Search

Accurate land valuation is necessary for tax purposes, land resources allocation, real estate management and urban development and planning. Since various factors from different domains affect land prices through non-linear relationships, automating the land valuation process on a large scale is a complex task. Advanced technologies in big data analysis and artificial intelligence have demonstrated superior capabilities in knowledge extraction in such cases. Accordingly, this paper develops and compares the performance of four Automated Valuation Models (AVMs) based on machine learning and deep learning techniques utilizing physical, geographical, socio-economic, environmental, legal and planning factors in Melbourne Metropolitan, Australia. According to the results, the eXtreme Gradient Boosting (XGBoost) method outperforms other algorithms of Support Vector Regression (SVR), random forest and Deep Neural Network (DNN). This method has achieved the coefficient of determination (R2) of 0.862, Mean Absolute Percentage Error (MAPE) of 0.139, and normalized Root Mean Square Error (nRMSE) of 0.281. The achieved high accuracy is due to incorporating a wide range of driving factors and applying innovative feature selection and hyperparameter tuning procedures evaluating various possible feature sets and hyperparameters. Accordingly, this paper can contribute to research, governmental and industry-based activities in terms of developing AVMs for mass land valuation. • Automated land valuation models using machine learning and deep learning • Comprehensive feature set and hybrid feature selection process for robust model performance • Spatial mapping of land values in large urban areas • Contribution to fair housing policies and urban development by accurate land valuation • Practical insights for housing affordability strategies in terms of land management [ABSTRACT FROM AUTHOR]

Power grid damage and blackouts are increasing with climate change. Load forecasting methods that integrate climate resilience are therefore essential to facilitate timely and accurate network reconfiguration during periods of extreme stress. Our paper proposes a generalised Wildfire Resilient Load Forecasting Model (WRLFM) to predict electricity load based on operational data of a Distribution Network (DN) in Australia during wildfire seasons in 2015–2020. We demonstrate that load forecasting during wildfire seasons is more challenging than during non-wildfire seasons, motivating an imperative need to improve forecast performance during wildfire seasons. To develop the robust WRLFM, comprehensive comparative analyses were conducted to determine proper Machine Learning (ML) forecast structures and methods for incorporating multiple factors. Bi-directional Gated Recurrent Unit (Bi-GRU) and Vision Transformer (ViT) were selected as they performed the best among all 13 recently trending ML methods. Multi-factors were incorporated to contribute to forecast performance, including input sequence structures, calendar information, flexible correlation-based temperature conditions, and categorical Fire Weather Index (FWI). High-resolution categorical FWI was used to build a forecasting model with climate resilience for the first time, significantly enhancing the average stability of forecast performances by 42%. A sensitivity analysis compared data set patterns and model performances during wildfire and non-wildfire seasons. The improvement rate of load forecasting performance during wildfire seasons was more than two times greater than in non-wildfire seasons. This indicates the significance and effectiveness of applying the WRLFM to improve forecast accuracy under extreme weather risks. Overall, the WRLFM reduces the Mean Absolute Percentage Error (MAPE) of the forecast by 14.37% and 20.86% for Bi-GRU and ViT-based models, respectively, achieving an average forecast MAPE of around 3%. • Novel climate-resilient load forecast model for use during extreme wildfire seasons. • Bi-GRU and ViT outperform 11 recently trending machine learning models. • Categorical FWI with high resolution enhances forecast stability by 42%. • Optimised calendar, temperature and FWI input reduce errors by 17.6%. • Forecast improvement during wildfires is twice that in non-wildfire seasons. [ABSTRACT FROM AUTHOR]

Although traditional physical models have been used to analyse groundwater systems, the emergence of novel machine learning models can improve the accuracy of the predictions. Deep learning has been prominent in environmental and climate change problems. In this paper, we present a framework for utilising deep learning models to predict groundwater levels based on nearby streamflow and rainfall data. We address the missing data problem using a Bayesian linear regression model within the deep learning framework. Our deep learning framework utilises models such as long-short term memory (LSTM) networks and convolutional neural networks (CNN) for multi-step ahead time series prediction. We examine the fluctuations in groundwater levels at various boreholes located near Middle Creek in New South Wales, Australia. We use the National Collaborative Research Infrastructure Strategy (NCRIS) groundwater database and utilise Bayesian linear regression to impute missing data. We investigate the accuracy of the selected models for individual and regional basins and univariate and multivariate strategies. Our results show that the LSTM-based regional model with multivariate strategy using rainfall data provided the best accuracy. • We predict groundwater levels based on stream flow and rainfall data. • Our framework uses Bayesian data imputation and deep learning for multi-step prediction. • We examine the groundwater fluctuations at various boreholes located in Australia. • Results show a fine-tuned regional model with rainfall data yielded the best accuracy. • We find that LSTM models outperformed CNNs using the multivariate approach. [ABSTRACT FROM AUTHOR]

