Transferability of Models for Predicting Rice Grain Yield from Unmanned Aerial Vehicle (UAV) Multispectral Imagery across Years, Cultivars and Sensors

Abstract

Timely and accurate prediction of crop yield prior to harvest is vital for precise agricultural management. Unmanned aerial vehicles (UAVs) provide a fast and convenient approach to crop yield prediction, but most existing crop yield models have rarely been tested across different years, cultivars and sensors. This has limited the ability of these yield models to be transferred to other years or regions or to be potentially used with data from other sensors. In this study, UAV-based multispectral imagery was used to predict rice grain yield at the booting and filling stages from four field experiments, involving three years, two rice cultivars, and two UAV sensors. Reflectance and texture features were extracted from the UAV imagery, and vegetation indices (VIs) and normalized difference texture indices (NDTIs) were computed. The models were independently validated to test the stability and transferability across years, rice cultivars, and sensors. The results showed that the red edge normalized difference texture index (RENDTI) was superior to other texture indices and vegetation indices for model regression with grain yield in most cases. However, the green normalized difference texture index (GNDTI) achieved the highest prediction accuracy in model validation across rice cultivars and sensors. The yield prediction model of Japonica rice achieved stronger transferability to Indica rice with root mean square error (RMSE), bias, and relative RMSE (RRMSE) of 1.16 t/ha, 0.08, and 11.04%, respectively. Model transferability was improved significantly between different sensors after band correction with a decrease of 15.05–59.99% in RRMSE. Random forest (RF) was found to be a good solution to improve the model transferability across different years and cultivars and obtained the highest prediction accuracy with RMSE, bias, and RRMSE of 0.94 t/ha, −0.21, and 9.37%, respectively. This study provides a valuable reference for crop yield prediction when existing models are transferred across different years, cultivars and sensors.

The Transferability of Spectral Grain Yield Prediction in Wheat Breeding across Years and Trial Locations

“…In a study on GY prediction between three years for two rice cultivars and multiple nitrogen levels based on multispectral UAV-based data, correlations differed between years, cultivars and two sensors [17]. Depending on the year combinations, either a normalized red edge reflectance or a texture index was recommended.…”

Visualization of the Effect of Additional Fertilization on Paddy Rice by Time-Series Analysis of Vegetation Indices using UAV and Minimizing the Number of Monitoring Days for its Workload Reduction

“…This was calculated by normalizing the NIR and Red bands. It is widely used; however, it has been reported that the soil easily affects it, and the index becomes saturated during the peak vegetation season [6], [16], [17]. The NDRE was used to diagnose crop stress and nitrogen content.…”

“…The RE band reaches deeper into the canopy than the Red band; therefore, stress can be detected earlier. Additionally, it is not easily saturated; therefore, depending on the season, it may be more appropriate than NDVI for diagnosing vegetation and yield [7], [17], [18]. A Standardized Normalized Difference Red Edge Index (sNDRE) was developed to ensure that the NDRE did not change unless it was under significant stress.…”

Generalizability of a Random Forest-based model of maize lodging built with satellite image data and its application to monitoring and evaluating maize lodging risks

“…The study area was located at the junction of Yihe Tara Town and Jianhua Town in Kailu County, Tongliao City, Inner Mongolia (43°40'40-43°43'40 "N; 121°8'20-121°12'40 "E). This region is within a middle temperate regional climate zone and has a semi-arid continental monsoon climate with dry, windy conditions, a long frost-free period, sufficient sunshine, and high cumulative temperatures [22], making it suitable for maize growth and development.…”