Browsing by Browse by SEO 2020 "100503 Native and residual pastures"

Grasslands cover up to about 40% of the world's total land area (Suttie et al. 2005" Gibson 2009). These complex plant communities are generally comprised of a range of species including grasses, legumes, shrubs, and/or other forbs (Figure 17.1) (Allen et al. 2011), and are used primarily for grazing livestock such as cattle, sheep, and goats (Sanderson et al. 2004). The nomenclature associated with grasslands varies around the world and is largely influenced by the level of management needed to achieve some level of productive potential (Gibson 2009). For example, rangelands are generally comprised of indigenous vegetation that is sparingly grazed with little other management. In contrast, intensively managed pastures are likely to include improved species and agrochemical inputs, and are specifically devoted to the production of forage for harvest by either grazing or cutting. Furthermore, grazing is generally carefully managed to maintain satisfactory levels of plant persistence and animal productivity (Sindel 2006" Allen et al. 2011). For the purposes of this chapter, all plant communities that are grazed and have some level of management will be referred to as pastures.

Blady grass (Imperata cylindrica) is a major invasive weed that threatens agricultural systems, biodiversity and ecosystem function throughout tropical and sub-tropical to warm temperate regions around the world. It is able to reproduce both sexually via seeds and asexually via rhizomes, making it a difficult species to control or eradicate. It is adapted to a range of soil types, growing in poor acid soils with low fertility and organic matter, and is tolerant of fire and soil salinity. Once established, it is regarded as a strong competitor for nutrients, water and light. Although primarily a species of tropical and other warm environments, blady grass occurs in the New England region on the Northern Tablelands of New South Wales, Australia, in a cool temperature environment. Here, it occurs in patches, many of which appear to be expanding very little over time with few new patches being formed. The question arises as to how blady grass reproduces in this environment and what constrains its spread and distribution. However, there has been a lack of information about the ecology of blady grass in this region as well as more generally in Australia. Such information is critical for the design of effective future management programs. Therefore, this research focused on quantifying the size of the blady grass soil seedbank, assessing the longevity and germination of seeds, measuring flowering and growth responses to a range of environmental factors, and recording changes in rhizomes and their regrowth.

The soil seedbank is a vital mechanism for the establishment, persistence, and re-invasion of many weedy species. Through a germination study, the soil seedbank was explored within and outside blady grass patches in the New England region. The results showed no germinable seeds of blady grass to be present. Potential explanations for this absence of germinable seeds included the presence of seed dormancy, a lack of seed production in this cool temperate environment, and a short period of seed persistence under field conditions. Most seeds of other weed and pasture species were concentrated in the top 5 cm of the soil profile and there were more seeds at the edge and outside of blady grass patches than in the centre of the patch. These results indicate that blady grass has a strong competitive or allelopathic impact on the growth and re-production of pasture species.

In a series of laboratory and field experiments, the longevity and germination of seeds was found to vary according to storage and burial conditions. Seeds were not initially dormant and lost viability relatively rapidly (from 89% to 23% over 5 months) when stored at room temperature, while most seeds had either disappeared or were no longer able to germinate after 3 months of burial in the field. Seeds remained viable for a longer period of time when not buried. As a result, biological processes associated with soil moisture, such as germination and microbial decay, were thought to be responsible for the more rapid drop in seed viability when buried. The short life of seeds under field conditions is likely to constrain blady grass spread and persistence through the mechanism of seed dispersal. These results showed that regardless of their small size, light weight and ability to travel by wind over long distances, seeds may play a lesser role in the invasion of blady grass than rhizomes in cool temperate Australia.

Changes in temperature, day length, fertilizer, foliage management (cutting and burning), and water stress failed to stimulate flowering of blady grass, while several of the treatments had a large impact on the growth of the weed. The results showed that cooler temperatures, as experienced in the New England region, constrained growth relative to warmer temperatures as found in more tropical areas. In the high-altitude New England region, blady grass is likely to be most active in summer, and has mechanisms for obtaining light and responding well to increased soil fertility, suggesting it is likely to be highly competitive against summerdominant native pasture grasses. However, both cutting and burning reduced the growth of blady grass and may offer some potential for control of the weed. A lack of flowering and viable seed production may well be a contributing factor in the limited spread and distribution of blady grass.

