Detecting the attributes of a wheat crop using digital imagery acquired from a low-altitude platform

A low-altitude platform utilising a 1.8-m diameter tethered helium balloon was used to position a multispectral sensor, consisting of two digital cameras, above a fertiliser trial plot where wheat (Triticum spp.) was being grown. Located in Cecil Plains, Queensland, Australia, the plot was a long-term fertiliser trial being conducted by a fertiliser company to monitor the response of crops to various levels of nutrition. The different levels of nutrition were achieved by varying nitrogen application rates between 0 and 120 units of N at 40 unit increments. Each plot had received the same application rate for 10 years. Colour and near-infrared images were acquired that captured the whole 2 ha plot. These images were examined and relationships sought between the captured digital information and the crop parameters imaged at anthesis and the at-harvest quality and quantity parameters. The statistical analysis techniques used were correlation analysis, discriminant analysis and partial least squares regression. A high correlation was found between the image and yield (R2 = 0.91) and a moderate correlation between the image and grain protein content (R2 = 0.66). The utility of the system could be extended by choosing a more mobile platform. This would increase the potential for the system to be used to diagnose the causes of the variability and allow remediation, and/or to segregate the crop at harvest to meet certain quality parameters.

Estimating crop area using seasonal time series of enhanced vegetation index from MODIS satellite imagery

Cereal grain is one of the main export commodities of Australian agriculture. Over the past decade, crop yield forecasts for wheat and sorghum have shown appreciable utility for industry planning at shire, state, and national scales. There is now an increasing drive from industry for more accurate and cost-effective crop production forecasts. In order to generate production estimates, accurate crop area estimates are needed by the end of the cropping season. Multivariate methods for analysing remotely sensed Enhanced Vegetation Index (EVI) from 16-day Moderate Resolution Imaging Spectroradiometer (MODIS) satellite imagery within the cropping period (i.e. April-November) were investigated to estimate crop area for wheat, barley, chickpea, and total winter cropped area for a case study region in NE Australia. Each pixel classification method was trained on ground truth data collected from the study region. Three approaches to pixel classification were examined: (i) cluster analysis of trajectories of EVI values from consecutive multi-date imagery during the crop growth period; (ii) harmonic analysis of the time series (HANTS) of the EVI values; and (iii) principal component analysis (PCA) of the time series of EVI values. Images classified using these three approaches were compared with each other, and with a classification based on the single MODIS image taken at peak EVI. Imagery for the 2003 and 2004 seasons was used to assess the ability of the methods to determine wheat, barley, chickpea, and total cropped area estimates. The accuracy at pixel scale was determined by the percent correct classification metric by contrasting all pixel scale samples with independent pixel observations. At a shire level, aggregated total crop area estimates were compared with surveyed estimates. All multi-temporal methods showed significant overall capability to estimate total winter crop area. There was high accuracy at pixel scale (>98% correct classification) for identifying overall winter cropping. However, discrimination among crops was less accurate. Although the use of single-date EVI data produced high accuracy for estimates of wheat area at shire scale, the result contradicted the poor pixel-scale accuracy associated with this approach, due to fortuitous compensating errors. Further studies are needed to extrapolate the multi-temporal approaches to other geographical areas and to improve the lead time for deriving cropped-area estimates before harvest.

High resolution satellite imagery and GPS collars can help assist in the assessment of patch selection by grazing cattle in semi-arid savannas.

The selection of different patch types for grazing by cattle in tropical savannas is well documented. Advances in high resolution satellite imagery and computing power now allow us to identify patch types over an entire paddock, combined with GPS collars as a non instrusive method of capturing positional data, an accurate and comprehensive picture of landscape use by cattle can be quantified.

Patch selection by cattle can be quantified using satellite imagery and GPS in extensive, semi-arid savannas.

Patch selection by grazing animals is difficult to quantify, particularly in large, extensive paddocks like those in northern Australia. However, advances in high resolution satellite imagery now allow identification of patch types over an entire paddock which combined with GPS collars to capture positional data, can give an accurate and comprehensive picture of landscape use by cattle.

Estimating winter crop area across seasons and regions using time-sequential MODIS imagery.

