Search

Simple Summary: In radiotherapy treatment, organs at risk and target volumes are contoured by the clinicians to prepare a dosimetry plan. In retrospective data, these structures are not often standardised to universal names across the patients plans, which is required to enable data mining and analysis. In this paper, a new method was proposed and evaluated to automatically standardise radiotherapy structures names using machine learning algorithms. The proposed approach was deployed over a dataset with 1613 patients collected from Liverpool & Macarthur Cancer Therapy Centres, New South Wales, Australia. It was concluded that machine learning techniques can standardise the dosimetry plan structures, taking into consideration the integration of multiple modalities representing each structure during the training process. In progressing the use of big data in health systems, standardised nomenclature is required to enable data pooling and analyses. In many radiotherapy planning systems and their data archives, target volumes (TV) and organ-at-risk (OAR) structure nomenclature has not been standardised. Machine learning (ML) has been utilised to standardise volumes nomenclature in retrospective datasets. However, only subsets of the structures have been targeted. Within this paper, we proposed a new approach for standardising all the structures nomenclature by using multi-modal artificial neural networks. A cohort consisting of 1613 breast cancer patients treated with radiotherapy was identified from Liverpool & Macarthur Cancer Therapy Centres, NSW, Australia. Four types of volume characteristics were generated to represent each target and OAR volume: textual features, geometric features, dosimetry features, and imaging data. Five datasets were created from the original cohort, the first four represented different subsets of volumes and the last one represented the whole list of volumes. For each dataset, 15 sets of combinations of features were generated to investigate the effect of using different characteristics on the standardisation performance. The best model reported 99.416% classification accuracy over the hold-out sample when used to standardise all the nomenclatures in a breast cancer radiotherapy plan into 21 classes. Our results showed that ML based automation methods can be used for standardising naming conventions in a radiotherapy plan taking into consideration the inclusion of multiple modalities to better represent each volume. [ABSTRACT FROM AUTHOR]

There is a long history of coastal erosion caused by frequent storm surges in the coastal regions of Australia, which imposes great threats to communities and infrastructures alongside the beach. Old Bar Beach, New South Wales, Australia, is one such hotspot famous for its extreme coastal erosion. To apply remedial measures such as beach nourishment effectively and economically, estimating/reconstructing the subsurface hydrogeology over the coastal areas is essential. A geophysical tool such as a ground-penetrating radar (GPR) which works on the principle of reflecting electromagnetic (EM) waves, can be conveniently deployed to delineate the soil and rock profiling, water-table depth, bedrock depth, and the subsurface structural features. Here, DeepLabv3+ architecture based newly developed deep convolutional neural networks (DCNNs) were used to establish an inherent non-linear relationship between the GPR data and the EM wave velocity. The presented DCNNs have a lesser number of layers, a lesser number of trainable (learnable) parameters, a high convergence rate and, at the same time, achieve prediction accuracy comparable to that of well-established DeepLabv3+ networks, having high trainable parameters and a relatively low convergence rate. Here, firstly the DCNNs were trained and validated on small 1D datasets. Each dataset contains a 1D GPR trace and a corresponding EM velocity model. The DCNNs turned out to be quite promising in the 1D case, with training, validation, and testing accuracy of approximately 95%, 94%, and 95%, respectively. Secondly, 1D trained weights were applied to 2D synthetic GPR data for EM velocity prediction, and the accuracy of prediction achieved was approximately 95%. Seeing the excellent performance of the DCNNs in the 2D prediction case using 1D trained weights, a large amount of 1D synthetic datasets (approximately 1.2 million) were generated and gaussian noise was added to it to replicate the real field scenario. Thirdly, topographically corrected GPR data acquired over the Old Bar Beach were inverted using the DCNNs trained on 1.2 million 1D synthetic datasets to obtain the subsurface high-resolution, high-precision EM velocity, and ε r distribution information to understand the hydrogeology over the beach. The findings presented in this paper agree well with the previous hydrogeological studies carried out using GPR. Our findings show that DCNNs, along with GPR, can be successfully used in coastal environments for the quick and accurate hydrogeological investigation required for the implementation of coastal erosion mitigation methods such as beach nourishment. [ABSTRACT FROM AUTHOR]

