Cameron Veal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Cameron Veal has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Anna Kuballa
School of Health, UniSC, Sippy Downs, QLD, Australia; Centre for Bioinnovation, UniSC, Sippy Downs, QLD, Australia; Sunshine Coast Health Institute, Sunshine Coast Hospital and Health Service, Birtinya, QLD, 4575, Australia
2 shared publications - Helen Stratton
School of Environment and Science, Griffith University, Nathan, QLD 4111, Australia
2 shared publications - Mohammad Katouli
Centre for Bioinnovation and School of Science, Technology and Engineering, University of the Sunshine Coast, Maroochydore, QLD 4556, Australia
2 shared publications - Muhammad Hassnain2 shared publications
- Muhammad Rizwan Azhar
School of Engineering Edith Cowan University Joondalup Western Australia Australia
2 shared publications - Nicole Masters
University of the Sunshine Coast
2 shared publications
Latest Publications
- Open Access
- 11 July 2026
- Published by Elsevier in Journal of Water Process Engineering
- Vol. 91
Spatiotemporal assessment of water quality around Western Australian central business district using satellite multispectral imaging
- 11 July 2026
- Published by Elsevier in Journal of Water Process Engineering
- Vol. 91
Open AccessSpatiotemporal assessment of water quality around Western Australian central business district using satellite multispectral imaging
- Open Access
- 4 May 2026
- Published by Elsevier in SSRN Electronic Journal
Artificial Intelligence Based Predictive Simulation and Decision-Support Framework for Full Scale Wastewater Treatment Systems
This study presents a full-scale, industry-deployed artificial intelligence (AI) framework integrating machine learning (ML), simulation, and operational boundary definition across a nitrogen-removal WWTP in Australia. Up to nine years of high-frequency online instrumentation data (≤419,000 records per target; 5-30 min resolution) and ~3,000 laboratory samples were used to train and evaluate 19 ML algorithms across 13 hydraulic, energy, pressure, and effluent-quality targets across full-scale WWTP.Extra Trees (ExT) and deep neural networks (NN) demonstrated superior performance. Deterministic operational variables, including plant inflow, aeration flow, blower energy, effluent pump power and speed, and ocean discharge pressure, were predicted with R2 ~ 0.96-0.99 on validation and unseen datasets. Biological and laboratory-derived parameters achieved R² ~ 0.86-0.92, reflecting intrinsic process variability. NN models enabled extrapolative simulation beyond historical operating ranges.The models generated and evaluated millions of feature combinations to define safe operational boundary conditions associated with screen bypass, overpressure risk, energy overuse, and effluent non-compliance. The framework enabled dynamic optimisation of aeration and pumping configurations, improved energy efficiency, and provided robust ML-based soft sensors during instrumentation faults. This work establishes a scalable pathway for embedding AI into real-world WWTP engineering infrastructure, measurable improvements in predictive accuracy, operational resilience, and risk-aware optimisation.
- 4 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessArtificial Intelligence Based Predictive Simulation and Decision-Support Framework for Full Scale Wastewater Treatment Systems
This study presents a full-scale, industry-deployed artificial intelligence (AI) framework integrating machine learning (ML), simulation, and operational boundary definition across a nitrogen-removal WWTP in Australia. Up to nine years of high-frequency online instrumentation data (≤419,000 records per target; 5-30 min resolution) and ~3,000 laboratory samples were used to train and evaluate 19 ML algorithms across 13 hydraulic, energy, pressure, and effluent-quality targets across full-scale WWTP.Extra Trees (ExT) and deep neural networks (NN) demonstrated superior performance. Deterministic operational variables, including plant inflow, aeration flow, blower energy, effluent pump power and speed, and ocean discharge pressure, were predicted with R2 ~ 0.96-0.99 on validation and unseen datasets. Biological and laboratory-derived parameters achieved R² ~ 0.86-0.92, reflecting intrinsic process variability. NN models enabled extrapolative simulation beyond historical operating ranges.The models generated and evaluated millions of feature combinations to define safe operational boundary conditions associated with screen bypass, overpressure risk, energy overuse, and effluent non-compliance. The framework enabled dynamic optimisation of aeration and pumping configurations, improved energy efficiency, and provided robust ML-based soft sensors during instrumentation faults. This work establishes a scalable pathway for embedding AI into real-world WWTP engineering infrastructure, measurable improvements in predictive accuracy, operational resilience, and risk-aware optimisation.
- Open Access
- 12 August 2021
- Published by MDPI AG in Microorganisms
- Vol. 9 (8) , 1721
Microbial Diversity Profiling of Gut Microbiota of Macropus giganteus Using Three Hypervariable Regions of the Bacterial 16S rRNA
Animal faecal contamination of surface waters poses a human health risk, as they may contain pathogenic bacteria or viruses. Of the numerous animal species residing along surface waterways in Australia, macropod species are a top contributor to wild animals’ faecal pollution load. We characterised the gut microbiota of 30 native Australian Eastern Grey Kangaroos from six geographical regions (five kangaroos from each region) within South East Queensland in order to establish their bacterial diversity and identify potential novel species-specific bacteria for the rapid detection of faecal contamination of surface waters by these animals. Using three hypervariable regions (HVRs) of the 16S rRNA gene (i.e., V1–V3, V3–V4, and V5–V6), for their effectiveness in delineating the gut microbial diversity, faecal samples from each region were pooled and microbial genomic DNA was extracted, sequenced, and analysed. Results indicated that V1-V3 yielded a higher taxa richness due to its larger target region (~480 bp); however, higher levels of unassigned taxa were observed using the V1-V3 region. In contrast, the V3–V4 HVR (~569 bp) attained a higher likelihood of a taxonomic hit identity to the bacterial species level, with a 5-fold decrease in unassigned taxa. There were distinct dissimilarities in beta diversity between the regions, with the V1-V3 region displaying the highest number of unique taxa (n = 42), followed by V3–V4 (n = 11) and V5–V6 (n = 8). Variations in the gut microbial diversity profiles of kangaroos from different regions were also observed, which indicates that environmental factors may impact the microbial development and, thus, the composition of the gut microbiome of these animals.
