Search

The determination of key phenological growth stages of banana plantations, such as flower emergence and plant establishment, is difficult due to the asynchronous growth habit of banana plants. Identifying phenological events assists growers in determining plant maturity, and harvest timing and guides the application of time-specific crop inputs. Currently, phenological monitoring requires repeated manual observations of individual plants’ growth stages, which is highly laborious, time-inefficient, and requires the handling and integration of large field-based data sets. The ability of growers to accurately forecast yield is also compounded by the asynchronous growth of banana plants. Satellite remote sensing has proved effective in monitoring spatial and temporal crop phenology in many broadacre crops. However, for banana crops, very high spatial and temporal resolution imagery is required to enable individual plant level monitoring. Unoccupied aerial vehicle (UAV)-based sensing technologies provide a cost-effective solution, with the potential to derive information on health, yield, and growth in a timely, consistent, and quantifiable manner. Our research explores the ability of UAV-derived data to track temporal phenological changes of individual banana plants from follower establishment to harvest. Individual plant crowns were delineated using object-based image analysis, with calculations of canopy height and canopy area producing strong correlations against corresponding ground-based measures of these parameters (R2 of 0.77 and 0.69 respectively). A temporal profile of canopy reflectance and plant morphology for 15 selected banana plants were derived from UAV-captured multispectral data over 21 UAV campaigns. The temporal profile was validated against ground-based determinations of key phenological growth stages. Derived measures of minimum plant height provided the strongest correlations to plant establishment and harvest, whilst interpolated maxima of normalised difference vegetation index (NDVI) best indicated flower emergence. For pre-harvest yield forecasting, the Enhanced Vegetation Index 2 provided the strongest relationship (R2 = 0.77) from imagery captured near flower emergence. These findings demonstrate that UAV-based multitemporal crop monitoring of individual banana plants can be used to determine key growing stages of banana plants and offer pre-harvest yield forecasts.

This research investigates the capability of field-based spectroscopy (350–2500 nm) for discriminating banana plants (Cavendish subgroup Williams) infested with spider mites from those unaffected. Spider mites are considered a major threat to agricultural production, as they occur on over 1000 plant species, including banana plant varieties. Plants were grown under a controlled glasshouse environment to remove any influence other than the imposed treatment (presence or absence of spider mites). The spectroradiometer measurements were undertaken with a leaf clip over three infestation events. From the resultant spectral data, various classification models were evaluated including partial least squares discriminant analysis (PLSDA), K-nearest neighbour, support vector machines and back propagation neural network. Wavelengths found to have a significant response to the presence of spider mites were extracted using competitive adaptive reweighted sampling (CARS), sub-window permutation analysis (SPA) and random frog (RF) and benchmarked using the classification models. CARS and SPA provided high detection success (86% prediction accuracy), with the wavelengths found to be significant corresponding with the red edge and near-infrared portions of the spectrum. As there is limited access to operational commercial hyperspectral imaging and additional complexity, a multispectral camera (Sequoia) was assessed for detecting spider mite impacts on banana plants. Simulated multispectral bands were able to provide a high level of detection accuracy (prediction accuracy of 82%) based on a PLSDA model, with the near-infrared band being most important, followed by the red edge, green and red bands. Multispectral vegetation indices were trialled using a simple threshold-based classification method using the green normalised difference vegetation index (GNDVI), which achieved 82% accuracy. This investigation determined that remote sensing approaches can provide an accurate method of detecting mite infestations, with multispectral sensors having the potential to provide a more commercially accessible means of detecting outbreaks.

This study presents the Segmented Colour Feature Extreme Learning Machine (SCF-ELM). The SCF-ELM is inspired by the Extreme Learning Machine (ELM) which is known for its rapid training and inference times. The ELM is therefore an ideal candidate for an ensemble learning algorithm. The Colour Feature Extreme Learning Machine (CF-ELM) is used in this study due to its additional ability to extract colour image features. The SCF-ELM is an ensemble learner that utilizes feature mapping via k-means clustering, a decision matrix and majority voting. It has been evaluated on a range of challenging agricultural object classification scenarios including weed, livestock and machinery detection. SCF-ELM model performance results were excellent both in terms of detection, 90 to 99% accuracy, and also inference times, around 0.01(s) per image. The SCF-ELM was able to compete or improve upon established algorithms in its class, indicating its potential for remote computing applications in agriculture.

