A hyperspectral plant health monitoring system for space crop production

Compact and automated sensing systems are needed to monitor plant health for NASA’s controlled-environment space crop production. A new hyperspectral system was designed early detection of stresses using both reflectance fluorescence imaging in visible near-infrared (VNIR) wavelength range (400–1000 nm). The prototype mainly includes two LED line lights providing VNIR broadband UV-A (365 nm) light measurement, respectively, a line-scan camera, linear motorized stage with travel 80 cm. In an overhead sensor-to-sample arrangement, the translates camera over plants acquire images sequence during one cycle imaging. System software developed LabVIEW realize hardware parameterization, data transfer, functions. unit installed growth chamber at NASA Kennedy Space Center monitoring studies pick-and-eat salad crops. preliminary experiment conducted detect drought stress twelve Dragoon lettuce samples, which half were well-watered under-watered while growing. machine learning method optimized discriminant classifier based on spectra generated classification accuracies 90% first four days treatment, showing great potential leaves before any symptoms size differences evident. is promising provide useful information optimization environment mitigation