Accurate inference of shoot biomass from high-throughput images of cereal plants

Abstract

With the establishment of advanced technology facilities for high throughput plant phenotyping, the problem of estimating plant biomass of individual plants from their two dimensional images is becoming increasingly important. The approach predominantly cited in literature is to estimate the biomass of a plant as a linear function of the projected shoot area of plants in the images. However, the estimation error from this model, which is solely a function of projected shoot area, is large, prohibiting accurate estimation of the biomass of plants, particularly for the salt-stressed plants. In this paper, we propose a method based on plant specific weight for improving the accuracy of the linear model and reducing the estimation bias (the difference between actual shoot dry weight and the value of the shoot dry weight estimated with a predictive model). For the proposed method in this study, we modeled the plant shoot dry weight as a function of plant area and plant age. The data used for developing our model and comparing the results with the linear model were collected from a completely randomized block design experiment. A total of 320 plants from two bread wheat varieties were grown in a supported hydroponics system in a greenhouse. The plants were exposed to two levels of hydroponic salt treatments (NaCl at 0 and 100 mM) for 6 weeks. Five harvests were carried out. Each time 64 randomly selected plants were imaged and then harvested to measure the shoot fresh weight and shoot dry weight. The results of statistical analysis showed that with our proposed method, most of the observed variance can be explained, and moreover only a small difference between actual and estimated shoot dry weight was obtained. The low estimation bias indicates that our proposed method can be used to estimate biomass of individual plants regardless of what variety the plant is and what salt treatment has been applied. We validated this model on an independent set of barley data. The technique presented in this paper may extend to other plants and types of stresses.

Figure 1

Process flow of image processing steps used in the extraction of plant's projected shoot area from the images.

Figure 2

Scatter plot of the linear method for two wheat varieties. The blue and green lines are the lines of best fit for two cultivar categories.

Figure 3

A scatter plot of actual SDW compared with the estimated values obtained using the linear model for two salt treatment categories. The blue and green lines are the lines of best fit for two salt treatment categories.

Figure 4

A scatter plot of actual SDW compared with the estimated values obtained using the linear model for five plant age categories.

Figure 5

Scatter plot of Plant Specific Weight in terms of time after planting (plant age). A straight line, the line of best fit, seems to describe a plant's PSW in terms of its age.

Figure 6

Scatter plots of actual SDW compared with the estimated values obtained using the model proposed in this study for two wheat varieties.

Figure 7

Scatter plots of actual SDW compared with the estimated values obtained using the model proposed in this study for two salt treatment categories.

Figure 8

Scatter plots of actual barley shoot dry weight values compared with the estimated shoot dry weight values obtained from Model A (left) and the Model B (right) under two salt treatment categories.