In response to the high uncertainty associated with residential net load due to the coupling of distributed photovoltaic generation and user demand, this paper proposed a novel cluster-based stacking ensemble learning model for net load interval prediction. Firstly, the k-means algorithm is employed to discover the similarity in user electricity consumption patterns. Then, a RIME optimization algorithm with local enhancement (LRIME) is developed to optimize the parameters and weights of the base learners in stacking ensemble learning. Subsequently, base learners with strong predictive capabilities and significant diversity are chosen as the first-layer predictive models, extreme learning machine (ELM) is utilized as the second-layer predictive model, ultimately resulting in the proposed stacking ensemble learning prediction model. And utilizing the bootstrap method to fit the volatility of point predictions, different prediction intervals are obtained at varying confidence levels, aiming to quantify the integrated uncertainty in photovoltaic generation and load. Testing on the open Ausgrid electricity load data in Australia provided robust validation of the proposed method's effectiveness. In comparison with other outstanding prediction models, the proposed ensemble model can effectively capture the uncertainty in integrating photovoltaic generation and user load. • A RIME optimization algorithm with local enhancement (LRIME) is developed. • A stacking ensemble model is proposed for residential net load interval prediction. • The proposed model demonstrates higher forecasting accuracy and reliability. [ABSTRACT FROM AUTHOR]

The increased penetration of renewable energy sources (RESs) as an effective mechanism to reduce carbon emissions leads to an increased weather dependency for power and energy systems. This has created dynamic operation and degradation phenomena, which affect the lifetime estimation of the assets operated with RESs. For the reliable and efficient operation of RES it is crucial to monitor the health of its constituent components and feature selection is a crucial step for building robust and accurate health monitoring approaches. In this context, this paper presents a probabilistic feature selection approach, which probabilistically weights and selects features through a heuristic and iterative process for an improved asset lifetime estimation. Power transformers are key power grid assets and they are used to demonstrate the validity and impact of the proposed approach. The approach is tested on two different photovoltaic power plants operated in Spain and Australia. Results consistently show that the proposed feature-selection approach reduces the prediction error and consistently selects relevant features. The approach has been applied to transformer lifetime estimation, but it can be generally applied to assist in the lifetime estimation of other components operated in RESs. Part of the studies presented here as well as source codes are all open-source under the GitHub repository https://github.com/iramirezg/FeatureSelection. • Probabilistic feature selection approach for improved asset lifetime estimation. • Integration of environmental features for improved renewable-operated asset lifetime. • Systematic and robust feature weighting methodology. • Improved transformer lifetime estimation including sensor and environmental data. • Validated on two real photovoltaic power plant case studies. [ABSTRACT FROM AUTHOR]

The peak period of an energy-generating wave is one of the most important parameters that describe the spectral shape of the oceanic wave, as this indicates the duration for which the waves prevail with respect to their maximum extractable energy. In this paper, a half-hourly peak wave energy period (T P) forecast model is constructed using a suite of statistically significant lagged inputs based on the partial auto-correlation function with an extreme learning machine model developed and its predictive utility is benchmarked against deep learning models, i.e., convolutional neural network (CNN/CovNet) and recurrent neural network (RNN) models and other traditional M5tree, Conditional Maximization based Multiple Linear Regression (MLR-ECM) and MLR models. The objective model (ELM) vs. the comparison models (CNN, RNN, M5tree, MLR-ECM, and MLR) were trained and validated independently on the test dataset obtained from coastal zones of eastern Australia that have a high potential for implementation of wave energy generation systems. The outcomes ascertain that the ELM model can generate significantly accurate predictions of the half-hourly peak wave energy period, providing a good level of accuracy relative to deep learning models in selected coastal study zones. The study establishes the practical usefulness of the ELM model as being a noteworthy methodology for the applications in renewable and sustainable energy resource management systems. • A real-time peak wave energy period forecasting model is constructed using ELM model. • The advance ELM is benchmarked against a deep learning and other traditional models. • The advance ELM generates better predictions than deep learning models in this region. • ELM model provides significant energy management implications for ocean waves. [ABSTRACT FROM AUTHOR]