The wheat grain industry is Australia's second largest agricultural export commodity. There is an increasing demand for accurate, objective and near real-time crop production information by industry. The advent of the Moderate Resolution Imaging Spectroradiometer (MODIS) satellite platform has augmented the capability of satellite-based applications to capture reflectance over large areas at acceptable pixel scale, cost and accuracy. The use of multi-temporal MODIS-enhanced vegetation index (EVI) imagery to determine crop area was investigated in this article. Here the rigour of the harmonic analysis of time-series (HANTS) and early-season metric approaches was assessed when extrapolating over the entire Queensland (QLD) cropping region for the 2005 and 2006 seasons. Early-season crop area estimates, at least 4 months before harvest, produced high accuracy at pixel and regional scales with percent errors of -8.6% and -26% for the 2005 and 2006 seasons, respectively. In discriminating among crops at pixel and regional scale, the HANTS approach showed high accuracy. The errors for specific area estimates for wheat, barley and chickpea were 9.9%, -5.2% and 10.9% (for 2005) and -2.8%, -78% and 64% (for 2006), respectively. Area estimates of total winter crop, wheat, barley and chickpea resulted in coefficient of determination (R(2)) values of 0.92, 0.89, 0.82 and 0.52, when contrasted against the actual shire-scale data. A significantly high coefficient of determination (0.87) was achieved for total winter crop area estimates in August across all shires for the 2006 season. Furthermore, the HANTS approach showed high accuracy in discriminating cropping area from non-cropping area and highlighted the need for accurate and up-to-date land use maps. The extrapolability of these approaches to determine total and specific winter crop area estimates, well before flowering, showed good utility across larger areas and seasons. Hence, it is envisaged that this technology might be transferable to different regions across Australia.

Separating grazing and rainfall effects at regional scale using remote sensing imagery: A dynamic reference-cover method

Remote detection of management-related trend in the presence of inter-annual climatic variability in the rangelands is difficult. Minimally disturbed reference areas provide a useful guide, but suitable benchmarks are usually difficult to identify. We describe a method that uses a unique conceptual framework to identify reference areas from multitemporal sequences of ground cover derived from Landsat TM and ETM+ imagery. The method does not require ground-based reference sites nor GIS layers about management. We calculate a minimum ground cover image across all years to identify locations of most persistent ground cover in years of lowest rainfall. We then use a moving window approach to calculate the difference between the window's central pixel and its surrounding reference pixels. This difference estimates ground-cover change between successive below-average rainfall years, which provides a seasonally interpreted measure of management effects. We examine the approach's sensitivity to window size and to cover-index percentiles used to define persistence. The method successfully detected management-related change in ground cover in Queensland tropical savanna woodlands in two case studies: (1) a grazing trial where heavy stocking resulted in substantial decline in ground cover in small paddocks, and (2) commercial paddocks where wet-season spelling (destocking) resulted in increased ground cover. At a larger scale, there was broad agreement between our analysis of ground-cover change and ground-based land condition change for commercial beef properties with different a priori ratings of initial condition, but there was also some disagreement where changing condition reflected pasture composition rather than ground cover. We conclude that the method is suitably robust to analyse grazing effects on ground cover across the 1.3 x 10(6) km(2) of Queensland's rangelands. Crown Copyright (c) 2012 Published by Elsevier Inc. All rights reserved.

VegMachine - putting pastoralists in the picture

Australia’s rangelands are the extensive arid and semi-arid grazing lands that cover approximately 70% of the Australian continent. They are characterised by low and generally variable rainfall, low productivity and a sparse population. They support a number of industries including mining and tourism, but pastoralism is the primary land use. In some areas, the rangelands have a history of biological decline (Noble 1997), with erosion, loss of perennial native grasses and incursion of woody vegetation commonly reported in the scientific and lay literature. Despite our historic awareness of these trends, the establishment of systems to measure and monitor degradation, has presented numerous problems. The size and accessibility of Australia’s rangeland often mitigates development of extensive monitoring programs. So, too, securing on-going commitment from Government agencies to fund rangeland monitoring activities have led to either abandonment or a scaled-down approach in some instances (Graetz et al. 1986; Holm 1993). While a multiplicity of monitoring schemes have been developed for landholders at the property scale, and some have received promising initial uptake, relatively few have been maintained for more than a few years on any property without at least some agency support (Pickup et al. 1998). But, ironically, such property level monitoring tools can contribute significantly to local decisions about stock, infrastructure and sustainability. Research in recent decades has shown the value of satellites for monitoring change in rangelands (Wallace et al. 2004), especially in terms of tree and ground cover. While steadily improving, use of satellite data as a monitoring tool has been limited by the cost of the imagery, and the equipment and expertise needed to extract useful information from it. A project now under way in the northern rangelands of Australia is attempting to circumvent many of the problems through a monitoring system that allows property managers to use long-term satellite image sequences to quickly and inexpensively track changes in land cover on their properties