Microgrids are extensively integrated into electrical systems due to their many technical, economic, and environmental advantages. However, they encounter a challenge as they experience high-frequency fluctuations caused by the stochastic nature of renewable energy generation, electric loads, and the presence of Electric Vehicles (EVs). Therefore, various techniques, algorithms, and controllers have been introduced to ensure effective Load Frequency Control (LFC) and maintain a stable power system in microgrids. These methods aim to ensure that the system's frequency remains stable and within an acceptable range, especially when faced with changing load demands and other factors. This paper presents a novel enhanced control approach, Particle Swarm Optimization-Trained Artificial Neural Network (PSO-TANN), to optimize the load frequency model of a microgrid with vehicle-to-grid integration. The results are then compared under various scenarios, including renewable energy integration, EV charging and discharging dynamics, and varying load demands. The comparative analysis involves assessing the performance of the conventional Proportional–Integral–Derivative (PID) controller, the PSO-PID controller, and the newly proposed controlling technique. The suggested controller attains 99.904% efficiency with a negligible mean squared error of 1.1112 × 10−7, decreasing the integrated time absolute error to 1.0 × 10−4. It shows rapid response, precise targeting, and quick peak output ability, with marginal overshoot and undershoot, and a transient time of 28.5626 s, efficiently controlling microgrid frequency. Stability analysis validates the effectiveness of the proposed PSO-TANN controller in ensuring stability within the microgrid's LFC system during uncertainties and disturbances. This establishes resilience, diminishes settling time, and maintains reliable performance while controlling frequency. • An investigation into an islanded microgrid's Load Frequency Control (LFC) model framework has been conducted, comprising diesel generator, solar PV system, wind turbine, and EVs operating in vehicle-to-grid mode to supply power to electric loads, consequently impacting the frequency dynamics of the microgrid system. • A novel enhanced control approach, Particle Swarm Optimization-Trained Artificial Neural Network (PSO-TANN) has been implemented to optimize the load frequency model of a microgrid. • An extensive comparative analysis with other controllers, including PID and PSO-PID, is conducted across diverse scenarios involving renewable energy integration and EV charging and discharging dynamics under various load disturbances to reduce settling time, control system frequency, and ensure reliable performance. • The stability analysis validates the efficiency of the proposed PSO-TANN controller in ensuring reliability during uncertainties and disturbances, maintaining overall robustness and stability of the LFC system within the microgrid. [ABSTRACT FROM AUTHOR]

• Develops a deep Bayesian survival model that integrates deep neural network and Bayesian inference into the survival analysis for rail useful lifetime modelling. • Demonstrates survival analysis is an effective way to handle censored data problems in rail useful lifetime modelling. • Conducts extensive evaluation to verify the effectiveness of this model, using Concordance index, root mean square error, and a proposed CW-index. • The estimated lifetimes obtained by this model are the closest to real lifetimes compared to other commonly used models. • This model can provide the confidence interval of the estimated lifetime, which is more useful than point estimates in decision-making and maintenance planning of railroad systems. Reliable estimation of rail useful lifetime can provide valuable information for predictive maintenance in railway systems. However, in most cases, lifetime data is incomplete because not all pieces of rail experience failure by the end of the study horizon, a problem known as censoring. Ignoring or otherwise mistreating the censored cases might lead to false conclusions. Survival approach is particularly designed to handle censored data for analysing the expected duration of time until one event occurs, which is rail failure in this paper. This paper proposes a deep Bayesian survival approach named BNN-Surv to properly handle censored data for rail useful lifetime modelling. The proposed BNN-Surv model applies the deep neural network in the survival approach to capture the non-linear relationship between covariates and rail useful lifetime. To consider and quantify uncertainty in the model, Monte Carlo dropout, regarded as the approximate Bayesian inference, is incorporated into the deep neural network to provide the confidence interval of the estimated lifetime. The proposed approach is implemented on a four-year dataset including track geometry monitoring data, track characteristics data, various types of defect data, and maintenance and replacement (M&R) data collected from a section of railway tracks in Australia. Through extensive evaluation, including Concordance index (C-index) and root mean square error (RMSE) for evaluating model performance, as well as a proposed CW-index for evaluating uncertainty estimations, the effectiveness of the proposed approach is confirmed. The results show that, compared with other commonly used models, the proposed approach can achieve the best concordance index (C-index) of 0.80, and the estimated rail useful lifetimes are closer to real lifetimes. In addition, the proposed approach can provide the confidence interval of the estimated lifetime, with a correct coverage of 81% of the actual lifetime when the confidence interval is 1.38, which is more useful than point estimates in decision-making and maintenance planning of railroad systems. [ABSTRACT FROM AUTHOR]