Property valuation plays a significant role in urban economics and is of great importance to various stakeholders who interact and shape the city, including property owners, buyers, banks, land developers, real estate agents, local councils and government planning authorities. In the literature, various predictive models have been proposed to automate the calculation of property value, most of which endeavour to factor in the combination of property characteristics, market factors and location-based attributes associated with individual properties use large citywide databases. At the same time, it has been widely acknowledged that regional sub-areas have impacts on property price prediction. Therefore, this paper aims to investigate the performance of various techniques on sub-areas using the Greater Sydney Region as the study area. The sub-area in this paper is defined as the statistical areas (SAs) as defined by the Australian Bureau of Statistics. In particular, two different SA geographies (SA4, SA3) along with the City Level are adopted to understand the spatial dependence which occurs at different levels. With real-world transaction records and data collected from a diverse range of sources, various methods including the traditional hedonic price model (HPM) and popular machine learning (ML) approaches are implemented and evaluated for property price prediction. Two different property markets for residential property are modelled, being for housing stock and apartment (unit) stock. Experimental results show that Random Forest and Gradient Boosting-based methods outperform other approaches in most scenarios and that the high spatial resolution property sub-area (SA3) improved the performance in terms of overall model accuracy. This research provides insights into how sub-area machine learning models can be employed in real estate to characterize property price, and helps understand the influential factors in different local geographical areas for policy-making. • Property valuation is modelled with property attributes, locational and socioeconomic factors by a variety of machine learning algorithms. • Models are implemented on three different geographical area levels. • Both in-time and out-of-time validation are implemented. • House and Apartments are both valued. • Valuation carried out on smaller regions can improve the predictive performance of most modelling techniques. • The study illustrates that the variables' contributions to the property price vary for different geographical areas. [ABSTRACT FROM AUTHOR]

In this paper, a systematic machine learning strategy is proposed to classify wood properties based on a contact ultrasonic testing results. As such, several aspects of the wood material including the type of wood (hardwood or softwood), the direction of an ultrasonic test with respect to the growth rings of the wood, and, whether the wood is damaged or intact are investigated. As a pre-processor, the Variational Mode Decomposition technique is applied to the nonlinearly modulated ultrasonic signals, and the centre frequencies of the decomposition results are taken as features for Machine learning Algorithms (MLAs). Then with each of the MLAs, hyperparameter settings were optimised and technical aspects of the feature engineering are discussed. Best results were achieved using Ensemble classifiers, SVM, and KNN using three features/decomposition. To explore the physics behind the nonlinear problem, the relative false discovery rate obtained from the confusion matrix associated with applying the MLAs is proposed as a metric. We show that different features are capable of exploring different aspects of the problem better. The techniques of this paper can be applied to quality assessment of wood materials. The paper also demonstrates the capability of MLAs in exploring some physics of such problems. Moreover, billets with natural imperfections harvested from the site Collie in WA, Australia are classified to demonstrate the applicability of the proposed approach in real world problems. The result of 94% 5-fold cross-validation accuracy indicates the effectiveness of the proposed approach. • Contact ultrasonic technique is used for the wood quality assessment. • The Variational Mode Decomposition is used to decompose ultrasonic signals. • time–frequency features of the decomposed signals are used as features. • Machine learning algorithms are used to solve classification problems. • Some physics of the problem has been explored from the machine learning results. [ABSTRACT FROM AUTHOR]