- 12 August 2021
- Published by MDPI AG in Microorganisms
- Vol. 9 (8) , 1721
Open AccessMicrobial Diversity Profiling of Gut Microbiota of Macropus giganteus Using Three Hypervariable Regions of the Bacterial 16S rRNA
Animal faecal contamination of surface waters poses a human health risk, as they may contain pathogenic bacteria or viruses. Of the numerous animal species residing along surface waterways in Australia, macropod species are a top contributor to wild animals’ faecal pollution load. We characterised the gut microbiota of 30 native Australian Eastern Grey Kangaroos from six geographical regions (five kangaroos from each region) within South East Queensland in order to establish their bacterial diversity and identify potential novel species-specific bacteria for the rapid detection of faecal contamination of surface waters by these animals. Using three hypervariable regions (HVRs) of the 16S rRNA gene (i.e., V1–V3, V3–V4, and V5–V6), for their effectiveness in delineating the gut microbial diversity, faecal samples from each region were pooled and microbial genomic DNA was extracted, sequenced, and analysed. Results indicated that V1-V3 yielded a higher taxa richness due to its larger target region (~480 bp); however, higher levels of unassigned taxa were observed using the V1-V3 region. In contrast, the V3–V4 HVR (~569 bp) attained a higher likelihood of a taxonomic hit identity to the bacterial species level, with a 5-fold decrease in unassigned taxa. There were distinct dissimilarities in beta diversity between the regions, with the V1-V3 region displaying the highest number of unique taxa (n = 42), followed by V3–V4 (n = 11) and V5–V6 (n = 8). Variations in the gut microbial diversity profiles of kangaroos from different regions were also observed, which indicates that environmental factors may impact the microbial development and, thus, the composition of the gut microbiome of these animals.
- 1 November 2019
- Published by Elsevier in Water Research
- Vol. 165, 114967
Compositional and temporal stability of fecal taxon libraries for use with SourceTracker in sub-tropical catchments
- 1 November 2019
- Published by Elsevier in Water Research
- Vol. 165, 114967
Compositional and temporal stability of fecal taxon libraries for use with SourceTracker in sub-tropical catchments
- 8 December 2017
- Published by IWA Publishing in Water Supply
- Vol. 18 (5) , 1719-1726
Managing cyanobacterial toxin risks to recreational users: a case study of inland lakes in South East Queensland
The management of inland waterways to protect recreational users from cyanotoxin exposure is complicated by common management practice of using proxy indicators of cyanotoxin production (cell counts and biovolumes of potentially toxin species), rather than the cyanotoxin itself. This widely accepted practice is further complicated by a lack of advisory guidelines for non microcystin producing cyanotoxins. This study has investigated the effectiveness of this management approach over five and a half years, monitoring 65 different sites in South East Queensland using phycological and toxin analysis. This study concluded that cell counts of Cylindrospermopsis raciborskii, the most common potentially toxin producing species of cyanobacteria in South East Queensland9s inland lakes, was a poor proxy indicator for cylindrospermopsin toxin production. Seqwater, the local water authority responsible for the management of recreational access to drinking water storage lakes, initiated an alternate management approach for recreational cyanobacterial water quality management in December, 2016. This new approach is based on cyanobacterial toxin guideline values for five different cyanotoxins, with closures and warning notices issued based on the actual cyanotoxin concentration, not the proxy indicator. We encourage other recreational water management authorities consider this approach to manage recreational access in the future.
- 8 December 2017
- Published by IWA Publishing in Water Supply
- Vol. 18 (5) , 1719-1726
Managing cyanobacterial toxin risks to recreational users: a case study of inland lakes in South East Queensland
The management of inland waterways to protect recreational users from cyanotoxin exposure is complicated by common management practice of using proxy indicators of cyanotoxin production (cell counts and biovolumes of potentially toxin species), rather than the cyanotoxin itself. This widely accepted practice is further complicated by a lack of advisory guidelines for non microcystin producing cyanotoxins. This study has investigated the effectiveness of this management approach over five and a half years, monitoring 65 different sites in South East Queensland using phycological and toxin analysis. This study concluded that cell counts of Cylindrospermopsis raciborskii, the most common potentially toxin producing species of cyanobacteria in South East Queensland9s inland lakes, was a poor proxy indicator for cylindrospermopsin toxin production. Seqwater, the local water authority responsible for the management of recreational access to drinking water storage lakes, initiated an alternate management approach for recreational cyanobacterial water quality management in December, 2016. This new approach is based on cyanobacterial toxin guideline values for five different cyanotoxins, with closures and warning notices issued based on the actual cyanotoxin concentration, not the proxy indicator. We encourage other recreational water management authorities consider this approach to manage recreational access in the future.