J.CAVAZZONI and P.P. LING

ABSTRACT: We present a conceptual framework for coupling non-destructive sensing to crop models for closed-loop plant production for NASA’s program in advanced life support. Coupling is achieved by linking environmental variables and observations to model inputs and outputs. Monitoring results are then compared with model predictions of plant growth and development. The information thus provided may be useful in diagnosing problems with the plant growth system, or as a feedback to the model for evaluation of plant scheduling and potential yield. We illustrate this concept using machine vision sensing of soybean top projected canopy area (TPCA) and canopy height, and the CROPGRO crop growth model. Model simulations of these variables produced reasonable agreement with data for hydroponic soybean grown under two light cycle-dark cycle temperature regimes (26-22 ° C and 23-19 ° C). Our results suggest that machine vision sensing of TPCA and canopy height is potentially useful for closed-loop plant production in controlled environments during the first few weeks of growth

Keywords: machine vision sensing, controlled environment agriculture, feed-back control, CROPGRO