• Developed an approach to approximate the demand of a carsharing station. • Improved the estimation accuracy of the model by including social media data and spatio-temporal correlated data. • Applied a spatio-temporal autocorrelation model. • Developed a correlation analysis to account for the interactions among variables. As an emerging urban mobility service, carsharing has become increasingly popular worldwide. To understand customers' needs and optimize the design of service networks, the usage of carsharing vehicles whose trips are recorded by the operators has been applied in research estimating carsharing demand. However, as a form of spatio-temporal correlated data, the underlying spatio-temporal information included in such carsharing records has not been investigated in existing models of carsharing demand. Meanwhile, due to the supply limitation of carsharing stations, some demand cannot be fulfilled and thus remains unrecorded in the operational data. Unrealized demand may lead to underestimation of carsharing demand and therefore an incorrect vehicle deployment strategy by the service providers. In view of these issues, this paper develops an innovative approach to estimating the actual demand at a carsharing station with operational data from GoGet , the largest carsharing company in Australia. The accuracy of the estimation is improved by adding spatio-temporal correlated variables as well as variables from emerging data sources such as social media. To explore the latent space-and-time correlated information, spatio-temporal autoregressive and moving-average models have been applied. Based on the results of the analysis, the paper also provides recommendations related to the operation policies of the service providers. [ABSTRACT FROM AUTHOR]

• The ELM model is applied to predict the ionospheric propagation factor M(3000)F2. • The ELM achieves slightly higher accuracy at a faster training speed than BPNN. • Better average accuracy of ELM over the IRI in high and low solar activity years. This paper presents an novel extreme learning machine (ELM)-based prediction model for the ionospheric propagation factor M(3000)F2 at Darwin station (12.4°S, 131.5°E; −44.5°dip) in Australia. The proposed ELM model is trained with hourly daily values of M(3000)F2 from the period 1998–2014 except 2001 and 2009. The hourly daily values of 2001 (high solar activity) and 2009 (low solar activity) are used for validating the prediction accuracy. The proposed ELM for modeling M(3000)F2 can achieve faster training process and similar testing accuracy compared with backward propagation neural network (BPNN). In addition, the performance of the ELM is verified by comparing the predicted values of M(3000)F2 with observed values and the international reference ionosphere (IRI −2016) model predicted values. Based on the error differences (the root mean square error (RMSE) and the M(3000)F2 percentage improvement values M(3000)F2 IMP (%)), the result demonstrates the effectiveness of the ELM model compared with the IRI-2016 model at hourly, daily, monthly, and yearly in high (2001) and low (2009) solar activity years. The ELM also shows good agreement with observations compared with the IRI during disturbed magnetic activity. [ABSTRACT FROM AUTHOR]

• Machine learning algorithms have been applied to estimate wheat yield for Australia. • Combining climate and satellite data achieves high performance for yield prediction. • The unique and overlapping information of climate and satellite data is quantified. • Optimal prediction performance can be achieved two-month lead time before maturity. Wheat is the most important staple crop grown in Australia, and Australia is one of the top wheat exporting countries globally. Timely and reliable wheat yield prediction in Australia is important for regional and global food security. Prior studies use either climate data, or satellite data, or a combination of these two to build empirical models to predict crop yield. However, though the performance of yield prediction using empirical methods is improved by combining the use of climate and satellite data, the contributions from different data sources are still not clear. In addition, how the regression-based methods compare with various machine-learning based methods in their performance in yield prediction is also not well understood and needs in-depth investigation. This work integrated various sources of data to predict wheat yield across Australia from 2000 to 2014 at the statistical division (SD) level. We adopted a well-known regression method (LASSO, as a benchmark) and three mainstream machine learning methods (support vector machine, random forest, and neural network) to build various empirical models for yield prediction. For satellite data, we used the enhanced vegetation index (EVI) from MODIS and solar-induced chlorophyll fluorescence (SIF) from GOME-2 and SCIAMACHY as metrics to approximate crop productivity. The machine-learning based methods outperform the regression method in modeling crop yield. Our results confirm that combining climate and satellite data can achieve high performance of yield prediction at the SD level (R2 ˜ 0.75). The satellite data track crop growth condition and gradually capture the variability of yield evolving with the growing season, and their contributions to yield prediction usually saturate at the peak of the growing season. Climate data provide extra and unique information beyond what the satellite data have offered for yield prediction, and our empirical modeling work shows the added values of climate variables exist across the whole season, not only at some certain stages. We also find that using EVI as an input can achieve better performance in yield prediction than SIF, primarily due to the large noise in the satellite-based SIF data (i.e. coarse resolution in both space and time). In addition, we also explored the potential for timely wheat yield prediction in Australia, and we can achieve the optimal prediction performance with approximately two-month lead time before wheat maturity. The proposed methodology in this paper can be extended to different crops and different regions for crop yield prediction. [ABSTRACT FROM AUTHOR]

