Perennial ryegrass biomass retrieval through multispectral UAV data

Alckmin, Gustavo Togeirode; Lucieer, Arko; Rawnsley, RP; Kooistra, L.

doi:10.1016/j.compag.2021.106574

Cited by 14 publications

(13 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Geipel et al (2021) investigated the potential of a hyperspectral camera on board of UAV to estimate fresh and dry forage mass in two different locations and achieved a high prediction performance (R 2 = 0.84, RMSE = 2358 kg ha −1 ; R 2 = 0.80, RMSE = 555 kg ha −1 respectively). Alckmin et al (2022) demonstrated the potential to predict perennial ryegrass (Lolium perenne) biomass accurately (RMSE = 397 kg DM ha −1 ) by the multispectral camera after post-processing imagery following a new radiometric calibration pipeline. Studies by Lussem et al (2019) and Batistoti et al (2019) deployed low-cost sensors (RGB) on board UAV to estimate forage biomass in temperate and tropical grasslands, respectively.…”

Section: Stocking Rate Adjustmentsmentioning

confidence: 99%

“…Alckmin et al. (2022) demonstrated the potential to predict perennial ryegrass ( Lolium perenne ) biomass accurately (RMSE = 397 kg DM ha −1 ) by the multispectral camera after post‐processing imagery following a new radiometric calibration pipeline. Studies by Lussem et al.…”

Section: Applications In Grazingland Managementmentioning

confidence: 99%

“…In this sense, some studies have been conducted recently to develop and calibrate models to predict the biophysical parameters of grazinglands on RS data. In addition, the application of machine learning algorithms offers tools for optimizing decision‐making related to grassland management (Alckmin et al., 2022; Batistoti et al., 2019; Bretas et al., 2021; De Rosa et al., 2021; Freitas et al., 2022; Lugassi et al., 2019; Lussem et al., 2019; Sun et al., 2022; Tiscornia et al., 2019; Wijesingha et al., 2020).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Precision livestock farming applied to grazingland monitoring and management—A review

et al. 2023

View full text Add to dashboard Cite

To meet the expected demand for food while protecting animal welfare, environmental sustainability, and profitability, animal production efficiency must improve. Improvements in grazinglands management techniques can impact livestock production efficiency. The current stage of artificial intelligence development, mainly machine learning techniques, remote sensing (RS), and precision agriculture technologies, automatizes data collection and raises the monitoring capacity to support on‐farm decision‐making. This literature review presents current developments in precision livestock farming (PLF) applied to grazinglands monitoring and management, demonstrates some knowledge gaps, and discusses potential solutions of grazinglands management issues. Although the implementation of precision technologies in grazing systems is advancing rapidly, challenges, such as lack of reliable reference data and low variability of datasets used to calibrate models, are examples of constraints to be addressed in future studies. More effort in terms of relationship strengthening between farmers and researchers, benefits elucidation, cooperation among professionals with different expertise, and software or app development must be directed to make the knowledge accessible and largely implemented in field conditions.

show abstract

Section: Stocking Rate Adjustmentsmentioning

confidence: 99%

Section: Applications In Grazingland Managementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Precision livestock farming applied to grazingland monitoring and management—A review

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In a purely spectral approach, Togeiro de Alckmin et al [116] achieved an RMSE of 397-464 kg ha −1 depending on the modeling algorithm for the DMY estimation using a small MS camera (Parrot Sequoia) in a two-year study. Oliveira et al [59] employed a similar sensor setup as [61] and reported an RMSE of 389 kg ha −1 for the combination of CH fused with narrowband indices and single bands from an HS camera modeled by RF regression.…”

Section: Impact Of Combining Structural and Spectral Data On Predicti...mentioning

confidence: 99%

Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning

et al. 2022

View full text Add to dashboard Cite

Precise and timely information on biomass yield and nitrogen uptake in intensively managed grasslands are essential for sustainable management decisions. Imaging sensors mounted on unmanned aerial vehicles (UAVs) along with photogrammetric structure-from-motion processing can provide timely data on crop traits rapidly and non-destructively with a high spatial resolution. The aim of this multi-temporal field study is to estimate aboveground dry matter yield (DMY), nitrogen concentration (N%) and uptake (Nup) of temperate grasslands from UAV-based image data using machine learning (ML) algorithms. The study is based on a two-year dataset from an experimental grassland trial. The experimental setup regarding climate conditions, N fertilizer treatments and slope yielded substantial variations in the dataset, covering a considerable amount of naturally occurring differences in the biomass and N status of grasslands in temperate regions with similar management strategies. Linear regression models and three ML algorithms, namely, random forest (RF), support vector machine (SVM), and partial least squares (PLS) regression were compared with and without a combination of both structural (sward height; SH) and spectral (vegetation indices and single bands) features. Prediction accuracy was quantified using a 10-fold 5-repeat cross-validation (CV) procedure. The results show a significant improvement of prediction accuracy when all structural and spectral features are combined, regardless of the algorithm. The PLS models were outperformed by their respective RF and SVM counterparts. At best, DMY was predicted with a median RMSECV of 197 kg ha−1, N% with a median RMSECV of 0.32%, and Nup with a median RMSECV of 7 kg ha−1. Furthermore, computationally less expensive models incorporating, e.g., only the single multispectral camera bands and SH metrics, or selected features based on variable importance achieved comparable results to the overall best models.

show abstract

“…For instance, frameworks currently exist to interpret model performance and uncertainties and to simulate C fluxes in cropping and grassland systems at a variety of distant and contrasting sites (Sándor et al, 2020). Also, the model does not currently Recent research has also underlined that combining unmanned aerial systems (UAS) with multispectral cameras can allow for an optimal observation system capable of deploying machine learning algorithms for near real-time mapping of perennial ryegrass dry matter (Togeirode Alckmin et al, 2022). As such technological solutions and efforts progress, they will have the potential to provide more data in an accurate and automated way with regards to, for instance, grass biomass assessments.…”

Section: Limitations and Future Developments Of The Toolmentioning

confidence: 99%

Translating and applying a simulation model to enhance understanding of grassland management

Giannitsopoulos

Burgess

Bell

et al. 2022

Grass and Forage Science

View full text Add to dashboard Cite

Each new generation of grassland managers could benefit from an improved understanding of how modification of nitrogen application and harvest dates in response to different weather and soil conditions will affect grass yields and quality.The purpose of this study was to develop a freely available grass yield simulation model, validated for England and Wales, and to examine its strengths and weaknesses as a teaching tool for improving grass management. The model, called LINGRA-N-Plus, was implemented in a Microsoft Excel spreadsheet and iteratively evaluated by students and practitioners (farmers, consultants, and researchers) in a series of workshops

show abstract

Perennial ryegrass biomass retrieval through multispectral UAV data

Cited by 14 publications

References 38 publications

Precision livestock farming applied to grazingland monitoring and management—A review

Precision livestock farming applied to grazingland monitoring and management—A review

Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning

Translating and applying a simulation model to enhance understanding of grassland management

Contact Info

Product

Resources

About