainable Agriculture Research » Research » Research Project #445679

Research Project: Crop Modeling Digital Twin Development through Remote Sensing and Machine Learning

Location: Genetics and Sustainable Agriculture Research

Project Number: 6064-21660-001-052-S
Project Type: Non-Assistance Cooperative Agreement

Start Date: Jan 1, 2024
End Date: Jul 31, 2025

Objective:
1. Establish a digital twin framework that enables the NASA remote sensing data products and land surface model products to be directly coupled with or assimilated into the crop growth model. 2. Assimilate high-resolution remote sensing inputs (precipitation, temperature, soil moisture, snow water equivalent, ground water, leaf area index) through the NASA Land Information System (LIS) to estimate land surface variables (water and energy fluxes) at daily time scales. 3. Implement crop growth models [Agricultural Policy/Environmental eXtender (APEX), Root Zone Water Quality Model (RZWQM2) and Decision Support System for Agrotechnology Transfer (DSSAT)] to estimate crop growth states, biomass, and crop yield under long-term weather conditions and projected future climate scenarios. 4. Develop tools to conduct ‘what if’ investigations to provide agricultural guidance. 5. Develop capability for disseminating non-confidential crop progress data, biomass and crop yield maps using an operational web application.

Approach:
Land Information System (LIS) is an interoperable environment which has been incorporated in several coupled Earth system models, through prior AIST funded efforts. The development of the agricultural modeling ESDT prototype around LIS will allow future integration with other related ESDT efforts. Crop models have large uncertainties with respect to the spatial distribution of crop parameters, initial conditions, and soil properties, which can reduce the estimation accuracy of crop yield when crop growth models are applied uniformly over large agricultural domains without incorporating spatial heterogeneity. The crop models (APEX/DSSAT) will be coupled with NASA LIS (Land Information System) to assimilate remote sensing data to improve estimates of crop state variables and improve the prediction accuracy of the crop yield through machine learning. Specifically, we will update the crop model states such as LAI, soil moisture, ET, and crop phenology with information from the NASA LIS system and NASS survey report.