Local and state governments depend on small area population forecasts to make important decisions concerning the development of local infrastructure and services. Despite their importance, current methods often produce highly inaccurate forecasts. Recent years have witnessed promising developments in time series forecasting using Machine Learning across a wide range of social and economic variables. However, limited work has been undertaken to investigate the potential application of Machine Learning methods in demography, particularly for small area population forecasting. In this paper we describe the development of two Long-Short Term Memory network architectures for small area populations. We employ the Keras Tuner to select layer unit numbers, vary the window width of input data, and apply a double training and validation regime which supports work with short time series and prioritises later sequence values for forecasts. These methods are transferable and can be applied to other data sets. Retrospective small area population forecasts for Australia were created for the periods 2006–16 and 2011–16. Model performance was evaluated against actual data and two benchmark methods (LIN/EXP and CSP-VSG). We also evaluated the impact of constraining small area population forecasts to an independent national forecast. Forecast accuracy was influenced by jump-off year, constraining, area size, and remoteness. The LIN/EXP model was the best performing method for the 2011-based forecasts whilst deep learning methods performed best for the 2006-based forecasts, including significant improvements in the accuracy of 10 year forecasts. However, benchmark methods were consistently more accurate for more remote areas and for those with populations <5000. • A novel deep learning method for small area forecasts is presented. • Forecast accuracy was influenced by jump-off year, constraining, area size, and remoteness. • Deep learning methods performed best for the 5 and 10 year 2006-based forecasts. • The LIN/EXP model was the best performing method for the 5 year 2011-based forecasts. • Benchmark methods were consistently more accurate for more remote areas and for those with populations <5000. [ABSTRACT FROM AUTHOR]

Predicting electricity demand data is considered an essential task in decisions taking, and establishing new infrastructure in the power generation network. To deliver a high-quality electricity demand prediction, this paper proposes a hybrid combination technique, based on a deep learning model of Convolutional Neural Networks and Echo State Networks, named as CESN. Daily electricity demand data from four sites (Roderick, Rocklea, Hemmant and Carpendale), located in Southeast Queensland, Australia, have been used to develop the proposed hybrid prediction model. The study also analyzes five other machine learning-based models (support vector regression, multilayer perceptron, extreme gradient boosting, deep neural network, and Light Gradient Boosting) to compare and evaluate the outcomes of the proposed deep learning approach. The results obtained in the experimental study showed that the proposed hybrid deep learning model is able to obtain the highest performance compared to other existing models developed for daily electricity demand data forecasting. Based on the statistical approaches utilized in this study, the proposed hybrid approach presents the highest prediction accuracy among the compared models. The obtained results showed that the proposed hybrid deep learning algorithm is an excellent and accurate electricity demand forecasting method, which outperformed the state of the art algorithms that are currently used in this problem. [Display omitted] • A Hybrid deep learning model is proposed for daily electricity demand prediction. • Convolutional Neural Networks and Echo State Networks are integrated into a single forecasting algorithm. • The proposed deep learning-based approach is excellent in electricity demand prediction. • The proposed algorithm has practical use in inter-daily electricity demand prediction. [ABSTRACT FROM AUTHOR]

• Formulate the logistic regression model with minimum classification error function. • Adopt classification maximum likelihood criterion to infer label information. • Compare results of the proposed model with others and show the effectiveness. • Investigate the most significant contributing factors to hit-and-run crashes. • Conduct sensitivity analysis of related parameters. • Provide implications for policies and counter-measures for hit-and-run crashes. Hit-and-run crashes not only degrade the morality, but also result in delays of medical services provided to victims. However, class imbalance problem exists as the number of hit-and-run crashes is much smaller than that of non-hit-and-run crashes. The missing label problem also exists in the crash analysis due to reasons like data barrier such that the information hidden in the unlabelled samples has not been effectively utilised. In this paper, a cost-sensitive semi-supervised logistic regression (CS3LR) model is proposed for hit-and-run analysis, in order to tackle class-imbalanced data distribution and missing label problem, based on the crash dataset of Victorian, Australia (2013–2019). By performing label estimation with logistic regression jointly utilising both labelled and unlabelled data with pseudo labels in a well-designed cost-sensitive semi-supervised maximum likelihood framework, the proposed model can obtain an unbiased likelihood parameter for hit-and-run prediction and analysis. Comparing the experimental results of CS3LR model with two logistic regression models and seven machine learning methods, better performance of CS3LR model is demonstrated. The most significant contributing factors to hit-and-run crashes extracted by CS3LR with only 10% labelled data show a high degree of consistency with the true contributing factors obtained by the supervised cost-sensitive logistic regression with complete hit-and-run labels. The effects of class-weighted ratio and hyper-parameter λ on the performance of hit-and-run crash prediction model have also been analysed. The results can further provide recommendations and implications on the policies and counter-measures for preventing hit-and-run collisions and crimes. The methodology proposed in this paper can also be employed to analyse crash data with other types of missing labels, such as crash severity. [ABSTRACT FROM AUTHOR]