This paper presents the results of a research project which investigated permeability prediction for the Precipice Sandstone of the Surat Basin. Machine learning techniques were used for permeability estimation based on multiple wireline logs. This information improves the prediction of CO2 injectivity in this formation. Well logs and core data were collected from 5 boreholes in the Surat Basin, where extensive core data and complete sets of conventional well logs exist for the Precipice Sandstone. Four different machine learning (ML) techniques, including Random Forest (RF), Artificial neural network (ANN), Gradient Boosting Regressor (GBR), and Support Vector Regressor (SVR), were independently trained with a wide range of hyper-parameters to ensure that not only is the best model selected, but also the right combination of model parameters is selected. Cross-validation for 20 different combinations of the seven available input logs was used for this study. Based on the performances in the validation and blind testing phases, the ANN with all seven logs used as input was found to give the best performance in predicting permeability for the Precipice Sandstone with the coefficient of determination (R2) of about 0.93 and 0.87 for the training and blind data sets respectively. Multi-regression analysis also appears to be a successful approach to calculate reservoir permeability for the Precipice Sandstone. Models with a complete set of well logs can generate reservoir permeability with R2 of more than 90%. [ABSTRACT FROM AUTHOR]

Abstract To support alternative forms of energy resources, the prediction of global incident solar radiation (I rad) is critical to establish the efficacy of solar energy resources as a free and clean energy, and to identify and screen solar powered sites. Solar radiation data for construction of energy feasibility studies are not available in many locations due to the absence of meteorological stations, especially in remote or regional sites. To surmount the challenge in solar energy site identification, the universally gridded data integrated into predictive models used to generate reliable I rad forecasts can be considered as a viable medium for future energy utilization. The objective of this paper is to review, develop and evaluate a suite of machine learning (ML) models based on the artificial neural network (ANN) versus several other kinds of data-driven models such as support vector regression (SVR), Gaussian process machine learning (GPML) and genetic programming (GP) models for the prediction of daily I rad generated through the European Centre for Medium Range Weather Forecasting (ECMWF) Reanalysis fields. The performance of the ML models are benchmarked against several statistical tools: auto regressive moving integrated average (ARIMA), Temperature Model (TM), Time series and Fourier Series (TSFS) models. To train these models, 87 different predictor variables from the ERA-Interim reanalysis dataset (01-January-1979 to 31-December-2015) were extracted for 5 solar-rich metropolitan sites (i.e., Brisbane, Gold Coast, Sunshine Coast, Ipswich and Toowoomba, Australia) targeted against surface level I rad available from the measured Scientific Information for Land Owners dataset. For daily forecast models, a total of the 20 most important predictors related to the I rad dataset were screened with nearest component analysis: " fsrnca " feature selection, and partitioned into training (70%), validation (15%) and testing (15%) sets for model design. To benchmark the ANN, TSFS and TM models were developed with Fourier series and regression analysis, respectively and the statistical performance was benchmarked with root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe efficiency (E NS), Willmott's Index (WI), Mean Bias error (MBE), Legates and McCabe Index (E 1), and relative MAE , RMSE and diagnostic plots. The performance of ANN was significantly better than the other models (SVR, GPML, GP, TM), resulting in lower RMSE (1.715–2.27 MJm−2/day relative to 2.14–5.90 MJm−2/day), relative RMSE (9.07–12.47 vs 10.98–29.15), relative RMAE (7.97–11.74 vs 9.27–33.96) and larger WI, E NS and E 1 (0.938–0.967 vs. 0.462–0.955, 0.935–0.872 vs. 0.355–0.915, 0.672–0.783 vs. 0.252–0.740). Additionally, models assessed with predictors grouped into El Niño, La Niña and the positive, negative and neutral periods of Indian Ocean Dipole, affirmed the merits of ANN model (RRMSE ≤ 11%). Seasonal analysis showed that ANN was an elite tool over SVR, GPML and GP for I rad prediction. The study concludes that an ANN approach integrated with ECMWF fields, incorporating physical interactions of I rad with atmospheric data, is an efficacious alternative to forecast solar energy and assist with energy modelling for solar-rich sites that have diverse climatic conditions to further support clean energy utilization. Graphical abstract Image 1 Highlights • ANN, SVR, GPML and GP models were designed for prediction of daily solar radiation with reanalysis data. • Determinstic model ARIMA, temperature model and time series with Fourier transform model was used for benchmarking. • Nearest component analysis (fsrnca) was used for feature selection to get optimum inputs. • ANN outperform all ML model and deterministic models. • Solar energy potential is assessed for 5 cities of Queensland, Australia. [ABSTRACT FROM AUTHOR]

