RCRichard Azu Crabbe

Richard Azu Crabbe

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Richard Azu Crabbe has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A preliminary investigation of the potential of an all-weather satellite to discriminate dual-purpose crops

    by Jacques Theron, Richard A. Crabbe, Ana Horta, Shawn McGrath

    Context: The application of optical satellite data for crop management is not uncommon in Australia. However, considerable cloud cover during winter or wet season limits the utility of optical satellite data for monitoring winter dual-purpose crops. Synthetic aperture radar (SAR) overcomes this shortcoming of optical remote sensing by self-emitting microwave energy that penetrates clouds. However, using satellite-based SAR for dual-purpose crop management in Australia is under-explored because of low knowledge and skills in interpreting SAR data. Aims: This study aimed to employ foundational and easy-to-interpret SAR methods evaluating the potential of Sentinel-1 SAR for discriminating between wheat and canola fields in a mixed cropping system. Methods: We used field-measured canola and wheat biomass data and Sentinel-1 ground range detected imagery to explore the correlation between wheat and canola biomass and backscattering coefficients by using maps, Wilcoxon’s rank-sum test, and Spearman’s rank correlation test. Key results: The cross-polarised backscatter was positively linearly correlated with canola biomass (R = 0.74, P = 4.8e–05), whereas the wheat biomass negatively correlated with the backscatter associated with the co-polarisation channel (R = −0.44, P = 0.046). Conclusions: Publicly available free-to-use Sentinel-1 SAR tracks wheat and canola productivity. Implications: By using earth observation satellites, SAR can be used alone or combined with optical data to map crop types, phenology, and productivity reliably. This could guide the timing of management inputs such as crop irrigation and applying pesticides and fertilisers.

  • Skysat Can Detect Blackberry Invasive Plants in Australia

    by Jordan Pont, Richard A. Crabbe

    In Australia, blackberry is one of the Weeds of National Significance (WoNS), as this weed causes significant environmental and economic problems to businesses and communities. Despite the growing need from government bodies to leverage satellite earth observation for the management of WoNS, limited studies have been conducted in Australia exploring the application of satellite remote sensor data for the detection of blackberry. This research examined the efficacy of high-resolution imagery sourced from the SkySat earth imaging satellites combined with a random forest (RF) classification algorithm for detecting blackberry infestations in Australia. The study estimated the change in blackberry infestation between El Niño and La Niña seasons. The RF model using spectral information alone achieved a producer accuracy of 99.1% and a user accuracy of 98.7% while using the textural GLCM features alone, the producer accuracy was 91% and user accuracy was 95.5%. The combination of the spectral and textural GLCM features produced an RF model that achieved a producer accuracy of 98.2% while the user accuracy was 99.4%. The study observed that blackberry infestations were fivefold higher during the period coinciding with the climatic phenomenon La Niña, which was characterised by widespread changes in rainfall patterns and temperatures. This study paves the way for future investigations into satellite remote sensing and machine learning for managing WoNS in Australia.

  • Open Access

    Improvement of pasture biomass modelling using high-resolution satellite imagery and machine learning

    by Michael Gbenga Ogungbuyi, Juan Guerschman, Andrew M. Fischer, Richard Azu Crabbe, Iffat Ara, Caroline Mohammed, Peter Scarth, Phil Tickle, Jason Whitehead, Matthew Tom Harrison


  • Open Access

    Enabling Regenerative Agriculture Using Remote Sensing and Machine Learning

    by Michael Gbenga Ogungbuyi, Juan P. Guerschman, Andrew M. Fischer, Richard Azu Crabbe, Caroline Mohammed, Peter Scarth, Phil Tickle, Jason Whitehead, Matthew Tom Harrison

