Image-based 3D canopy reconstruction to determine potential productivity in complex multi-species crop systems

Abstract

Background and Aims Intercropping systems contain two or more species simultaneously in close proximity. Due to contrasting features of the component crops, quantification of the light environment and photosynthetic productivity is extremely difficult. However it is an essential component of productivity. Here, a low-tech but high-resolution method is presented that can be applied to single- and multi-species cropping systems to facilitate characterization of the light environment. Different row layouts of an intercrop consisting of Bambara groundnut (Vigna subterranea) and proso millet (Panicum miliaceum) have been used as an example and the new opportunities presented by this approach have been analysed.Methods Three-dimensional plant reconstruction, based on stereo cameras, combined with ray tracing was implemented to explore the light environment within the Bambara groundnut–proso millet intercropping system and associated monocrops. Gas exchange data were used to predict the total carbon gain of each component crop.Key Results The shading influence of the tall proso millet on the shorter Bambara groundnut results in a reduction in total canopy light interception and carbon gain. However, the increased leaf area index (LAI) of proso millet, higher photosynthetic potential due to the C4 pathway and sub-optimal photosynthetic acclimation of Bambara groundnut to shade means that increasing the number of rows of millet will lead to greater light interception and carbon gain per unit ground area, despite Bambara groundnut intercepting more light per unit leaf area.Conclusions Three-dimensional reconstruction combined with ray tracing provides a novel, accurate method of exploring the light environment within an intercrop that does not require difficult measurements of light interception and data-intensive manual reconstruction, especially for such systems with inherently high spatial possibilities. It provides new opportunities for calculating potential productivity within multi-species cropping systems, enables the quantification of dynamic physiological differences between crops grown as monoculture and those within intercrops, and enables the prediction of new productive combinations of previously untested crops.

Intercropping with wheat lowers nutrient uptake and biomass accumulation of maize, but increases photosynthetic rate of the ear leaf

“…A second ‘ ex post ’ hypothesis that could explain high photosynthesis rate in intercropped maize is that the ear leaves (most often the ninth leaf) of intercropped maize had a greater exposure to sunlight than the ear leaves of sole maize, due to the different canopy structure and leaf area index (LAI). Similar patterns have been found in millet–groundnut intercrop ( Burgess et al 2017 ). As a result, ear leaves in intercropped maize are likely to be acclimated to a higher light level than ear leaves in sole maize.…”

A robot-assisted imaging pipeline for tracking the growths of maize ear and silks in a high-throughput phenotyping platform

“…The positioning of the camera and the ear image acquisition was fast enough allowing phenotyping hundreds of plants several times per day. Similar works have combined computer vision methods and robotics to increase the reconstruction accuracy of highly occluded complex plant structures [ 21 , 50 , 51 ]. Here, the combination of these methods allowed establishing a loop between extraction of partial descriptions of side view images and the positioning of the mobile camera, and thus acquiring precise images of ears and silks.…”

Three-dimensional plant architecture and sunlit–shaded patterns: a stochastic model of light dynamics in canopies

“…To investigate light dynamics in a range of canopies with different structural characteristics, we constructed digital canopies by assembling imaged and digitally reconstructed plants of wheat (lines 1 and 2 in Burgess et al , 2015 a ) and Bambara groundnut (from Burgess et al ., 2017 a , at two different growth stages: 39 and 80 d after sowing) in various configurations. The reconstructions represent the surface of a plant with a large number, N , of small triangular patches.…”

“…We constructed canopies in silico by arranging into various configurations several individual-plant reconstructions of Burgess et al (2015) and Burgess et al . (2017 a ), exploiting the periodic boundary conditions of the ray-tracer (explained below) which give a natural way to ‘tile’ individual plants to form an effective canopy.…”