This paper presents a new hybrid approach for Global Solar Radiation (GSR) prediction problems, based on deep learning approaches. Predictive models are useful ploys in solar energy industries to optimize the performance of photovoltaic power systems. Specifically, in this work we develop a new 4-phase hybrid CXGBRFR framework, which includes a deep learning Convolutional Neural Network, an Extreme Gradient Boosting with Random Forest Regression, and a Harris Hawks Optimization for initial feature selection. The proposed system has been tested in a problem of daily GSR prediction at six solar farms in Australia. Data from three global climate models (GCM) (CSIRO-BOM ACCESS1-0, MOHC Hadley-GEM2-CC and MRI MRI-CGCM3) have been considered as predictive (input) variables for the proposed approach. The variables from these GCMs contain enough information to obtain an accurate prediction of the GSR at each solar farm. The performance of the proposed approach is compared against different deep and shallows learning approaches: Deep Belief Network, Deep Neural Network, Artificial Neural Network, Extreme Learning Machine and Multivariate Auto-Regressive Spline models. We show that the proposed approach exhibits an excellent performance in GSR prediction, against all alternative approaches in all solar farms considered. [Display omitted] • We develop hybrid deep learning model to predict solar radiation • We optimize the algorithm with Harris Hawks, gradient boosting and random forest • We adopt global climate model and observed predictors as learning model inputs • We build an expert system with relevant knowledge in context of solar application • Our methods benefit solar photovoltaic power monitoring in solar engineering problems. [ABSTRACT FROM AUTHOR]

Mean sea level rise is a significant emerging risk from climate change. This research paper is based on the use of artificial intelligence models to assess and predict the trend on mean sea level around northern Australian coastlines. The study uses sea-level times series from four sites (Broom, Darwin, Cape Ferguson, Rosslyn Bay) to make the prediction. Multivariate adaptive regression splines (MARS) and artificial neural network (ANN) algorithms have been implemented to build the prediction model. Both models show high accuracy (R2 > 0.98) and low error values (RMSE < 27%) overall. The ANN model showed slightly better performance compared to MARS over the selected sites. The ANN performance was further assessed for modelling storm surges associated with cyclones. The model reproduced the surge profile with the maximum correlation coefficients ~0.99 and minimum RMS errors ~4 cm at selected validating sites. In addition, the ANN model predicted the maximum surge at Rosslyn Bay for cyclone Marcia to within 2 cm of the measured peak and the maximum surge at Broome for cyclone Narelle to within 7 cm of the measured peak. The results are comparable with a MARS model previously used in this region; however, the ANN shows better agreement with the measured peak and arrival time, although it suffers from slightly higher predictions than the observed sea level by tide gauge station. [ABSTRACT FROM AUTHOR]

This paper presents and evaluates artificial neural network (ANN) models used for macrocell path-loss prediction. Measurement data obtained by utilizing the IS-95 pilot signal from a commercial code-division multiple-access (CDMA) mobile network in rural Australia are used to train and evaluate the models. A simple neuron model and feed-forward networks with different numbers of hidden layers and neurons are evaluated regarding their training time, prediction accuracy, and generalization properties. Furthermore, different backpropagation training algorithms, such as gradient descent and Levenberg--Marquardt, are evaluated. The artificial neural network inputs are chosen to be distance to base station, parameters easily obtained from terrain path profiles, land usage, and vegetation type and density near the receiving antenna. The path-loss prediction results obtained by using the ANN models are evaluated against different versions of the semi-terrain based propagation model Recommendation ITU-R P.1546 and the Okumura--Hata model. The statistical analysis shows that a non-complex ANN model performs very well compared with traditional propagation models with regard to prediction accuracy, complexity, and prediction time. The average ANN prediction results were 1) maximum error: 22 dB; 2) mean error: 0 dB; and 3) standard deviation: 7 dB. A multilayered feedforward network trained using the standard backpropagation algorithm was compared with a neuron model trained using the Levenberg--Marquardt algorithm. It was found that the training time decreases from 150 000 to 10 iterations, while the prediction accuracy is maintained. [ABSTRACT FROM AUTHOR]

