High-Resolution UAV-Based Hyperspectral Imagery for LAI and Chlorophyll Estimations from Wheat for Yield Prediction

Abstract

The efficient use of nitrogen fertilizer is a crucial problem in modern agriculture. Fertilization has to be minimized to reduce environmental impacts but done so optimally without negatively affecting yield. In June 2017, a controlled experiment with eight different nitrogen treatments was applied to winter wheat plants and investigated with the UAV-based hyperspectral pushbroom camera Resonon Pika-L (400-1000 nm). The system, in combination with an accurate inertial measurement unit (IMU) and precise gimbal, was very stable and capable of acquiring hyperspectral imagery of high spectral and spatial quality. Additionally, in situ measurements of 48 samples (leaf area index (LAI), chlorophyll (CHL), and reflectance spectra) were taken in the field, which were equally distributed across the different nitrogen treatments. These measurements were used to predict grain yield, since the parameter itself had no direct effect on the spectral reflection of plants. Therefore, we present an indirect approach based on LAI and chlorophyll estimations from the acquired hyperspectral image data using partial least-squares regression (PLSR). The resulting models showed a reliable predictability for these parameters (R 2 LAI = 0.79, RMSE LAI [m 2 m −2 ] = 0.18, R 2 CHL = 0.77, RMSE CHL [µg cm −2 ] = 7.02). The LAI and CHL predictions were used afterwards to calibrate a multiple linear regression model to estimate grain yield (R 2 yield = 0.88, RMSE yield [dt ha −1 ] = 4.18). With this model, a pixel-wise prediction of the hyperspectral image was performed. The resulting yield estimates were validated and opposed to the different nitrogen treatments, which revealed that, above a certain amount of applied nitrogen, further fertilization does not necessarily lead to larger yield.From the farmer's perspective, the most important economic parameter is achieved yields. An overdose of N fertilizer, within the legal limits, results higher costs without adding value in terms of additional yield. Further possible regulations for the application of fertilizers should only have a limited negative impact on yields. With controlled experiments, directly comparing the harvested yield resulting from different N applications, one can identify the effects of reduced fertilization. Moreover, new concepts of monitoring these effects during vegetative growth enables the development of precision farming applications, especially created for efficient N fertilization [3].Remote sensing technology at various scales has often proved to be a suitable tool for agricultural crop monitoring [4]. In particular, UAV-supported remote sensing enables very precise monitoring of individual areas through lower flight altitudes and high-resolution data [5]. In recent years, the development of UAV-based hyperspectral recording systems has made rapid progress [6]. In comparison to manned aircraft based systems, the sensors are smaller, lighter, and less costly during acquisition and processing [7]. The great potential of this technology has been demonstrated [8].Hyper...

Combining Color Indices and Textures of UAV-Based Digital Imagery for Rice LAI Estimation

“…Previous research has revealed significant differences in the results of UAV RS-based crop growth monitoring due to the use of different sensors [14]. With the exception of a few studies using Lidar [52] and non-imaging active or passive canopy sensors [7,53], most of the UAV-based studies have used imaging spectrometers or multispectral [16,48] and hyperspectral cameras [19]. However, professional imaging sensors, UAV systems, and their supporting software may lead to a high total cost for ordinary consumers and cause challenges for technical promotion.…”

“…Considering remotely sensed variables, traditional spectral indices such as VIs or CIs have been widely used in UAV RS-based crop biomass estimation [57], flower count [58], vegetation detection [59], yield prediction [19,48], and other applications of precision agriculture [60]. On the other hand, other studies have also used spatial information derived from UAV-based imagery, such as digital crop surface models (CSMs) [36], degree of canopy cover [61], plant height [36], and textures [49] for crop growth monitoring.…”

“…The VIs consisting of near-infrared and red edge bands performed well in the universal predictive models both for UAV-based and handheld applications. Kanning et al [19] demonstrated the reliable predictability of wheat LAI and chlorophyll content using canopy spectra extracted from UAV-based hyperspectral images and partial least-squares regression. However, the widespread use of professional multispectral and hyperspectral cameras is limited by their high cost and the complexity of data processing.…”

High-Throughput Prediction of Whole Season Green Area Index in Winter Wheat With an Airborne Multispectral Sensor

“…Before discussing different GAI-models or possible areas of application, it is necessary to consider the applicability of the Sequoia camera. Other studies using different UAV-based sensors in general (Duan et al, 2017;Zhou et al, 2017;Condorelli et al, 2018;Kanning et al, 2018), predecessors of the Sequoia sensor (Verger et al, 2014;Haghighattalab et al, 2016;Nebiker et al, 2016) and in particular the Sequoia sensor (Condorelli et al, 2018;Tunca et al, 2018) showed promising results in terms of comparability with ground-based multispectral sensors and their implication to generate information about crop characteristics. Our results match to these findings; the Sequoia camera provides reliable and sufficiently accurate data for crop monitoring purposes on plot level in terms of a scientific context.…”

Estimating Peanut Leaf Chlorophyll Content with Dorsiventral Leaf Adjusted Indices: Minimizing the Impact of Spectral Differences between Adaxial and Abaxial Leaf Surfaces

“…The Sentinel-2 multispectral instrument includes three bands in the red-edge region centered at 705, 740, and 775 nm, which were found to be of great interest for crop monitoring [46]. Unmanned aerial vehicle (UAV) platforms coupled with imaging sensors are able to collect multispectral or hyperspectral imagery and offer great possibilities in the precision farming [47,48]. When using these remote sensing techniques to investigate peanut canopy information, the spectral information collected by the sensors may not only come from the adaxial leaf surfaces but also the abaxial leaf surfaces.…”