Massey Documents by Type

Permanent URI for this communityhttps://mro.massey.ac.nz/handle/10179/294

Browse

Filters

2020 - 20242

Settings

Subject: search.filters.subject.300402 Agro-ecosystem function and prediction

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Predicting nutritional content of native forage feed using ATR-FTIR and NIR chemometrics : a thesis presented in partial fulfilment of the requirements for the degree of Master of Science in Nanoscience at Massey University, Manawatū, New Zealand
    (Massey University, 2024) Coleman, Gregory Maurice
    Near infrared (NIR) reflectance spectroscopy has historically dominated the agriculture industry in the prediction of the nutritional content of pasture and forage in New Zealand. This study investigates using an alternative infrared reflectance technique in the mid infrared (MIR) region, Attenuated Total Reflectance Fourier Transform Infrared (ATR-FTIR) spectroscopy, and compares it to NIR, for the prediction of the chemical composition of native forage feed for sheep. Six native forage species and one non-native control species comprised 181 samples, which were recorded with both NIR and ATR-FTIR spectroscopy. Spectral pre-treatment was applied to all spectra in the form of a first-order Savitzky-Golay (SG) smoothening filter. Prediction of nutritional content for six analytes was achieved for both IR methods, using Principal Component Analysis (PCA) and a Partial Least Squares (PLS) regression model. The predictive ability of ATR-FTIR and NIR models was evaluated using the coefficient of determination (R²), Root Mean Square Error of Cross Validation (RMSECV), and Relative Performance Deviation (RPD). NIR had superior R2 and RPD, and similar RMSECV to ATR-FTIR for all analyte predictions. The best models were crude protein (CP) for NIR (R² : 0.95, RPD: 5.58) and metabolisable energy (ME) for FTIR (R² :0.79, RPD: 3.52). Post prediction statistics were also investigated for FTIR and NIR, finding that a ‘one size fits all’ blanket model for all species and tissue types was sufficient for quality prediction of CP, ME, and neutral detergent fiber (NDF) for native shrub species. These models suggested that ME and NDF predictions were similar between NIR and FTIR but NIR was superior to FTIR for CP. Overall, this study demonstrates the considerable potential of ATR-FTIR for quality nutritional content predictions, that are comparable to NIR.
  • Thumbnail Image
    Item
    Predicting spatiotemporal yield variability to aid arable precision agriculture in New Zealand : a case study of maize-grain crop production in the Waikato region : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Agriculture and Horticulture at Massey University, Palmerston North, New Zealand
    (Massey University, 2020) Jiang, Guopeng
    Precision agriculture attempts to manage within-field spatial variability by applying suitable inputs at the appropriate time, place, and amount. To achieve this, delineation of field-specific management zones (MZs), representing significantly different yield potentials are required. To date, the effectiveness of utilising MZs in New Zealand has potentially been limited due to a lack of emphasis on the interactions between spatiotemporal factors such as soil texture, crop yield, and rainfall. To fill this research gap, this thesis aims to improve the process of delineating MZs by modelling spatiotemporal interactions between spatial crop yield and other complementary factors. Data was collected from five non-irrigated field sites in the Waikato region, based on the availability of several years of maize harvest data. To remove potential yield measurement errors and improve the accuracy of spatial interpolation for yield mapping, a customised filtering algorithm was developed. A supervised machine-learning approach for predicting spatial yield was then developed using several prediction models (stepwise multiple linear regression, feedforward neural network, CART decision tree, random forest, Cubist regression, and XGBoost). To provide insights into managing spatiotemporal yield variability, predictor importance analysis was conducted to identify important yield predictors. The spatial filtering method reduced the root mean squared errors of kriging interpolation for all available years (2014, 2015, 2017 and 2018) in a tested site, suggesting that the method developed in R programme was effective for improving the accuracy of the yield maps. For predicting spatial yield, random forest produced the highest prediction accuracies (R² = 0.08 - 0.50), followed by XGBoost (R² = 0.06 - 0.39). Temporal variables (solar radiation, growing degree days (GDD) and rainfall) were proven to be salient yield predictors. This research demonstrates the viability of these models to predict subfield spatial yield, using input data that is inexpensive and readily available to arable farms in New Zealand. The novel approach employed by this thesis may provide opportunities to improve arable farming input-use efficiency and reduce its environmental impact.