Remote sensing of nitrogen and water stress in wheat

Nitrogen (N) is the largest agricultural input in many Australian cropping systems and applying the right amount of N in the right place at the right physiological stage is a significant challenge for wheat growers. Optimizing N uptake could reduce input costs and minimize potential off-site movement. Since N uptake is dependent on soil and plant water status, ideally, N should be applied only to areas within paddocks with sufficient plant available water. To quantify N and water stress, spectral and thermal crop stress detection methods were explored using hyperspectral, multispectral and thermal remote sensing data collected at a research field site in Victoria, Australia. Wheat was grown over two seasons with two levels of water inputs (rainfall/irrigation) and either four levels (in 2004; 0, 17, 39 and 163 kg/ha) or two levels (in 2005; 0 and 39 kg/ha N) of nitrogen. The Canopy Chlorophyll Content Index (CCCI) and modified Spectral Ratio planar index (mSRpi), two indices designed to measure canopy-level N, were calculated from canopy-level hyperspectral data in 2005. They accounted for 76% and 74% of the variability of crop N status, respectively, just prior to stem elongation (Zadoks 24). The Normalised Difference Red Edge (NDRE) index and CCCI, calculated from airborne multispectral imagery, accounted for 41% and 37% of variability in crop N status, respectively. Greater scatter in the airborne data was attributable to the difference in scale of the ground and aerial measurements (i.e., small area plant samples against whole-plot means from imagery). Nevertheless, the analysis demonstrated that canopy-level theory can be transferred to airborne data, which could ultimately be of more use to growers. Thermal imagery showed that mean plot temperatures of rainfed treatments were 2.7 °C warmer than irrigated treatments (P < 0.001) at full cover. For partially vegetated fields, the two-Dimensional Crop Water Stress Index (2D CWSI) was calculated using the Vegetation Index-Temperature (VIT) trapezoid method to reduce the contribution of soil background to image temperature. Results showed rainfed plots were consistently more stressed than irrigated plots. Future work is needed to improve the ability of the CCCI and VIT methods to detect N and water stress and apply both indices simultaneously at the paddock scale to test whether N can be targeted based on water status. Use of these technologies has significant potential for maximising the spatial and temporal efficiency of N applications for wheat growers. ‘Ground–breaking Stuff’- Proceedings of the 13th Australian Society of Agronomy Conference, 10-14 September 2006, Perth, Western Australia.

Land condition monitoring information for reef catchments: a new era

Land condition monitoring information is required for the strategic management of grazing land and for a better understanding of ecosystem processes. Yet, for policy makers and those land managers whose properties are situated within north-eastern Australia's vast Great Barrier Reef catchments, there has been a general lack of geospatial land condition monitoring information. This paper provides an overview of integrated land monitoring activity in rangeland areas of two major Reef catchments in Queensland: the Burdekin and Fitzroy regions. The project aims were to assemble land condition monitoring datasets that would assist grazing land management and support decision-makers investing public funds; and deliver these data to natural resource management(NRM) community groups, which had been given increased responsibility for delivering local environmental outcomes. We describe the rationale and processes used to produce new land condition monitoring datasets derived from remotely sensed Landsat thematic mapper (TM) and high resolution SPOT 5 satellite imagery and from rapid land condition ground assessment. Specific products include subcatchment groundcover change maps, regional mapping of indicative very poor land condition, and stratified land condition site summaries. Their application, integration, and limitations are discussed. The major innovation is a better understanding of NRM issues with respect to land condition across vast regional areas, and the effective transfer of decision-making capacity to the local level. Likewise, with an increased ability to address policy questions from an evidence-based position, combined with increased cooperation between community, industry and all levels of government, a new era has emerged for decision-makers in rangeland management.