In this paper, a deep learning long-short-term memory (LSTM) method is applied to the forecasting of the critical frequency of the ionosphere F2 layer (foF2). Hourly values of foF2 from 10 ionospheric stations in China and Australia (based on availability) from 2006 to 2019 are used for training and verifying. While 2015 and 2019 are exclusive for verifying the forecasting accuracy. The inputs of the LSTM model are sequential data for the previous values, which include local time (LT), day number, solar zenith angle, the sunspot number (SSN), the daily F10.7 solar flux, geomagnetic the Ap and Kp indices, geographic coordinates, neutral winds, and the observed value of foF2 at the previous moment. To evaluate the forecasting ability of the deep learning LSTM model, two different neural network forecasting models: a back-propagation neural network (BPNN) and a genetic algorithm optimized backpropagation neural network (GABP) were established for comparative analysis. The foF2 parameters were forecasted under geomagnetic quiet and geomagnetic disturbed conditions during solar activity maximum (2015) and minimum (2019), respectively. The forecasting results of these models are compared with those of the international reference ionosphere model (IRI2016) and the measurements. The diurnal and seasonal variations of foF2 for the 4 models were compared and analyzed from 8 selected verification stations. The forecasting results reveal that the deep learning LSTM model presents the optimal performance of all models in forecasting the time series of foF2, while the IRI2016 model has the poorest forecasting performance, and the BPNN model and GABP model are between two of them. [ABSTRACT FROM AUTHOR]

This paper presents the results from a study on the application of an artificial neural network (ANN) model for regional flood frequency analysis (RFFA). The study was conducted using stream flow data from 88 gauging stations across New South Wales (NSW) in Australia. Five different models consisting of three to eight predictor variables (i.e., annual rainfall, drainage area, fraction forested area, potential evapotranspiration, rainfall intensity, river slope, shape factor and stream density) were tested. The results show that an ANN model with a higher number of predictor variables does not always improve the performance of RFFA models. For example, the model with three predictor variables performs considerably better than the models using a higher number of predictor variables, except for the one which contains all the eight predictor variables. The model with three predictor variables exhibits smaller median relative error values for 2- and 20-year return periods compared to the model containing eight predictor variables. However, for 5-, 10-, 50- and 100-year return periods, the model with eight predictor variables shows smaller median relative error values. The proposed ANN modelling framework can be adapted to other regions in Australia and abroad. [ABSTRACT FROM AUTHOR]

Cocoa is an important commodity crop, not only to produce chocolate, one of the most complex products from the sensory perspective, but one that commonly grows in developing countries close to the tropics. This paper presents novel techniques applied using cover photography and a novel computer application (VitiCanopy) to assess the canopy architecture of cocoa trees in a commercial plantation in Queensland, Australia. From the cocoa trees monitored, pod samples were collected, fermented, dried, and ground to obtain the aroma profile per tree using gas chromatography. The canopy architecture data were used as inputs in an artificial neural network (ANN) algorithm, with the aroma profile, considering six main aromas, as targets. The ANN model rendered high accuracy (correlation coefficient (R) = 0.82; mean squared error (MSE) = 0.09) with no overfitting. The model was then applied to an aerial image of the whole cocoa field studied to produce canopy vigor, and aroma profile maps up to the tree-by-tree scale. The tool developed could significantly aid the canopy management practices in cocoa trees, which have a direct effect on cocoa quality. [ABSTRACT FROM AUTHOR]

Solar energy predictive models designed to emulate the long-term (e.g., monthly) global solar radiation (GSR) trained with satellite-derived predictors can be employed as decision tenets in the exploration, installation and management of solar energy production systems in remote and inaccessible solar-powered sites. In spite of a plethora of models designed for GSR prediction, deep learning, representing a state-of-the-art intelligent tool, remains an attractive approach for renewable energy exploration, monitoring and forecasting. In this paper, algorithms based on deep belief networks and deep neural networks are designed to predict long-term GSR. Deep learning algorithms trained with publicly-accessible Moderate Resolution Imaging Spectroradiometer (MODIS) satellite data are tested in Australia's solar cities to predict the monthly GSR: single hidden layer and ensemble models. The monthly-scale MODIS-derived predictors (2003–2018) are adopted, with 15 diverse feature selection approaches including a Gaussian Emulation Machine for sensitivity analysis used to select optimal MODIS-predictor variables to simulate GSR against ground-truth values. Several statistical score metrics are adopted to comprehensively verify surface GSR simulations to ascertain the practicality of deep belief and deep neural networks. In the testing phase, deep learning models generate significantly lower absolute percentage bias (≤3%) and high Kling–Gupta efficiency (≥97.5%) values compared to the single hidden layer and ensemble model. This study ascertains that the optimal MODIS input variables employed in GSR prediction for solar energy applications can be relatively different for diverse sites, advocating a need for feature selection prior to the modelling of GSR. The proposed deep learning approach can be adopted to identify solar energy potential proactively in locations where it is impossible to install an environmental monitoring data acquisition instrument. Hence, MODIS and other related satellite-derived predictors can be incorporated for solar energy prediction as a strategy for long-term renewable energy exploration. [ABSTRACT FROM AUTHOR]