The re-sprouting and growth of rhizome fragments depended on their size, colour, and presence of terminal meristematic tissue. The results showed that rhizome fragments with a greater number of nodes had more shoot and rhizome regrowth, while there was significant interaction between the effects of node number, rhizome colour, and presence of tips on regrowth. Rhizomes from different sources also varied in weight and diameter and this affected the degree of change they underwent following soil burial. While the capacity of rhizomes to contribute to the spread of blady grass is likely to vary, they are clearly responsible for the slow short-distance spread of blady grass patches in the New England region and may also have been responsible for longer distance spread when the weed was first introduced to the region.

As far as can be determined, the patches of blady grass in the New England region that were included in this study have been in the same places for many years. How the local populations of blady grass were initially established is unknown. However, these studies support the hypothesis that these high elevation cool-climate populations of blady grass are 'relic' populations, that seeds do not play a significant role in the persistence of this species in the region, and that there is little evidence for long distance expansion under the current climatic conditions and land management regime. Whether climate change in future alters this situation remains to be seen. This research provides important information about the ecology of blady grass in the New England region that can help inform the design of effective and sustainable management strategies for its control.

To establish an indirect method for estimating and partitioning pasture evapotranspiration, it is vital to develop a direct reference method that aligns with the required temporal and spatial resolution. An evapotranspiration chamber offers an effective solution as it is easy to deploy and operates at an appropriate measurement scale. In this study, we prepared and tested a closed hemispherical chamber for on-site measurements of evaporation and/ or transpiration. Advanced data monitoring and logging techniques were integrated to enhance the precision and reliability of direct in-field evapotranspiration measurements. During laboratory testing, vapor accumulation within the chamber was monitored to identify the best representative segment of the vapor accumulation curve. Results indicated that the instrument stabilizes its readings within 5 to 10 s post-deployment in laboratory settings. The subsequent 15 s produce stable readings that best represent actual vapor accumulation. The optimal fan speed, producing an air speed of 5.36 ms^{− 1} at the vicinity of the fan within the chamber, paired with a wire mesh above the vapor-producing surface, yielded the best results. The study established a calibration factor (C) of 1.02 based on the actual water loss and vapor accumulation readings from the sensors at this fan speed. Advanced data analytics were applied to derive the calibration factor and to calculate the values of evapotranspiration from the changing microclimate within the chamber. Direction towards complete automation and the limitations of the chamber in field measurement are provided. The chamber was also tested under field conditions, and the paper examines its practical application and necessary adjustments for field measurements.

Effective weed management in pastures is critical for maintaining the productivity of grazing land. Autonomous ground vehicles (AGVs) are increasingly being considered for weed localization and treatment in agricultural land. Weeds, however, can be difficult to distinguish from background plants, due to similarities in colour, shape and texture. While deep learning approaches can be used to solve the localization issue, they are computationally expensive, and require a large volume of training images in order to combat overfitting. In this paper we present a novel Extreme Learning Machine based network for segmenting weeds from the background pasture. The proposed method utilizes a combination of LBP, HOG and colour features, and is tested on four small datasets, achieving a high mean Intersection over Union of 87.1, 79.5, 81.6 and 87.6 for Bathurst burr, horehound, thistle and serrated tussock respectively.

Knowledge of crop evapotranspiration is crucial for irrigation decision making. An appropriate, user-friendly and time-efficient means of inferring such information is therefore essential. In this study, a closed hemispherical chamber was instrumented, calibrated and deployed in the field for measuring actual evapotranspiration of a vital pasture species, Tall Fescue (Festuca arundinacea). The pasture crop coefficient (K_c) was calculated from the measured instantaneous evapotranspiration and reference crop evapotranspiration (ET_o) for a range of growth stages. Also the relationship between K_c and Normalized Difference Vegetation Index (NDVI) as measured using an active optical sensor was established. Using the FAO dual crop coefficient approach and the hemispherical chamber, a technique for partitioning evapotranspiration components was developed. The components of evapotranspiration in terms of basal crop coefficient (K_cb) and soil evaporation coefficient (K_e) were expressed relative to canopy NDVI and Leaf Area Index (LAI). A theoretical model for estimating transpiration was also developed by scaling up stomatal conductance to canopy level in a controlled glasshouse environment. The model was validated against the measured transpiration.