Remote sensing applications for cotton.

This paper compares classified normalized difference vegetation index images of cotton crops derived from both low and high resolution satellite imagery to determine the most accurate and feasible option for Australian cotton growers. It also demonstrates a rapid automated processing and internet delivery system for distributing satellite SPOT-2 imagery. Also provided is the profile of two case studies conducted in the Darling Towns demonstrating the potential benefit of adopting this technology for improving in-season agronomic crop assessments and therefore enable improved management decisions to be made.

Reef Catchments Catalyst

To interogate spatial data sets including satellite imagery, EM surveys and ground samples to identify the efficiencies of current management practices within Australian cane regions.

Understanding the barriers to the implementation of precision agriculture in the central region

There is an increasing requirement for more astute land resource management through efficiencies in agricultural inputs in a sugar cane production system. A precision agriculture (PA) approach can provide a pathway for a sustainable sugarcane production system. One of the impediments to the adoption of PA practices is access to paddock-scale mapping layers displaying variability in soil properties, crop growth and surface drainage. Variable rate application (VRA) of nutrients is an important component of PA. However, agronomic expertise within PA systems has fallen well behind significant advances in PA technologies. Generally, advisers in the sugar industry have a poor comprehension of the complex interaction of variables that contribute to within-paddock variations in crop growth. This is regarded as a significant impediment to the progression of PA in sugarcane and is one of the reasons for the poor adoption of VRA of nutrients in a PA approach to improved sugar cane production. This project therefore has established a number of key objectives which will contribute to the adoption of PA and the staged progression of VRA supported by relevant and practical agronomic expertise. These objectives include provision of base soils attribute mapping that can be determined using Veris 3100 Electrical Conductivity (EC) and digital elevation datasets using GPS mapping technology for a large sector of the central cane growing region using analysis of archived satellite imagery to determine the location and stability of yield patterns over time and in varying seasonal conditions on selected project study sites. They also include the stablishment of experiments to determine appropriate VRA nitrogen rates on various soil types subjected to extended anaerobic conditions, and the establishment of trials to determine nitrogen rates applicable to a declining yield potential associated with the aging of ratoons in the crop cycle. Preliminary analysis of archived yield estimation data indicates that yield patterns remain relatively stable overtime. Results also indicate the where there is considerable variability in EC values there is also significant variation in yield.

Automating Crop Damage Assessments with Unmanned Aerial Systems and Machine Learning

Agricultural pests are responsible for millions of dollars in crop losses and management costs every year. In order to implement optimal site-specific treatments and reduce control costs, new methods to accurately monitor and assess pest damage need to be investigated. In this paper we explore the combination of unmanned aerial vehicles (UAV), remote sensing and machine learning techniques as a promising methodology to address this challenge. The deployment of UAVs as a sensor platform is a rapidly growing field of study for biosecurity and precision agriculture applications. In this experiment, a data collection campaign is performed over a sorghum crop severely damaged by white grubs (Coleoptera: Scarabaeidae). The larvae of these scarab beetles feed on the roots of plants, which in turn impairs root exploration of the soil profile. In the field, crop health status could be classified according to three levels: bare soil where plants were decimated, transition zones of reduced plant density and healthy canopy areas. In this study, we describe the UAV platform deployed to collect high-resolution RGB imagery as well as the image processing pipeline implemented to create an orthoimage. An unsupervised machine learning approach is formulated in order to create a meaningful partition of the image into each of the crop levels. The aim of this approach is to simplify the image analysis step by minimizing user input requirements and avoiding the manual data labelling necessary in supervised learning approaches. The implemented algorithm is based on the K-means clustering algorithm. In order to control high-frequency components present in the feature space, a neighbourhood-oriented parameter is introduced by applying Gaussian convolution kernels prior to K-means clustering. The results show the algorithm delivers consistent decision boundaries that classify the field into three clusters, one for each crop health level as shown in Figure 1. The methodology presented in this paper represents a venue for further esearch towards automated crop damage assessments and biosecurity surveillance.