Remote Sensing-Based Estimation of Advanced Perennial Grass Biomass Yields for Bioenergy

Abstract

A sustainable bioeconomy would require growing high-yielding bioenergy crops on marginal agricultural areas with minimal inputs. To determine the cost competitiveness and environmental sustainability of such production systems, reliably estimating biomass yield is critical. However, because marginal areas are often small and spread across the landscape, yield estimation using traditional approaches is costly and time-consuming. This paper demonstrates the (1) initial investigation of optical remote sensing for predicting perennial bioenergy grass yields at harvest using a linear regression model with the green normalized difference vegetation index (GNDVI) derived from Sentinel-2 imagery and (2) evaluation of the model’s performance using data from five U.S. Midwest field sites. The linear regression model using midsummer GNDVI predicted yields at harvest with R2 as high as 0.879 and a mean absolute error and root mean squared error as low as 0.539 Mg/ha and 0.616 Mg/ha, respectively, except for the establishment year. Perennial bioenergy grass yields may be predicted 152 days before the harvest date on average, except for the establishment year. The green spectral band showed a greater contribution for predicting yields than the red band, which is indicative of increased chlorophyll content during the early growing season. Although additional testing is warranted, this study showed a great promise for a remote sensing approach for forecasting perennial bioenergy grass yields to support critical economic and logistical decisions of bioeconomy stakeholders.

UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of Miscanthus by Machine Learning Techniques

“…Among the VIs used in the RF model, the peak of the VIs based on the green band as GNDVI and greenWDRVI (Figure 3) were the most important variables for predicting not only Miscanthus yield at harvest, but also in estimating standing biomass and green leaf biomass during the growing season (Figure 4). Similar results for GNDVI were found in switchgrass and other warm-season perennial grasses [26]. In order to assess the capability of the model to predict the yield months before harvest (i.e., using only early season UAV acquisition and not waiting to perform UAV monitoring during the entire crop season), the RF model was calculated using the peak derived from the partial time series of Vis, and performance analysed.…”

“…The daily time series of the VIs were used to estimate the crop traits by linking the traits values measured in the field with the VIs' values of the time series. To predict yield, the peak descriptor was chosen among several land surface phenology (LSP) descriptors, due to the reliability it achieved in previous studies [17,26,47]. The peak descriptor is defined as the maximum value and was derived from the GAM fitting of each VI time series.…”

“…Remote sensing approaches can also be used to (i) estimate yield-related traits for high-throughput phenotyping (HTP) [20][21][22], (ii) to calibrate crop growth models [23,24], and (iii) to predict the yield of many crops for commercial purposes [25]. To date, few studies have focused on the estimation and prediction of perennial biomass crops traits using remote sensing technologies from satellite or UAV [26][27][28], and only two on Miscanthus [18,19]. Crop traits such as the plant height [29], the fraction of absorbed photosynthetically active radiation (fAPAR) [30], and the aboveground biomass [31] can be estimated from the VIs in combination with machine learning (ML) algorithms.…”

“…In particular, the use of a VIs' time series helped to derive descriptors of land surface phenology (LSP, i.e., the spatial and temporal development of the vegetated land surface) [41][42][43][44][45] such as the start of season (SOS), the peak of growing season, the stay-green duration (onset of senescence), the end of the season (EOS), and growing season length [46]. Among the available descriptors of LSP, the peak of a VI is one of the most important descriptors for crop yield prediction, such as the peak of NDVI [47] and EVI2 [17] for grain yield and the peak of GNDVI for biomass yields of perennial grass [26]. Yield prediction is, in many studies, theoretical, as it requires to fit the whole seasonal curve for deriving the peak of the time series of VIs.…”

“…To achieve these overarching objectives, UAV multispectral images and ground phenotypic data were collected at two locations within the same multi-environment trial: one in Italy and one in the UK. These data were analysed using: (i) the PROSAIL model to simulate crop spectral signatures in order to intercalibrate VIs of two different common multispectral sensors, (ii) the random forest (RF) algorithm to estimate crop traits using the VIs time series and to predict yield using the peak descriptor derived from the VIs time series, for the reliability it achieved in previous studies [17,26,47], and (iii) the generalized additive model (GAM) to derive the peak from a complete and partial time series of VIs.…”