In-field hyperspectral proximal sensing for estimating quality parameters of mixed pasture

Pullanagari, Reddy; Yule, Ian; Tuohy, M. P.; Hedley, M. J.; Dynes, Robyn; King, W. M.

doi:10.1007/s11119-011-9251-4

Cited by 103 publications

(103 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, a hill country farm was imaged with an airborne hyperspectral system which produced accurate estimates for CP (RPD CV = 2.23) and ME (RPD CV = 2.25) of heterogeneous mixed pasture. The successful application of this technology in pasture quality is not surprising, as pointed out by previous studies [14,16,19,39]; however, the approach used in this study improved the prediction results by integrating the hyperspectral and environmental data-combined machine-learning algorithms. Such knowledge of the landscape could inform pasture and herd management decisions to improve animal production and assist in land stewardship efforts.…”

Section: Discussionmentioning

confidence: 62%

See 1 more Smart Citation

Integrating Airborne Hyperspectral, Topographic, and Soil Data for Estimating Pasture Quality Using Recursive Feature Elimination with Random Forest Regression

2018

View full text Add to dashboard Cite

Accurate and efficient monitoring of pasture quality on hill country farm systems is crucial for pasture management and optimizing production. Hyperspectral imaging is a promising tool for mapping a wide range of biophysical and biochemical properties of vegetation from leaf to canopy scale. In this study, the potential of high spatial resolution and airborne hyperspectral imaging for predicting crude protein (CP) and metabolizable energy (ME) in heterogeneous hill country farm was investigated. Regression models were developed between measured pasture quality values and hyperspectral data using random forest regression (RF). The results proved that pasture quality could be predicted with hyperspectral data alone; however, accuracy was improved after combining the hyperspectral data with environmental data (elevation, slope angle, slope aspect, and soil type) where the prediction accuracy for CP was R 2 CV (cross-validated coefficient of determination) = 0.70, RMSE CV (cross-validated root mean square error) = 2.06%, RPD CV (cross-validated ratio to prediction deviation) = 1.82 and ME: R 2 CV = 0.75, RMSE CV = 0.65 MJ/kg DM, RPD CV = 2.11. Interestingly, the accuracy was further out-performed by considering important hyperspectral and environmental variables using RF combined with recursive feature elimination (RFE) (CP: R 2 CV = 0.80, RMSE CV = 1.68%, RPD CV = 2.23; ME: R 2 CV = 0.78, RMSE CV = 0.61 MJ/kg DM, RPD CV = 2.19). Similar performance trends were noticed with validation data. Utilizing the best model, spatial pasture quality maps were created across the farm. Overall, this study showed the potential of airborne hyperspectral data for producing accurate pasture quality maps, which will help farm managers to optimize decisions to improve environmental and economic benefits.

show abstract

Section: Discussionmentioning

confidence: 62%

“…SD(y) refers to standard deviation of measured y. Models with RPD ≥ 2 predict well with reliable estimates [14]. Pasture quality maps were generated using the best model.…”

Section: Introductionmentioning

confidence: 99%

Integrating Airborne Hyperspectral, Topographic, and Soil Data for Estimating Pasture Quality Using Recursive Feature Elimination with Random Forest Regression

2018

View full text Add to dashboard Cite

show abstract

“…Therefore, combining both, HS and in-situ, is highly potential for research. In fact, several successful applications of the combination of airborne HS sensor and in-situ measurements to assess the chemical composition of pasture quality have been reported [28][29][30][31][32][33][34][35][36][37][38]. For example, Schellberg et al [28] suggested that a sensor with high spectral and spatial resolution is a basic requirement for high-precision estimation of pasture quality.…”

Section: Introductionmentioning

confidence: 99%

“…For example, Schellberg et al [28] suggested that a sensor with high spectral and spatial resolution is a basic requirement for high-precision estimation of pasture quality. Pullanagari et al [29,30] showed the ability of HS sensors to predict pasture quality parameters in research carried out on New Zealand dairy pastures. Sanches [31] and Mutanga and Skidmore [32,33] found relationships between nitrogen concentration and in-situ spectral reflectance of the vegetation.…”

Section: Introductionmentioning

confidence: 99%

Spectral Slope as an Indicator of Pasture Quality

et al. 2014

View full text Add to dashboard Cite

Abstract:In this study, we develop a spectral method for assessment of pasture quality based only on the spectral information obtained with a small number of wavelengths. First, differences in spectral behavior were identified across the near infrared-shortwave infrared spectral range that were indicative of changes in chemical properties. Then, slopes across different spectral ranges were calculated and correlated with the changes in crude protein (CP), neutral detergent fiber (NDF) and metabolic energy concentration (MEC). Finally, partial least squares (PLS) regression analysis was applied to identify the optimal spectral ranges for accurate assessment of CP, NDF and MEC. Six spectral domains and a set of slope criteria for real-time evaluation of pasture quality were suggested. The evaluation of three level categories (low, medium, high) for these three parameters showed a success rate of: 73%-96% for CP, 72%-87% for NDF and 60%-85% for MEC. Moreover, only one spectral range, 1748-1764 nm, was needed to provide a good estimation of CP, NDF and MEC. Importantly, five of the six selected spectral regions were not affected by water absorbance. With some OPEN ACCESSRemote Sens. 2015, 7 257 modifications, this rationale can be applied to further analyses of pasture quality from airborne sensors.

show abstract

“…Protein has also been detected in other types of vegetation [35][36][37]. However, all of these studies made use of the spectrometer's entire spectral range and models were calibrated using fresh vegetation datasets.…”

mentioning

confidence: 99%

Estimating Pasture Quality of Fresh Vegetation Based on Spectral Slope of Mixed Data of Dry and Fresh Vegetation—Method Development

et al. 2015

View full text Add to dashboard Cite

Abstract:The main objective of the present study was to apply a slope-based spectral method to both dry and fresh pasture vegetation. Differences in eight spectral ranges were identified across the near infrared-shortwave infrared (NIR-SWIR) that were indicative of changes in chemical properties. Slopes across these ranges were calculated and a partial least squares (PLS) analytical model was constructed for the slopes vs. crude protein (CP) and neutral detergent fiber (NDF) contents. Different datasets with different numbers of fresh/dry samples were constructed to predict CP and NDF contents. When using a mixed-sample dataset with dry-to-fresh ratios of 85%:15% and 75%:25%, the correlations of CP (R 2 = 0.95, in both) and NDF (R 2 = 0.84 and 0.82, respectively) were almost as high as when using only dry samples (0.97 and 0.85, respectively). Furthermore, satisfactory correlations were obtained with a dry-to-fresh ratio of 50%:50% for CP (R 2 = 0.92). The OPEN ACCESSRemote Sens. 2015, 7 8046 results of our study are especially encouraging because CP and NDF contents could be predicted even though some of the selected spectral regions were directly affected by atmospheric water vapor or water in the plants.

show abstract

In-field hyperspectral proximal sensing for estimating quality parameters of mixed pasture

Cited by 103 publications

References 34 publications

Integrating Airborne Hyperspectral, Topographic, and Soil Data for Estimating Pasture Quality Using Recursive Feature Elimination with Random Forest Regression

Integrating Airborne Hyperspectral, Topographic, and Soil Data for Estimating Pasture Quality Using Recursive Feature Elimination with Random Forest Regression

Spectral Slope as an Indicator of Pasture Quality

Estimating Pasture Quality of Fresh Vegetation Based on Spectral Slope of Mixed Data of Dry and Fresh Vegetation—Method Development

Contact Info

Product

Resources

About