As the global population continues to increase, the demand for food production rises accordingly. The water availability of crops has a significant impact on their yield during the processes of photosynthesis and transpiration. Crops exchange carbon dioxide and water with the atmosphere through stomata. When crops undergo water stress, they tend to close their stomata to reduce water loss. However, this can also negatively affect the crop's photosynthetic rate and carbon assimilation, leading to low yields. Stomatal conductance (SC) quantifies the rate of gas exchange between crops and the atmosphere and can inform the crop's water status. SC measurements require the use of contact-type instruments, which is time-consuming and labor-intensive. This study examined the accuracy of multiple linear regression (MLR), support vector regression (SVR), and convolutional neural network (CNN) models for SC estimation in corn and soybean using RGB, near-infrared, and thermal-infrared images from a field phenotyping platform. The results show that the CNN model outperformed other two models, with R 2 value of 0.52. Furthermore, adding soil moisture as a variable to the model improved its accuracy, decreasing model RMSE from 0.147 to 0.137 mol/(m2*s). This study highlights the potential of estimating SC from remote sensing platforms to help growers obtain information about their crop water status and plan irrigation more effectively.
Crop nitrogen (N) content reflects crop nutrient status and is an important trait in crop management. Over the decades, non-destructive N estimation has greatly benefited from remote sensing and data-intensive computational approaches. However, previous studies mostly focused on the estimation accuracy under a specific environment; few of them considered estimation robustness across varying growth conditions. As climate change intensifies, crops are facing more unexpected stresses. It is critical to improve N estimation under changing environments with better model generalizability. Thus, we proposed a novel hybrid method with merits of both mechanistic and machine learning models and integrating in-situ data and simulated data for an improved model training. The in-situ data were the canopy reflectance extracted from hyperspectral images collected by an Unmanned Aerial Vehicle (UAV) and destructively sampled plant N content;the simulated data referred to the canopy reflectance simulated by a mechanistic model, the PROSAIL-PRO. The performance of the hybrid method was compared with one of the most popular machine learning models (i.e., Gaussian Process Regression, GPR) across three study sites. Results showed that the hybrid method outperformed the GPR by reducing RRMSE up to 6.84% on canopy nitrogen content (CNC) estimation. It also achieved more stable performances across varying soil water and N availabilities. Altogether, we demonstrated an approach to estimate CNC under diversesoil and environmentalconditions from remotely sensed spectral data with better accuracy and generalizability. It leverages the robustness of mechanistic models and the computational efficiency of machine learning models and has great potential to be transferred to other crops and many common crop traits.
Plant height is an important trait in crop breeding as it has high correlations with grain yield, biomass, and stress tolerance. Most of the studies so far for field-based high-throughput plant height phenotyping with UAS rely on ground control points (GCPs) for geometric calibrations due to the limited positioning accuracy of the GPS onboard. Setting up these GCPs is labor-intensive and is not feasible for a large field. The advent of commercial UAS equipped with Real-Time Kinematic (RTK) Global navigation satellite system (GNSS) technology are expected to achieve a centimeter-level positioning accuracy and have the potential of expediting and improving plant height phenotyping process. Hence, the objective of our study was to investigate the potential and dependency on GCPS of RTK GNSS enabled UAS technology and compare its performance to regular differential GNSS on plant height estimation. In the summer of 2021, images were corrected with two UAS – one with RTK GNSS; and the other with regular differential GNSS – for three different methods over cornfields: Method 1 used both the differential GNSS and the GCPs; Method 2 used both the RTK GNSS with the realtime corrections via cellular network and the GCPs; Method 3 used only the RTK GNSS with the real time corrections via cellular network but without GCPs. In this study, method 2 and 3 resulted with close accuracies, with a 𝑅2 of 0.775 for method 2 and a 𝑅2of 0.760 for method 3 in maize plant height estimation. Method 1 had the lowest correlation (𝑅2 = 0.250) in this study mostly due to the less data and data quality issues. Results from the study showed that the RTK GNSS enabled UAS has the potential and less dependency on GCPs in deriving accurate horizontal positioning and estimating plant height. Aerial surveys and plant phenotyping with RTK GNSS enabled UAS are more convenient and easily deployed in plant phenotyping and precision agriculture.
