Development of an early detection tool to assess drought stress in plants is crucial in reducing irrigation water used to grow agricultural crops. The AIDA model was developed using field data and variables that are physiologic and direct indicators of drought stress. A custom-built Spectra-Rover was constructed with infrared (IR) and RGB cameras to capture radiometric IR and RGB plant canopy images. Radiometric IR temperature, red, green, and blue light reflectance values, and soil moisture readings were used to train the AIDA model.
Eighty percent (80%) of the data was used in the training dataset and the remaining 20% was used in the validation dataset. The AIDA model validation output was very close to the actual CWSI values with a low mean absolute error. A prediction output program was coded and appended to the AIDA model to output an AIDA score. This accurately approximated the manually calculated CWSI values. If this novel AIDA model with an AIDA score is used on all tomato farms in California, approximately 26 billion gallons of irrigation water can be saved each season.
This is how I came up with the idea for this project:Witnessing the damage brought about by prolonged drought in our agricultural community here in California’s Central Valley inspired us to find a solution to this devastating problem. We develop a system that can predict the earliest signs of drought stress to help farmers conserve irrigation water without sacrificing their yield.