    The emergence of cloud computing, big data analytics, and machine learning has catalysed the use of remote sensing technologies to enable more timely management of sustainability indicators, given the uncertainty of future climate conditions. Here, we examine the potential of “regenerative agriculture”, as an adaptive grazing management strategy to minimise bare ground exposure while improving pasture productivity. High-intensity sheep grazing treatments were conducted in small fields (less than 1 ha) for short durations (typically less than 1 day). Paddocks were subsequently spelled to allow pasture biomass recovery (treatments comprising 3, 6, 9, 12, and 15 months), with each compared with controls characterised by lighter stocking rates for longer periods (2000 DSE/ha). Pastures were composed of wallaby grass (Austrodanthonia species), kangaroo grass (Themeda triandra), Phalaris (Phalaris aquatica), and cocksfoot (Dactylis glomerata), and were destructively sampled to estimate total standing dry matter (TSDM), standing green biomass, standing dry biomass and trampled biomass. We invoked a machine learning model forced with Sentinel-2 imagery to quantify TSDM, standing green and dry biomass. Faced with La Nina conditions, regenerative grazing did not significantly impact pasture productivity, with all treatments showing similar TSDM, green biomass and recovery. However, regenerative treatments significantly impacted litterfall and trampled material, with high-intensity grazing treatments trampling more biomass, increasing litter, enhancing surface organic matter and decomposition rates thereof. Pasture digestibility and sward uniformity were greatest for treatments with minimal spelling (3 months), whereas both standing senescent and trampled material were greater for the 15-month spelling treatment. TSDM prognostics from machine learning were lower than measured TSDM, although predictions from the machine learning approach closely matched observed spatiotemporal variability within and across treatments. The root mean square error between the measured and modelled TSDM was 903 kg DM/ha, which was less than the variability measured in the field. We conclude that regenerative grazing with short recovery periods (3–6 months) was more conducive to increasing pasture production under high rainfall conditions, and we speculate that – in this environment - high-intensity grazing with 3-month spelling is likely to improve soil organic carbon through increased litterfall and trampling. Our study paves the way for using machine learning with satellite imagery to quantify pasture biomass at small scales, enabling the management of pastures within small fields from afar.


  • Open Access

    Quantifying Grassland Biomass and Regenerative Grazing Using Satellite Remote Sensing and Machine Learning

    by Michael Gbenga Ogungbuyi, Juan Pablo Guerschman, Andrew Martin Fischer, Richard Azu Crabbe, Caroline Mohammed, Peter Scarth, Phil Tickle, Jason Whitehead, Matthew Tom Harrison

    The emergence of cloud computing, big data analytics, and machine learning has catalysed the use of remote sensing technologies to enable more timely land management of sustainability indicators such as ground cover and grassland biomass, given the uncertainty of future climate and drought conditions. Here, we examine the potential of “regenerative agriculture”, as an adaptive grazing management strategy to minimise bare ground exposure while maximising pasture biomass productivity. High-intensity sheep grazing treatments were conducted in small fields (less than 1 hectare) for short durations (typically less than 1 day). Paddocks were subsequently spelled to allow pasture biomass recovery (treatments comprising 3, 6, 9, 12, and 15 months) with each compared with control treatments with lighter stocking rates for longer periods (2,000 DSE). Pastures were composed of wallaby grass (Austrodanthonia species), kangaroo grass (Themeda triandra), Phalaris (Phalaris aquatica, and cocksfoot (Dactylis glomerata) were destructively sampled to estimate total standing dry matter (TSDM), standing green biomass, standing dry biomass and trampled biomass. We then invoked a machine learning model using Sentinel-2 imagery to quantify TSDM, standing green biomass and standing dry biomass. Faced with La Nina conditions, regenerative grazing did not significantly impact pasture productivity, with all treatments showing similar TSDM and green biomass. However, regenerative treatments significantly impacted litter fall and trampled material, with the high intensity grazing treatments causing more dry matter trampling, increasing litter, enhancing decomposition rates and surface organic matter. Pasture digestibility was greatest for treatments with minimal spelling (3 months), whereas both standing senescent and trampled material were significantly greater for the treatment with 15-month spell periods. Estimates of TSDM using machine learning with Sentinel-2 imagery underestimated TSDM in treatment plots but explained spatiotemporal variability associated within and across treatments. The root mean square error between the measured and modelled TSDM was 903 kg DM/ha, which was less than the variability measured in the field. We conclude that regenerative grazing with short recovery periods (3-6 months) are most conducive to increasing pasture production under high rainfall conditions, and we speculate that high intensity grazing is likely to positively impact on soil organic carbon through increased litterfall and trampling. Our study paves the way forward for using machine learning with satellite imagery to quantify pasture biomass at small scales, enabling management of pastures from afar.


