Current Projects
High-Throughput Screening of Wheat Genotypes for Drought Tolerance Using Aerial Thermal Imagery
Drought tolerance is critical in wheat breeding programs, ensuring yield stability and food security in water-limited environments. This study leverages high-throughput phenotyping using an uncrewed aerial vehicle (UAV) based thermal imagery to assess the drought response of wheat genotypes. Field trials were conducted under rainfed and irrigated conditions, with canopy temperature measurements obtained via UAV-mounted thermal sensors. Additionally, ground-based infrared thermometer (IRT) readings and yield data were collected for evaluation. Canopy Temperature Depression (CTD) served as an important physiological indicator, where lower canopy temperatures indicated superior water use efficiency, deeper rooting, and better transpiration regulation. The study established strong correlations between thermal indices and drought susceptibility indices (DSI), demonstrating the relevance of canopy temperature measurements in identifying stress-resilient genotypes. Rainfed trial data exhibited stronger correlations between canopy temperature and yield-based indices, highlighting the role of temperature regulation in drought tolerance assessment. The results underscore the effectiveness of predictive models in assessing various yield-based and spectral indices. Linear Regression (LR) emerged as the most robust model, achieving high coefficient of determination (R²) values across multiple indices and channels. Drought resistance index (DRI), and yield stability index (YSI), when paired with green normalized difference vegetation index (GNDVI) and normalized difference water index (NDWI), achieved the highest R² values of approximately 65%, demonstrating strong predictive capabilities. Overall, this study highlights the utility of UAV-based thermal phenotyping, combined with vegetation indices and robust predictive models, as a scalable and efficient approach for selecting climate-resilient wheat genotypes.
Precision Phenotyping in Wheat: LiDAR-Based Plant Height and Lodging Estimation Using Uncrewed Ground Vehicle
Accurate phenotyping of wheat traits is essential for advancing breeding programs and crop science research. This study employs the University of Saskatchewan Field Phenotyping Systems (UFPS), an uncrewed ground vehicle (UGV), across six Canadian research stations during the 2023 and 2024 field seasons to explore LiDAR-based evaluation of plant height and lodging in spring wheat. A total of 90 plots of 30 historical wheat cultivars were planted in a Randomized Complete Block Design (RCBD), with LiDAR data collected at key growth stages. Four methods—height distribution vector, overhead projection, orthographic projection, and voxelized spatial grid—were assessed for height and lodging estimation. For plant height, overhead projection (95.98%) and orthographic projection (96.05%) delivered the highest accuracy, with RMSE and MAPE at 3.7 cm and 3.55%. Voxelized spatial grid and height distribution vector methods showed lower performance, with R-squared values of 88.15% and 84.37%. For lodging, overhead projection excelled, achieving up to 0.97 Quadratic Weighted Kappa (QWK), and 98.51% Macro-F1 (MF1), especially in 2- and 3-class scenarios. The voxelized spatial grid performed well, while the height distribution vector and orthographic projection lagged with more classes. These results establish overhead projection as a robust method for high-throughput phenotyping in spring wheat.
Image acquisition for quantifying agronomic traits to evaluate wheat cultivars in different agro-climatic conditions using UFPS (University of Saskatchewan Field Phenotyping System)
Working with UFPS phenocart will facilitate to characterize the differences in a large set of diverse wheat cultivars. This project will develop and advance methodologies to process and analyze high-resolution imagery. The data will be use to quantify phenometrics that will aid in crop breeding programs. To facilitate plant phenotyping, the establishment of UFPS system will require various phases of development
- Imaging with the proximal sensors mounted on a GPS-enabled phenocart to acquire multilocation datasets from diverse wheat cultivars.
- Explore and identify data management, integration and computing options to efficiently store, share, process and archive big volume of phenomics dataset.
- Develop multivariate regression algorithms for training and validation of data collected from different environment field trials within wheat breeding programs.
- Establish a data collection, processing and analysis pipeline that translate acquired images into phenometrics, to interpret for traits selection by wheat breeders.