Estimating dry biomass and plant nitrogen concentration in pre-Alpine grasslands with low-cost UAS-borne multispectral data – a comparison of sensors, algorithms, and predictor sets

Abstract

Abstract. Grasslands are an important part of pre-Alpine and Alpine landscapes. Despite the economic value and the significant role of grasslands in carbon and nitrogen (N) cycling, spatially explicit information on grassland biomass and quality is rarely available. Remotely sensed data from unmanned aircraft systems (UASs) and satellites might be an option to overcome this gap. Our study aims to investigate the potential of low-cost UAS-based multispectral sensors for estimating above-ground biomass (dry matter, DM) and plant N concentration. In our analysis, we compared two different sensors (Parrot Sequoia, SEQ; MicaSense RedEdge-M, REM), three statistical models (linear model; random forests, RFs; gradient-boosting machines, GBMs), and six predictor sets (i.e. different combinations of raw reflectance, vegetation indices, and canopy height). Canopy height information can be derived from UAS sensors but was not available in our study. Therefore, we tested the added value of this structural information with in situ measured bulk canopy height data. A combined field sampling and flight campaign was conducted in April 2018 at different grassland sites in southern Germany to obtain in situ and the corresponding spectral data. The hyper-parameters of the two machine learning (ML) approaches (RF, GBM) were optimized, and all model setups were run with a 6-fold cross-validation. Linear models were characterized by very low statistical performance measures, thus were not suitable to estimate DM and plant N concentration using UAS data. The non-linear ML algorithms showed an acceptable regression performance for all sensor–predictor set combinations with average (avg; cross-validated, cv) Rcv2 of 0.48, RMSEcv,avg of 53.0 g m2, and rRMSEcv,avg (relative) of 15.9 % for DM and with Rcv,avg2 of 0.40, RMSEcv,avg of 0.48 wt %, and rRMSEcv, avg of 15.2 % for plant N concentration estimation. The optimal combination of sensors, ML algorithms, and predictor sets notably improved the model performance. The best model performance for the estimation of DM (Rcv2=0.67, RMSEcv=41.9 g m2, rRMSEcv=12.6 %) was achieved with an RF model that utilizes all possible predictors and REM sensor data. The best model for plant N concentration was a combination of an RF model with all predictors and SEQ sensor data (Rcv2=0.47, RMSEcv=0.45 wt %, rRMSEcv=14.2 %). DM models with the spectral input of REM performed significantly better than those with SEQ data, while for N concentration models, it was the other way round. The choice of predictors was most influential on model performance, while the effect of the chosen ML algorithm was generally lower. The addition of canopy height to the spectral data in the predictor set significantly improved the DM models. In our study, calibrating the ML algorithm improved the model performance substantially, which shows the importance of this step.

Opportunities for Adaptation to Climate Change of Extensively Grazed Pastures in the Central Apennines (Italy)

“…The great deal of fundamental research incorporated into the mechanistic PaSim model has ensured satisfactory estimates, which are also comparable to published grassland modeling studies [68,69]. This is relevant considering that simulations for grasslands are generally less accurate compared with arable crops [70] since large uncertainties in biomass and LAI measurements cause simulation of grassland vegetation dynamics to be difficult to perform [67,71].…”

An Overview of Using Unmanned Aerial System Mounted Sensors to Measure Plant Above-Ground Biomass

“…The majority of studies considered in this review (more than 65%) reported using rotary-wing platforms to collect data, and quadcopters were the most frequently employed (45-67%) platform (Figure 2). The eBee UASs (developed by senseFly, Swiss, Switzerland) was the commonly used fixed-wing UAS to estimate the AGB [34,48,[70][71][72]. It does not come as surprise that most of the studies reported using DJI drones (DJI Inc., Shenzhen, China) (Phantom 3, Phantom 4, Matrice 100, Matrice 200, and Matrice 600) as the platform of choice to carry RGB [11,17,32,73], multispectral (MS) [45,72,[74][75][76][77], hyperspectral (HS) [78][79][80], and LIDAR [81][82][83] sensors.…”

The role of remote sensing in tropical grassland nutrient estimation: a review

“…Presently, cost-effective unmanned aerial vehicles (UAVs) are developing technologies in the estimation of grasslands parameters. In addition to providing high-spatial-resolution imagery, UAVs are also less subject to cloud and haze interference, making them suitable for measuring grassland aboveground biomass and biochemicals (Franceschini et al, 2022 ; Schucknecht et al, 2022 ). For instance, Schucknecht et al ( 2022 ) evaluated the effectiveness of UAV-borne multispectral data for determining dry biomass and nitrogen (N) concentration of pre-Alpine grasslands.…”

“…In addition to providing high-spatial-resolution imagery, UAVs are also less subject to cloud and haze interference, making them suitable for measuring grassland aboveground biomass and biochemicals (Franceschini et al, 2022 ; Schucknecht et al, 2022 ). For instance, Schucknecht et al ( 2022 ) evaluated the effectiveness of UAV-borne multispectral data for determining dry biomass and nitrogen (N) concentration of pre-Alpine grasslands. The authors produced a relative root mean square error (average cross-validated) rRMSE cv of 12.6 % for dry biomass and rRMSE cv of 14.2 % for N model using the raw reflectance and vegetation indices.…”

“…Remotely sensed data offers a timely, economical, and efficient approach to monitoring rangelands’ foliar biochemicals for assessment and management (Lu et al, 2020 ; Ramoelo et al, 2012 ). In addition, present advancements in sensor technology have enhanced the estimation and detection of changes in grassland health and biomass (Schucknecht et al, 2021 ; Zhao et al, 2021 ). In addition, remotely sensed data can be integrated with ancillary data, augmenting data-based decision-making in rangeland management.…”