Integration of smartphone technology for maize recognition

The study of android based maize assessment was done by involving two popular machine learning software i.e. teachable machine and android studio. The classification model was performed in online teachable machine learning while interface generation was performed in android studio. Various maize tassel from male, female and contamination plants were collected and used for training and model validation. The results indicated that Android-based tassel classification was successfully applied to the study area with accuracy of 80.7%. In addition, the error of classification was 19.3%, a relatively lower values for large testing datasets. Several mis-classification were found particularly at similar tassel shape. The integration of the model with smartphone technology enables rapid recognition of off-type plant at real-time, even though operated by personnel with limited skills or no knowledge seed technology on maize parental lines ideotype.

TasselGAN: An Application of the Generative Adversarial Model for Creating Field-Based Maize Tassel Data

Machine learning-based plant phenotyping systems have enabled high-throughput, non-destructive measurements of plant traits. Tasks such as object detection, segmentation, and localization of plant traits in images taken in field conditions need the machine learning models to be developed on training datasets that contain plant traits amidst varying backgrounds and environmental conditions. However, the datasets available for phenotyping are typically limited in variety and mostly consist of lab-based images in controlled conditions. Here, we present a new method called TasselGAN, using a variant of a deep convolutional generative adversarial network, to synthetically generate images of maize tassels against sky backgrounds. Both foreground tassel images and background sky images are generated separately and merged together to form artificial field-based maize tassel data to aid the training of machine learning models, where there is a paucity of field-based data. The effectiveness of the proposed method is demonstrated using quantitative and perceptual qualitative experiments.

Response surface methodology for optimization of Cd(II) adsorption from wastewaters by fabricated tartaric acid-maize tassel magnetic hybrid sorbent

Maize tassels (MT), an agro-based biomass waste was carbonised followed by thermo-chemical modification using tartaric acid. The functionalized activated carbon was further modified to yield a magnetic hybrid composite adsorbent. The adsorbent was characterized using Fourier transform infrared (FTIR) spectroscopy, X-ray diffraction (XRD) and Scanning Electron Microscopy (SEM). The adsorbent was evaluated for its efficiency to remove Cd(II) ions from aqueous solutions through batch adsorption studies following a Central Composite Design. Effects of solution pH, contact time, adsorbent dosage, initial metal concentration and temperature on Cd(II) adsorption were investigated. Optimization of the adsorption process was done using desirability function on the Design Expert V11 software. The desirability function showed that the optimum parameters were pH 5.29, contact time (67.50 min), dosage (0.575 g) and initial concentration (152.50 mg/L). The adsorption process was analysed using kinetic and isotherm models. The kinetics of the adsorption process followed the pseudo-second-order model (lowest sum of square error (SSE) values and correlation coefficients (R2) > 0.999) in addition to the intraparticle diffusion model. The isotherm data were consistent with the Langmuir isotherm as evidenced by the highest correlation coefficient (R2= 0.998). The thermodynamic parameters showed that the process was endothermic and spontaneous in nature. The adsorption capacity of the adsorbent was found to be 188.68 mg/g at 20 ⁰C which is higher than that of the previously reported magnetic maize tassel hybrid (52.05 mg/g). The adsorbent showed good removal efficiency on real effluent samples.

Reconstructing the transcriptional ontogeny of maize and sorghum supports an inverse hourglass model of inflorescence development

Assembling meaningful comparisons between species is a major limitation in studying the evolution of organismal form. To understand development in maize and sorghum, closely-related species with architecturally distinct inflorescences, we collected RNAseq profiles encompassing inflorescence body plan specification in both species. We reconstructed molecular ontogenies from 40 B73 maize tassels and 47 BT×623 sorghum panicles and separated them into transcriptional stages. To discover new markers of inflorescence development, we used random forest machine learning to determine stage by RNAseq. We used two descriptions of transcriptional conservation to identify hourglass-like developmental stages. Despite short evolutionary ancestry of 12 million years, we found maize and sorghum inflorescences are most different during their hourglass-like stages of development, following an ‘inverse-hourglass’ model of development. We discuss if agricultural selection may account for the rapid divergence signatures in these species and the observed separation of evolutionary pressure and developmental reprogramming.HighlightsTranscript dynamics identify maize tassel and sorghum panicle developmental stagesRandom forest predicts developmental age by gene expression, providing molecular markers and an in silico staging applicationMaize and sorghum inflorescences are most similar when committing stem cells to a determinant fateExpression conservation identifies hourglass-like stage, but transcriptomes diverge, similar to ‘inverse hourglass’ observations in cross-phyla animal embryo comparisons