The energy industry is undergoing significant disruption. This research outlines that, whilst challenging, this disruption is also an emerging opportunity for electricity utilities. One such opportunity is leveraging the developments in data analytics and machine learning. As the uptake of renewable energy technologies and complimentary control systems increases, electricity grids will likely transform towards dense microgrids with high penetration of renewable generation sources, rich in network and customer data, and linked through intelligent, wireless communications. Data digitisation and analytics has already impacted numerous industries, and its influence on the energy sector is growing, as computational capabilities increase to manage big data, and as machines develop algorithms to solve the energy challenges of the future. The objective of this paper is to address how far the uptake of renewable technologies can go given the constraints of existing grid infrastructure, and provides a qualitative assessment of how higher levels of renewable energy penetration can be facilitated by incorporating even broader technological advances in the fields of data analytics and machine learning. Western Australia is used as a contextualised case-study, given its abundance and diverse renewable resources (solar, wind, biomass, and wave) and isolated networks, making a high penetration of renewables a feasible target for policy makers over coming decades. [ABSTRACT FROM AUTHOR]

Modern power systems are experiencing the challenge of high uncertainty with the increasing penetration of renewable energy resources and the electrification of heating systems. In this paradigm shift, understanding electricity users' demand is of utmost value to the retailers, aggregators, and policymakers. However, behind-the-meter (BTM) equipment and appliances at the household level are unknown to the other stakeholders mainly due to privacy concerns and tight regulations. In this paper, we seek to identify residential consumers based on their BTM equipment, mainly rooftop photovoltaic (PV) systems and electric heating, using imported/purchased energy data from utility meters. To solve this problem with an interpretable, fast, secure, and maintainable solution, we propose an integrated method called Interpretable Refined Motifs And binary Classification (IRMAC). The proposed method comprises a novel shape-based pattern extraction technique, called Refined Motif (RM) discovery, and a single-neuron classifier. The first part extracts a sub-pattern from the long time series considering the frequency of occurrences, average dissimilarity, and time dynamics while emphasising specific times with annotated distances. The second part identifies users' types with linear complexity while preserving the transparency of the algorithms. With the real data from Australia and Denmark, the proposed method is tested and verified in identifying PV owners and electrical heating system users. The performance of the IRMAC is studied and compared with various state-of-the-art methods. The proposed method reached an accuracy of 96% in identifying rooftop PV users and 94.4% in identifying electric heating users, which is comparable to the best solution based on deep learning, while the speed of the inference model is a thousand times faster. Last but not least, the proposed method is a transparent algorithm, which can tackle the concerns regarding the agnostic decision-making process when policies prohibit some machine learning methods. [ABSTRACT FROM AUTHOR]

This paper uses examples from Australia to argue for a new approach to integrative research in the Earth's near surface environment where the pedosphere, atmosphere, hydrosphere, and biosphere interact, the so-called ‘Critical Zone’. In Australia, for around 25 years, environmental data layers presented through Geographical Information Systems software have been combined with field-based measurements and observations to produce spatially explicit predictive models for digitally mapping soils and soil properties. The availability of spatially extensive datasets representing different factors of landscape evolution and their exploration with machine learning and rule induction techniques also allow the evaluation of emergent patterns against existing domain knowledge, which in turn can lead to new insights and can facilitate their extrapolation over large areas. Thus the data-driven approach is complementary to the hypothesis-driven scientific inquiry in Critical Zone observatories. [ABSTRACT FROM AUTHOR]

