Unmanned aerial vehicles offer the opportunity for precision agriculture to efficiently monitor agricultural land. A vegetation index (VI) derived from an aerially observed multispectral image (MSI) can quantify crop health, moisture and nutrient content. However, due to the high cost of multispectral sensors, alternate, low-cost solutions have lately received great interest. We present a novel method for model-based estimation of a VI using RGB color images. The non-linear spatio-spectral relationship between the RGB image of vegetation and the index computed by its corresponding MSI is learned through deep neural networks. The learned models can be used to estimate VI of a crop segment. Analysis of images obtained in wheat breeding trials show that the aerially observed VI was highly correlated with ground-measured VI. In addition, VI estimates based on RGB images were highly correlated with VI deduced from MSIs. Spatial, spectral and temporal information of images contributed to estimation of VI. Both intra-variety and inter-variety differences were preserved by estimated VI. However, VI estimates were reliable until just before significant appearance of senescence. The proposed approach validates that it is reasonable to accurately estimate VI using deep neural networks. The results prove that RGB images contain sufficient information for VI estimation. It demonstrates that low-cost VI measurement is possible with standard RGB cameras.

This study evaluates an aerial and ground imaging platform for assessment of canopy development in a wheat field. The dependence of two canopy traits, height and vigour, on fertilizer treatment was observed in a field trial comprised of ten varieties of spring wheat. A custom-built mobile ground platform (MGP) and an unmanned aerial vehicle (UAV) were deployed at the experimental site for standard red, green and blue (RGB) image collection on five occasions. Meanwhile, reference field measurements of canopy height and vigour were manually recorded during the growing season. Canopy level estimates of height and vigour for each variety and treatment were computed by image analysis. The agreement between estimates from each platform and reference measurements was statistically analysed. Estimates of canopy height derived from MGP imagery were more accurate (RMSE = 3.95 cm, R${}^2$ = 0.94) than estimates derived from UAV imagery (RMSE = 6.64 cm, R${}^2$ = 0.85). In contrast, vigour was better estimated using the UAV imagery (RMSE = 0.057, R${}^2$ = 0.57), compared to MGP imagery (RMSE = 0.063, R${}^2$ = 0.42), albeit with a significant fixed and proportional bias. The ability of the platforms to capture differential development of traits as a function of fertilizer treatment was also investigated. Both imaging methodologies observed a higher median canopy height of treated plots compared with untreated plots throughout the season, and a greater median vigour of treated plots compared with untreated plots exhibited in the early growth stages. While the UAV imaging provides a high-throughput method for canopy-level trait determination, the MGP imaging captures subtle canopy structures, potentially useful for fine-grained analyses of plants.

Grain protein content (GPC) is a key quality attribute and an important marketing trait in wheat. In the current cropping systems worldwide, GPC is mostly determined by nitrogen (N) fertilizer application. The objectives of this study were to understand the differences in N response between high and low GPC wheat genotypes, and to assess the value of biomass growth analysis to assess the differences in N response. Six wheat genotypes from a range of high to low GPC were grown in low, medium and high N, under glasshouse conditions. This experiment was designed around non-destructive estimation of biomass using a high throughput image-based phenotyping system. Results showed that Spitfire and Mace had higher grain N% than Gazelle and QAL2000, and appeared to demand more N to grow their biomass. Moreover, at low N, Spitfire grew faster and achieved the maximum absolute growth rate earlier than high N-treated plants. High grain N% genotypes seem able to manage grain N reserves by compromising biomass production at low N. This study also indicated the importance of biomass growth analysis to show the differences in the N responsiveness of high and low GPC wheat.

Multi-environment trial studies provide an opportunity for the detailed analysis of complex traits. However, conducting trials across a large number of regions can be costly and labor intensive. The Australian National Variety Trials (NVT) provide grain yield and protein content (GPC) data of over 200 wheat varieties in many and varied environments across the Australian wheat-belt and is representative of similar trials conducted in other countries. Through our analysis of the NVT dataset, we highlight the advantages and limitations in using these data to explore the relationship between grain yield and GPC in the low yielding environments of Australia. Eight environment types (ETs), categorized in a previous study based on the time and intensity of drought stress, were used to analyze the impact of drought on the relationship between grain yield and protein content. The study illustrates the value of comprehensive multi-environment analysis to explore the complex relationship between yield and GPC, and to identify the most appropriate environments to select for a favorable relationship. However, the NVT trial design does not follow the rigor associated with a normal genotype × environment study and this limits the accuracy of the interpretation.