Machine vision is an essential function of autonomous robotics, especially those which use visual mechanisms to navigate the complexities of the outside world. Agricultural environments such as pastures presents diverse and complex visual scenes containing flora, fauna and farm machinery. The ability to detect key objects within this environment greatly assist autonomous robotic navigation and operations. Operation of agricultural robotics such as quad-copters requires real-time (milliseconds) analysis of visual data to ensure performance. Current machine vision systems lack performance in processing time or detection accuracy within such environments. To address current machine vision limitations, this thesis presents a customised class of extreme learning machine algorithms intended for use within remote laptop or fog computing settings.

Colour was observed to often be a key visual cue for object detection in pasture scenes. The colour-feature extreme learning machine (CF-ELM) was introduced for image classification and was demonstrated to out-perform existing extreme learning machine (ELM) algorithms which did not use colour information for object detection. The CF-ELM utilised the small memory structure and fast training times of the ELM to develop a real-time classification algorithm with the added benefit of colour information. This allowed the CF-ELM to classify objects within pastoral scenarios in 0.06 to 0.18 seconds and between 82% to 96% accuracy. These scenarios included, weed detection, cattle detection and farm vehicle detection.

The multiple expert colour-feature extreme learning machine (MEC-ELM) was then introduced to both enhance detection and further reduce processing time. The MEC-ELM used multiple instances of the CF-ELM and a summed area table to produce real-time classification of objects within video frames. Object detection was performed on both quad-copter and surveillance camera video to demonstrate the wide utility of the MEC-ELM algorithm. Detection scenarios included stock monitoring, weed scouting and vehicle tracking with the MEC-ELM producing 78% to 95% precision and recall with processing times between 0.5 and 2.0 seconds per frame. Performance of the MEC-ELM was compared and contrasted to other suitable machine vision algorithms. The results in this research indicate that the MEC-ELM is a highly competitive algorithm suitable for real-time object detection in video, particularly for agricultural robotics applications.

Pasture grasses are an important feed-base for the livestock industry. The ability to identify and characterise pasture type, species composition and quantify the available biomass in fields is invaluable to the sustainability and profitability of our livestock industries. Pasture species composition, biomass and canopy structural variations have been measured at different spatial scales using varied optical methods/tools such as active optical sensors, as well as aerial and spaceborne passive optical sensors. At large spatial scale, optical satellite sensors are often used. However, the utilisation of these sensors is affected by cloudy weather conditions and the fact that they are really only responsive to photosynthetically active biomass.

Satellite-based Synthetic Aperture Radar (SAR) sensors, though not popular yet in pasture studies, have the potential to offset this limitation of optical sensing as the microwave energy emitted by these sensors penetrate clouds and that these wavelengths are also sensitive to volumetric scattering processes rendering them, potentially useful to situations involving significant, senesced, plant material (e.g. during drought) . This thesis predominantly focussed on Sentinel-1 C-band SAR with the whole research project comprising of three main components: (i) discrimination of pasture species based on C3 and C4 photosynthetic mechanisms and diversity of the botanical composition; (ii) estimating pasture biophysical variables with emphasis on aboveground biomass; and (iii) detection of surface heterogeneity due to selective grazing in pasture fields.

In discriminating pasture species into C3, C4 and mixed C3/C4 classes, Random Forest classification was used and the highest overall classification accuracy (86%) was achieved with a combination of grey-level co-occurrence textural metrics and polarimetric SAR metrics. Moreover, the combined strengths of Sentinel-1 SAR and Sentinel-2 optical information parameterised into K-Nearest Neighbours, Random Forest and Support Vector Machine classifiers, produced the highest overall accuracy estimates of 89%, 96% and 95%, respectively. Regression models such as the generalised additive model estimated pasture biomass with a root mean square error of prediction of 392 kg/ha over AGB estimates between 443–2642 kg/ha. Here pasture LAI ranged from 0.27 to 1.87, and sward height from 3.25 cm to 13.75 cm. In the final study, canopy heterogeneity due to selective grazing was detectable with the Sentinel-1 SAR. Particularly, the range estimates (dispersion measure) of the polarimetric scattering entropy produced the strongest, statistically significant, linear correlation with a metric of patchiness (R² =0.74). Altogether, this thesis has demonstrated that Sentinel-1 SAR on its own as well as when integrated with optical data, could be a useful tool providing data to aid in pasture management.

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.