Estimation of biomass and nutritive value of grass and clover mixtures by analyzing spectral and crop height data using chemometric methods

Sun, Sashuang; Zuo, Zhuang; Yue, Wenjun; Morel, Julien; Parsons, David; Liu, Jian; Peng, Junxiang; Cen, Haiyan; He, Yong; Shi, Jianxin; Li, Xiaolong; Zhou, Zhenjiang

doi:10.1016/j.compag.2021.106571

Cited by 10 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Interestingly, the range of accuracies obtained in both the current study and Sun et al. (2021) are similar, although the spectral range of the YNS is much smaller, and the spectral sampling much coarser, compared with what is obtained from a FieldSpec 4. The authors reported that, of the different spectral regions measured by the FieldSpec 4, the most important ones for CP, IVTD, NDF, and NDFD were all located in the visible range.…”

Section: Resultssupporting

confidence: 76%

“…More generally, Chlingaryan et al (2018) reported that the relative performances of MR (e.g., PLS, SVM, RF, and artificial neural networks) for N estimations are largely changing between studies; that is, thus far, there is no algorithm that is expected to systematically stand out for N (and, by extension, CP) estimations. Interestingly, the range of accuracies obtained in both the current study and Sun et al (2021) are similar, although the spectral range of the YNS is much smaller, and the spectral sampling much coarser, compared with what is obtained from a Field-Spec 4. The authors reported that, of the different spectral regions measured by the FieldSpec 4, the most important ones for CP, IVTD, NDF, and NDFD were all located in the visible range.…”

Section: Resultssupporting

confidence: 61%

“…Although SVM tended to yield the highest accuracies for calibration, validation results suggest that performances are balanced between PLS and SVM. Sun et al (2021) used Field-Spec 4 data from a subset of the current dataset showed that PLS was more robust than SVM for estimating various quality traits. However, opposite results were obtained by Zhou et al (2019), where the authors showed that SVM systematically outperformed PLS to estimate dry matter yield and CP content of leys from YNS spectral data.…”

Section: Resultsmentioning

confidence: 99%

“…Sun et al. (2021) used FieldSpec 4 data from a subset of the current dataset and showed that PLS was more robust than SVM for estimating various quality traits. However, opposite results were obtained by Zhou et al.…”

Section: Resultsmentioning

confidence: 99%

See 3 more Smart Citations

Estimation of the nutritive value of grasslands with the Yara N‐sensor field spectrometer

Morel

Zhou

Monteiro

et al. 2022

The Plant Phenome Journal

Self Cite

View full text Add to dashboard Cite

Forage crops are a cornerstone of the agricultural industry in Nordic countries. Economic and ecological performances are directly linked to adapted farming practices, which require timed and precise information on the nutritive value of the forage. Field spectrometers could offer an interesting alternative to time‐consuming laboratory measurements, as they provide near real time information. We used a handheld version of a field spectrometer already commercialized for cereal adjustable rate fertilization, to evaluate its potential for grassland nutritive quality estimation. Spectral data and samples were acquired over experimental fields and plots in four locations in Northern Sweden; samples were analyzed using wet chemistry to determine the crude protein concentration, the in vitro true digestibility, the neutral detergent fiber and the neutral detergent fiber digestibility. Grid‐based adjusted spectral indices, partial least squares, random forest and support vector machine were tested to link the spectral data to the nutritive traits. Partial least squares and support vector machine outperformed the adjusted spectral indices and random forest. Best predictions were obtained with partial least squares for in vitro true digestibility and neutral detergent fiber (R2 of 0.64 and 0.78 and normalized root mean square error [nRMSE] of 2.1 and 8.0%, respectively) and with support vector machine for crude protein and neutral detergent fiber digestibility (R2 of 0.49 and 0.65 and nRMSE of 13.0 and 3.8%, respectively). These results suggests that there is a potential for this affordable, industry‐ready spectrometer to be used as a practical farming tool, although more comprehensive datasets are needed to ensure that robust models are developed.

show abstract

Section: Resultssupporting

confidence: 76%

Section: Resultssupporting

confidence: 61%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Estimation of the nutritive value of grasslands with the Yara N‐sensor field spectrometer

Morel

Zhou

Monteiro

et al. 2022

The Plant Phenome Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…När dessa spektra används med lämpliga matematiska verktyg kan de härledas till relevant information för praktiska ändamål. Till exempel har flera studier redan bekräftat potentialen hos fältspektrometrar för att uppskatta vallars kvalitet (Morel et al, 2022;Parsons et al, 2020;Sun et al, 2021). Dessa studier utfördes dock mestadels på ett begränsat geografiskt område, vilket gjorde det svårt att validera robustheten hos de spektrometerbaserade modellerna.…”

Section: Introduktionunclassified

Vallkonferens 2023

Bernes¹

2023

Report From the Department of Crop Production Ecology (VPE)

View full text Add to dashboard Cite

Rapporten presenterar resultat från aktuell forskning kring såväl vallens odling och konservering som dess utnyttjande hos olika djurslag samt som protein-och energiråvara. Odlingsmaterialets produktion och näringsvärde behandlas, olika strategier och metoder för bete presenteras och vallens betydelse för klimatet diskuteras. Konferensen arrangeras av institutionerna HUV och VPE vid SLU i samarbete med Växa, Hushållningssällskapet, Greppa Näringen via Jordbruksverket och LRF.

show abstract

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

Estimation of biomass and nutritive value of grass and clover mixtures by analyzing spectral and crop height data using chemometric methods

Cited by 10 publications

References 27 publications

Estimation of the nutritive value of grasslands with the Yara N‐sensor field spectrometer

Estimation of the nutritive value of grasslands with the Yara N‐sensor field spectrometer

Vallkonferens 2023

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

Contact Info

Product

Resources

About