  • Investigating the potential of Sentinel-1 to detect varying spatial heterogeneity in pasture cover in grasslands

    by Richard A. Crabbe, David W. Lamb, Clare Edwards

    Selective grazing by livestock may be indicative of a site’s grass species diversity and depending on the grazing intensity; this may or may not promote further diversity. However, the detection of sites with spatial heterogeneity in pasture cover as a manifestation of selective grazing has not yet been investigated using satellite remote sensing. Thus, this study was conducted to address the question; can Sentinel-1 detect spatial heterogeneity induced by livestock grazing in grassy fields? Since Synthetic Aperture Radar (SAR) imaging is noted to be sensitive to vegetation architectural arrangement, this study used Sentinel-1 C-band SAR to detect spatial heterogeneity created by selective livestock grazing. The study examined a range of semivariogram, grey-level co-occurrence matrix (GLCM), and eigenvector-eigenvalue polarimetric decomposition features. The coefficient of variation estimates of the GLCM contrast feature consistently produced the strongest correlation (R 2 = 0.71) with Lloyd’s Patchiness Index and semivariogram sill while the polarimetric scattering entropy (range estimates) produced a significant linear correlation with semivariogram sill (R 2 = 0.55, p < 0.05). Inferably, the GLCM contrast and polarimetric scattering entropy can predict spatial heterogeneity in a grazing environment. This is the first time polarimetric scattering entropy estimated from Sentinel-1 has been used for the detection of spatial heterogeneity in a grazing landscape, which makes this study different from past similar studies. Nonetheless, we recommend the testing of this parameter (polarimetric scattering entropy) with a multitemporal SAR data and encourage future studies to investigate the potential of Sentinel-1 for the detection of spatial distances between grass clumps.


  • Open Access

    A Preliminary Investigation of the Potential of Sentinel-1 Radar to Estimate Pasture Biomass in a Grazed Pasture Landscape

    by Richard Azu Crabbe, David William Lamb, Clare Edwards, Karl Andersson, Derek Schneider

    Knowledge of the aboveground biomass (AGB) of large pasture fields is invaluable as it assists graziers to set stocking rate. In this preliminary evaluation, we investigated the response of Sentinel-1 (S1) Synthetic Aperture Radar (SAR) data to biophysical variables (leaf area index, height and AGB) for native pasture grasses on a hilly, pastoral farm. The S1 polarimetric parameters such as backscattering coefficients, scattering entropy, scattering anisotropy, and mean scattering angle were regressed against the widely used morphological parameters of leaf area index (LAI) and height, as well as AGB of pasture grasses. We found S1 data to be more responsive to the pasture parameters when using a 1 m digital elevation model (DEM) to orthorectify the SAR image than when we employed the often-used Shuttle Radar Topography 30 m and 90 m Missions. With the 1m DEM analysis, a significant quadratic relationship was observed between AGB and VH cross-polarisation (R2 = 0.71), and significant exponential relationships between polarimetric entropy and LAI and AGB (R2 = 0.53 and 0.45, respectively). Similarly, the mean scattering angle showed a significant exponential relationship with LAI and AGB (R2 = 0.58 and R2 = 0.83, respectively). The study also found a significant quadratic relationship between the mean scattering angle and pasture height (R2 = 0.72). Despite a relatively small dataset and single season, the mean scattering angle in conjunction with a generalised additive model (GAM) explained 73% of variance in the AGB estimates. The GAM model estimated AGB with a root mean square error of 392 kg/ha over a range in pasture AGB of 443 kg/ha to 2642 kg/ha with pasture LAI ranging from 0.27 to 1.87 and height 3.25 cm to 13.75 cm. These performance metrics, while indicative at best owing to the limited datasets used, are nonetheless encouraging in terms of the application of S1 data to evaluating pasture parameters under conditions which may preclude use of traditional optical remote sensing systems.