Conventional housing price prediction methods rarely consider the spatiotemporal non-stationary problem in a large data volumes. In this study, four machine learning (ML) models are used to explore the impacts of various features – i.e., property attributes and neighborhood quality - on housing price variations at different geographical scales. Using a 32-year (1984–2016) housing price dataset of Metropolitan Adelaide, Australia, this research relies on 428,000 sale transaction records and 38 explanatory variables. It is shown that non-linear tree-based models, such as Decision Tree, have perform better than linear models. In addition, ensemble machine learning techniques, such as Gradient-Boosting and Random Forest, are better at predicting future housing prices. A spatiotemporal lag (ST-lag) variable was added to improve the prediction accuracy of the models. The study demonstrates that ST-lag (or similar spatio-temporal indicator) can be a useful moderator of spatio-temporal effects in ML applications. This paper will serve as a catalyst for future research into the dynamics of the Australian property market, utilizing the benefits of cutting-edge technologies to develop models for business and property valuation at various geographical levels. • Spatio-temporal non-stationary is significant in explanation of the variations in housing price; • A proposed spatiotemporal lag is incorporated to increase the accuracy of the models; • Non-linear tree-based models have better performance than the linear model. • Ensemble ML techniques are powerful methods to produce better predictive performance. [ABSTRACT FROM AUTHOR]

More timely and accurate air quality forecasting could contribute to better public health protection and air pollution prevention. Particulates are a significant indicator for measuring the degree of air pollution. This paper reports on research to model an early warning tool for coarse particulates when assessing the impact of the 12 satellite-derived and ground-based meteorological pollutants out of 30 pollutants considered using hourly Australian data from January 2018–December 2020. A one-dimensional convolutional neural network (CNN) was integrated with a one-directional fully gated recurrent unit (GRU) to forecast consecutive hours' air quality. The CNN model acts as a spatial feature extractor, whereas the new generation GRU makes it computationally efficient. The resultant hybrid ' CNN-GRU' is then comprehensively benchmarked outperforming an ensemble of six other deep learning models. The proposed model's efficacy is indicated at the four most air polluted Australian postcodes in the testing phase. A detailed error analysis with visual and statistical metrics for air quality forecasting ascertains the proposed model's countermeasure to reduce harm and loss. The practical tool is immensely beneficial and can be widely deployed to the regions of public health concern where air pollution is a significant hazard. [Display omitted] • A novel early warning hybrid PM10 forecasting framework designed for Australia. • 30 satellite and ground-based meteorological pollutants were considered with 7 modeling approaches. • CNN integrated with GRU outperformed the other models. • Early warning AI model show potential in the health, environment sector, and decision-making. [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]

The prediction of future drought is an effective mitigation tool for assessing adverse consequences of drought events on vital water resources, agriculture, ecosystems and hydrology. Data-driven model predictions using machine learning algorithms are promising tenets for these purposes as they require less developmental time, minimal inputs and are relatively less complex than the dynamic or physical model. This paper authenticates a computationally simple, fast and efficient non-linear algorithm known as extreme learning machine (ELM) for the prediction of Effective Drought Index (EDI) in eastern Australia using input data trained from 1957–2008 and the monthly EDI predicted over the period 2009–2011. The predictive variables for the ELM model were the rainfall and mean, minimum and maximum air temperatures, supplemented by the large-scale climate mode indices of interest as regression covariates, namely the Southern Oscillation Index, Pacific Decadal Oscillation, Southern Annular Mode and the Indian Ocean Dipole moment. To demonstrate the effectiveness of the proposed data-driven model a performance comparison in terms of the prediction capabilities and learning speeds was conducted between the proposed ELM algorithm and the conventional artificial neural network (ANN) algorithm trained with Levenberg–Marquardt back propagation. The prediction metrics certified an excellent performance of the ELM over the ANN model for the overall test sites, thus yielding Mean Absolute Errors, Root-Mean Square Errors, Coefficients of Determination and Willmott's Indices of Agreement of 0.277, 0.008, 0.892 and 0.93 (for ELM) and 0.602, 0.172, 0.578 and 0.92 (for ANN) models. Moreover, the ELM model was executed with learning speed 32 times faster and training speed 6.1 times faster than the ANN model. An improvement in the prediction capability of the drought duration and severity by the ELM model was achieved. Based on these results we aver that out of the two machine learning algorithms tested, the ELM was the more expeditious tool for prediction of drought and its related properties. [ABSTRACT FROM AUTHOR]

