Abstract
Abstract. Pasture biomass information is essential to monitor forage resources in grazed areas, as well as to support grazing management decisions. The increasing temporal and spatial resolutions offered by the new generation of orbital platforms, such as Planet CubeSat satellites, have improved the capability of monitoring pasture biomass using remotely-sensed data. In a preliminary study, we investigated the potential of spectral variables derived from PlanetScope imagery to predict pasture biomass in an area of Integrated Crop-Livestock System (ICLS) in Brazil. Satellite and field data were collected during the same period (May–August 2019) for calibration and validation of the relation between predictor variables and pasture biomass using the Random Forest (RF) regression algorithm. We used as predictor variables 24 vegetation indices derived from PlanetScope imagery, as well as the four PlanetScope bands, and field management information. Pasture biomass ranged from approximately 24 to 656 g m−2, with a coefficient of variation of 54.96%. Near Infrared Green Simple Ratio (NIR/Green), Green Leaf Algorithm (GLA) vegetation indices and days after sowing (DAS) are among the most important variables as measured by the RF Variable Importance metric in the best RF model predicting pasture biomass, which resulted in Root Mean Square Error (RMSE) of 52.04 g m−2 (32.75%). Accurate estimates of pasture biomass using spectral variables derived from PlanetScope imagery are promising, providing new insights into the opportunities and limitations related to the use of PlanetScope imagery for pasture monitoring.
Highlights
Monitoring pasture biomass is fundamental to understand the spatio-temporal dynamics of forage resources in grazed areas, and to support grazing management decisions (Andersson et al, 2017)
In this context, using the Random Forest (RF) machine learning algorithm, we investigated the potential of spectral variables derived from PlanetScope imagery associated with field management information to predict pasture biomass in an area of Integrated Crop-Livestock System (ICLS) in the western region of São Paulo State, Brazil
Our results demonstrated the capacity of spectral variables derived from PlanetScope imagery to monitor pasture biomass at high spatial (~3 m) and temporal (~daily) resolution
Summary
Monitoring pasture biomass is fundamental to understand the spatio-temporal dynamics of forage resources in grazed areas, and to support grazing management decisions (Andersson et al, 2017). The increasing temporal and spatial resolution offered by the new generation of satellites, so-called constellations of nanosatellites, such as Planet CubeSat satellites, may overcome this spatio-temporal limitation by using multiple small satellites to collect global high spatial resolution data with very high temporal resolution These nano-satellites may advance the field of crop monitoring by offering an unprecedented combination of high temporal (daily) and high spatial (3 meters) resolutions imagery (Planet Team, 2019). Machine learning algorithms have been increasingly used for a wide range of tasks including pasture monitoring (Parente et al, 2017, Liu et al, 2019, Wang et al, 2019) In this context, using the Random Forest (RF) machine learning algorithm, we investigated the potential of spectral variables (spectral bands and vegetation indices) derived from PlanetScope imagery associated with field management information to predict pasture biomass in an area of Integrated Crop-Livestock System (ICLS) in the western region of São Paulo State, Brazil
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have