Fusion of Spectral and Structural Information from Aerial Images for Improved Biomass Estimation

Abstract

Efficient, precise and timely measurement of plant traits is important in the assessment of a breeding population. Estimating crop biomass in breeding trials using high-throughput technologies is difficult, as reproductive and senescence stages do not relate to reflectance spectra, and multiple growth stages occur concurrently in diverse genotypes. Additionally, vegetation indices (VIs) saturate at high canopy coverage, and vertical growth profiles are difficult to capture using VIs. A novel approach was implemented involving a fusion of complementary spectral and structural information, to calculate intermediate metrics such as crop height model (CHM), crop coverage (CC) and crop volume (CV), which were finally used to calculate dry (DW) and fresh (FW) weight of above-ground biomass in wheat. The intermediate metrics, CHM (R2 = 0.81, SEE = 4.19 cm) and CC (OA = 99.2%, Κ = 0.98) were found to be accurate against equivalent ground truth measurements. The metrics CV and CV×VIs were used to develop an effective and accurate linear regression model relationship with DW (R2 = 0.96 and SEE = 69.2 g/m2) and FW (R2 = 0.89 and SEE = 333.54 g/m2). The implemented approach outperformed commonly used VIs for estimation of biomass at all growth stages in wheat. The achieved results strongly support the applicability of the proposed approach for high-throughput phenotyping of germplasm in wheat and other crop species.

CBM: An IoT enabled LiDAR sensor for in-field crop height and biomass measurements

“…Crop volume measurement of wheat was earlier reported to correlate with FW and DW (Banerjee et al, 2020). Therefore, linear regression modeling was applied to estimate FW and DW from BV, producing R 2 of 0.70 and 0.84, RMSE of 490 gm and 138 gm, and MAE of 375 gm and 111 gm, respectively (Figure 9b,c).…”

“…Different reflectance based imaging sensors such as multispectral and hyperspectral systems have been used to estimate biomass. Fusion of reflectance and structural information has been reported useful to estimate crop biomass (Banerjee et al, 2020;Tilly et al, 2015). Other sensors such as ultrasonic devices and most of the light detection and ranging (LiDAR) systems are all based on the timeof-flight (ToF) principle (Klose et al, 2009;Lu et al, 2017).…”

The Potential of Widespread Ready-Made UAVs in Quantifying Conifers and Delineating Their Crowns

“…Despite their still limited payload capacity, ight endurance and massive data storage and processing capabilities (Matese et al, 2015), unmanned systems bring great potential bene ts to forestry applications (Banu et al, 2016) due to their relatively low acquisition costs, increasing user-friendliness, and high exibility regarding temporal and sensor variability. Over the last few years, their popularity increased (Gambella et al, 2016) and those systems are now used for plant species classi cation (Brovkina et al, 2018;Nevalainen et al, 2017), individual tree detection (Klouček et al, 2019;Mohan et al, 2017), complex assessment of forest structure (Tuominen et al, 2017;Wallace et al, 2016) and biomass estimations (Banerjee et al, 2020).…”

Estimation of nitrate nitrogen content in cotton petioles under drip irrigation based on wavelet neural network approach using spectral indices

“…Diagnosis of N nutrition in crops based on spectral data has made considerable progress [ 17 ]. The technique has been applied in several crops to obtain crop N nutrition status spectral indices [ 18 – 20 ]. Based on spectral indices, various crop N nutrition monitoring models have been established, and they have achieved a high accuracy.…”