Leaf area index (LAI) is an important phenotypic trait closely related to plant vigor and biomass. It is also a key parameter used in crop growth modeling. However, manually measuring LAI in the field can be slow and labor intensive. High resolution remote sensing, such as unmanned aircraft systems (UAS), has been explored for LAI estimation but with limited data sources, usually RGB and multispectral imagery. As UAS-based thermal infrared (TIR) imaging becoming readily available in agriculture, it is worth investigating the potential of its role in improving LAI estimation. In this study we evaluated the importance of canopy temperature measured by UAS-based TIR and multispectral imagery on maize LAI quantification within a breeding context (23 genotypes). Five plot-level features (canopy temperature, structure and two common vegetation indices) were extracted from the images, and used as inputs of machine learning models for the LAI estimation. The performance of the estimation was evaluated with a 5-fold cross validation with 30 random repeats for 162 samples. Results showed that, canopy temperature, together with canopy structure as model predictors, slightly improved LAI estimation (root mean square error, RMSE of 0.853 m2/m2 and coefficient of determination, R2 of 0.740) than those models without temperature difference (RMSE of 0.917 m2/m2 and R2 of 0.706) for the various genotypes included in this study. In addition, canopy temperature showed moderate and more stable significance in estimating LAI than plant height and image uniformity. Its contribution to the estimation was comparable or even higher than those from vegetation indices when being modeled with random forest in this study. These relationships may be changed with a single or less genotypes which can be explored in future studies.
Leaf stomata regulate the process of gas exchange between the plant and the atmosphere, therefore play an important role in plant growth and water use. Thermal infrared sensing of leaf surface temperature is proved to be an indirect but effective approach to estimate leaf stomatal conductance, and shows the potential to rapidly differentiate genotypes for water-use related traits. The objective of this study was to estimate leaf stomatal conductance from thermal IR images of crops and relevant environmental parameters. The experiment was conducted in the NU-Spidercam field phenotyping facility near Mead, NE. Leaf stomatal conductance was measured from soybean, sorghum, maize, and sunflower using a leaf porometer. Thermal IR images of the crop canopies were captured by a thermal IR camera and then processed to extract crop canopy temperature (Tc). In addition, weather variables including solar radiation, air temperature, relative humidity, and wind speed were extracted from a nearby weather station. Correlation analysis was implemented to explore the relationships between these variables. Multiple linear regression (MLR), random forest (RF), gradient boosting machine (GBM) were applied to model stomatal conductance from Tc and weather variables. The Pearson correlation coefficients between predicted and measured stomatal conductance were 0.495 for MLR, 0.591 for RF, and 0.878 for GBM when Tc was not used as an input variable. After adding Tc as input, Pearson correlation coefficients were improved to 0.584 for MLR, 0.593 for RF, and 0.896 for GBM. The mean absolute errors for the three models were 225, 237, and 129 mmol/(m2·s) when Tc was included as a model input. This research would lead to rapid assessment of leaf stomatal conductance and crop water status using thermal IR imaging.
High throughput phenotyping (HTP) is an emerging frontier field across many basic and applied plant science disciplines. RGB imaging is most widely used in HTP to extract image-based phenotypes such as pixel volume or projected area. These image-based phenotypes are further used to derive plant physical parameters including plant fresh biomass, plant dry biomass, water use efficiency etc. In this paper, we investigated the robustness of regression models to predict fresh biomass of maize plants from image-based phenotypes. Data used in this study were from three different experiments. Data were grouped into five datasets, two for model development and three for independent model validation. Three image-derived phenotypes were investigated: BioVolume, Projected.Area.1, and Projected.Area.2. Models were assessed with R2, Bias, and RMSEP (Root Mean Squared Error of Prediction). The results showed that almost all models were validated with high R2 values, indicating that these digital phenotypes can be useful to rank plant biomass on a relative basis. However, in many occasions when accurate prediction of plant biomass is needed, it is important for researchers to know that models that relate image-based phenotypes to plant biomass should be carefully constructed. Our results show that the range of plant size and the genotypic diversity of the calibration sets in relation to the validation sets have large impact on the model accuracy. Large maize plants cause systematic bias as they grow toward the top-view camera. Excluding top-view images from modeling can there benefit modeling for the experiments involving large maize plants.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.