Unoccupied aerial vehicles (UAVs) have become increasingly commonplace in aiding planning and management decisions in agricultural and horticultural crop production. The ability of UAV-based sensing technologies to provide high spatial (

Nitrogen (N) is the most important fertiliser element determining the productivity of wheat. N nutrition is known to affect the level of stripe rust infection, with higher N associated with increased disease severity. Stripe rust, caused by Puccinia striiformis f. sp. tritici, is a major yield-limiting disease of wheat in Australia. This paper describes experiments designed to investigate the agronomic response to the interaction of various levels of N application and stripe rust severity in wheat varieties differing in response. Experimental plots were established in crop seasons 2006 and 2007 on the Liverpool Plains of northern NSW, Australia. Yield, biomass, grain protein content (GPC) and harvest index (HI) data were recorded. Increased rates of N increased the severity of stripe rust during grain filling. N application also increased yield and GPC in all varieties in both years. Stripe rust reduced the yield of the rust-susceptible wheat varieties, and GPC and proportion of added N recovered in the grain were also reduced in one year but not the other. It was evident from our experiment that stripe rust caused yield loss accompanied by either no change or reduction in GPC, indicating that the total amount of N entering the grain was reduced by stripe rust. The effects of stripe rust on N yield are most likely associated with reduced uptake of N during grain filling.

Studies estimating canopy volume are mostly based on laborious and time-consuming field measurements; hence, there is a need for easier and convenient means of estimation. Accordingly, this study investigated the use of remotely sensed data (WorldView-2 and LiDAR) for estimating tree height, canopy height and crown diameter, which were then used to infer the canopy volume of remnant eucalypt trees at the Newholme/Kirby ‘SMART’ farm in north-east New South Wales. A regression model was developed with field measurements, which was then applied to remote-sensing-based measurements. LiDAR estimates of tree dimensions were generally lower than the field measurements (e.g., 6.5% for tree height) although some of the parameters (such as tree height) may also be overestimated by the clinometer/rangefinder protocols used. The WorldView-2 results showed both crown projected area and crown diameter to be strongly correlated to canopy volume, and that crown diameter yielded better results (Root Mean Square Error RMSE 31%) than crown projected area (RMSE 42%). Although the better performance of LiDAR in the vertical dimension cannot be dismissed, as suggested by results obtained from this study and also similar studies conducted with LiDAR data for tree parameter measurements, the high price and complexity associated with the acquisition and processing of LiDAR datasets mean that the technology is beyond the reach of many applications. Therefore, given the need for easier and convenient means of tree parameters estimation, this study filled a gap and successfully used 2D multispectral WorldView-2 data for 3D canopy volume estimation with satisfactory results compared to LiDAR-based estimation. The result obtained from this study highlights the usefulness of high resolution data for canopy volume estimations at different locations as a possible alternative to existing methods.

The total biomass of a tall fescue (Festuca arundinacea var. Fletcher) pasture was assessed by using a vehicle mounted light detection and ranging (LiDAR) unit to derive canopy height and an active optical reflectance sensor to determine the spectro-optical reflectance index, normalized difference vegetation index (NDVI). In a random plot design, measurements of NDVI and pasture height were combined to estimate biomass with a root mean square error of prediction (RMSEP) equal to ±455.28 kg green dry matter (GDM)/ha, over a range of 286 kg to 3933 kg GDM/ha. The combination of NDVI and height measurements were observed to be more accurate in assessing total biomass than just the NDVI (RMSEP ± 846.51 kg/ha) and height (RMSEP ± 708.13 kg/ha). Based on the results of the study it was concluded the use of combined LiDAR and active optical reflectance sensors can help unlock the complex interrelationship between green fraction and biomass in swards containing both green and senescent material.

Modern soil mapping is characterised by the need to interpolate point referenced (geostatistical) observations and the availability of large numbers of environmental characteristics for consideration as covariates to aid this interpolation. Modelling tasks of this nature also occur in other fields such as biogeography and environmental science. This analysis employs the Least Angle Regression (LAR) algorithm for fitting Least Absolute Shrinkage and Selection Operator (LASSO) penalized Multiple Linear Regressions models. This analysis demonstrates the efficiency of the LAR algorithm at selecting covariates to aid the interpolation of geostatistical soil carbon observations. Where an exhaustive search of the models that could be constructed from 800 potential covariate terms and 60 observations would be prohibitively demanding, LASSO variable selection is accomplished with trivial computational investment.