Climate Smart Practices

The development of science and technology-based management practices is key to realizing the maximum potential of climate-smart cultivars. We discuss below the application of some of these technologies and practices which will help producers by better forecasting stressors, improving soil health, reducing chemicals and fertilizer use, and minimizing the environmental footprint.

Digital Agricultural Technologies to Transform the Rice Production Practices

Data collection and scouting: Develop a rapid plant stand data collection protocol and plant stress scouting protocol using Unmanned Aerial Vehicles (UAVs) and machine learning.

Disease management: Investigate the critical infection period of bacterial leaf blight using hyperspectral remote sensing and machine learning to determine the optimal timing for fungicide application.

Pest detection: Develop a remote-sensing-based detection system for rice stink bugs (Oebalus pugnax) in fields using an electronic nose and ultrasonic sensor.

Decision support tools: Develop in-season decision support tools for pest and disease scouting, irrigation scheduling, and nutrient management. These tools will be powered by seasonal climate forecasts, remote sensing observations, and crop models.

Phenotyping and yield prediction: Implement remote sensing techniques such as vegetation indices at multiple wavelengths and imagery processing to support phenotyping studies and rice yield prediction.

Field measurements: Use drones, crop canopy sensors, spectrometers, and soil sensors to measure spatial variability and the influence of several parameters used in the rice breeding program.

Machine learning for yield prediction: Use drone imagery and detailed soil information to generate a machine-learning algorithm to predict rice yield based on drone measurements and validate the algorithm to retrieve plant characteristics for breeding purposes.

Environmentally Friendly Pest, Diseases, and Nutrient Management Practices

Disease management: (a) Investigate the suppression mechanism of an avirulent strain of Burkholderia glumae NA2 and compare host defense responses in different rice types. (b) Examine NA2’s antagonistic activity against rice pathogens in the lab and study the population dynamics of B. glumae strains in rice plants. (c) Optimize the efficacy of NA2 through manipulation of application timings and methods. (d) Investigate the sheath blight-suppressing efficacy of NA-2 and other bacteria, as well as their combined effects with fungicides.

Sheath blight forecasting: Validate and develop new forecasting models for rice cultivation, using both traditional statistical and machine learning methods. These models will be informed by historical data from the Crowley Rice Research Station and local weather data.

Pest resistance surveillance: Determine the potential for key insect pests to develop resistance to widely used insecticides through laboratory bioassays.

Precision nutrient management: Compare standard N application practices and a “need-based” application of N-fertilizer using NDVI with ground/aerial sensors, and N-rich strip technology to reduce fertilizer use and production expenses.

Use of silicon, biostimulants, and mycorrhizae: (a) Evaluate the impact of Silicon amendments and biostimulants on rice pest and disease resistance. (b) Investigate the influence of commercial mycorrhizae on rice yield and pest numbers in large-scale field trials.

Cover crop: Selection of cover crops suitable for rice production system based on soil health assessment.

Expected outcomes:

Digital agriculture technology and crop modeling will benefit the growers in saving crop production costs with proper timing of management practices due to accurate forecasting of climate-induced biotic and abiotic stresses. The forecasting model for SB will be a crucial step in projecting the effect of climate change on disease development which can help the farmers to choose appropriate management practices. The benefits of mycorrhizae, Si amendment, cover crop, and precision nutrient management in improving soil health will be demonstrated. The development of biopesticides, a vital component of integrated disease management strategy, will reduce chemical use leading to improved environmental quality.