A new model for water balance estimation on lettuce crops using effective diameter obtained with image analysis

Digital processing and analysis of vegetation cover images allow a precise calculation of some parameters related to crop development, which are linked to the estimation of irrigation requirements of the plants. In this paper, a new methodology for visual monitoring of horticultural crops and computation of the corresponding water needs is presented. The proposed approach is based on the concept of effective diameter, defined as the equivalent diameter of a plant biomass as seen from a top view. It has been applied to a 'Little Gem' lettuce crop. The percentage of green cover (PGC), computed by means of a digital processing of captured coverage images, is used to provide accurate estimates of the effective diameter of the plants. Then, this value can be precisely related with some important parameters in agronomy such as root depth, height of the plants, and crop coefficient Kc. Since Kc is an essential parameter in most existing methodologies for water balance estimation, an extensive comparative study on the accuracy of the proposed approach with respect to two alternative methods has been conducted. The first approach is based on PGC and crop density data, while the second is exclusively based on image analysis. The proposed method behaved significantly better in all cases, yielding a coefficient of determination, R2, to the actual Kc values obtained with a Bowen station always above 0.95, and a maximum relative error of only 2.1%. Moreover, the proposed methodology also produced accurate estimates of root depth with R2 values above 0.986 and maximum error below 9%. This approach not only leads to a reduction of water consumption compared to traditional estimation methods, but it also simplifies the required computations and field equipment.