Abstract: Fire danger indices are used by fire management agencies to assess fire weather conditions and issue public warnings. The most widely used fire danger indices in Australia are the McArthur Fire Forest Danger Index and the Grassland Fire Danger Index. These indices are calculated at weather stations using measurements of weather variables and fuel information. For a vast country like Australia when assessing the risk of severe fire weather events, it is also important to calculate the spatial distribution of these indices considering the extreme tail of the distribution. The spatial distribution of one of the fire weather danger indices regularly used in Australia is presented in this paper. In particular, we present the spatial distribution of the long-term tendency of extreme values of the McArthur Forest Fire Danger Index (FFDI). This indicator of fire weather conditions was assessed by calculating the return period of its extreme values by fitting extreme value distributions to data sets of FFDI at 78 recording stations around Australia. The spatial distribution of these return periods was obtained by using spatial interpolation algorithms with the recording stations measurements. Two conventional and two new algorithms based on machine-learning techniques were tested. This study shows that the best interpolation results for the FFDI can be obtained by using a combination of random forest and inverse distance weighting interpolation algorithms. The spatial distribution of the seasonal FFDI return period shows that the highest FFDI over large parts of southern Australia occurs during the summer months whilst in northern Australia it occurs in spring. The results also show that the FFDI in eastern Australia, the most populated region of the country, is higher inland than in the coastal areas particularly during spring and summer. [Copyright &y& Elsevier]

• Novel ensemble framework which improves short-term load forecasting accuracy. • Model divides the problem into several subtasks based on peak and off-peak conditions. • Classification and regression models were developed to solve each subtask. • Framework is validated on real-world operational demand across regions in Australia. • Model has a substantially higher accuracy (up to 25.4% in MAE) over other methods. [Display omitted] To keep the balance between electricity demand and supply as well as infrastructure planning, it is important to accurately forecast the electricity demand. This has become a challenging task due to increasing share of renewable energy and prosumers (i.e. consumers who produce electricity) in the electricity grid. This paper develops a cooperative ensemble framework which divides the forecasting problem into several subtasks based on peak and off-peak conditions. Each subtask is then solved using multiple forecasting models that include classification and regression. The developed framework is finally validated on real-world operational demand across the National Electricity Market (NEM) of Australia. The performance is comprehensively compared against various state-of-the-art techniques in the field, which indicates up to 25.4% mean absolute error (MAE) improvement. [ABSTRACT FROM AUTHOR]

• A hybrid short-term load forecasting method is proposed. • A data preprocessing module is conducted based on de-noising technique and fuzzy time series. • To balance the forecasting accuracy and stability, a multi-objective optimization algorithm is applied to optimize the BPNN model. Countries around the globe have introduced renewable energies (RE) and minimized the dependency of fossil resources in power systems to address extensive environmental risks. However, such large-scale energy transitions pose a great challenge to power systems due to the volatility of RE. Meanwhile, power demand is increasing over time and it shows temporal characteristics, such as seasonal and peak-valley patterns. Whether the future power system with a larger proportion of RE can meet the surging but fluctuated electricity demand remains problematic. Previous studies on short-term load forecasting focused more on forecasting accuracy than stability. Further, there is a relative paucity of research into temporal patterns. In order to fill in these research gaps, this paper proposes a fuzzy theory-based machine learning model for workdays and weekends short-term load forecasting. Fuzzy time series (FTS) is applied for data mining and back propagation (BP) neural network is used as the main predictor for short-term load forecasting. To exploit the trade-offs between forecasting stability and accuracy, multi-objective optimization is applied to modify the parameters of BP. Moreover, an interval forecasting architecture with several statistical tests is constructed to address forecasting uncertainties. Short-term load data from Victoria in Australia is selected as a case study. Results demonstrate that the proposed method can significantly boost forecasting stability and accuracy, and help strategy making in the field of energy and electricity system management and planning. [ABSTRACT FROM AUTHOR]

• Developing a novel approach for using trip sequences instead of separate trips. • Developing a unique similarity measure for the trip sequences. • Focusing only on the temporal attributes of the trip sequences. • Running the method on real-world case studies. • Evaluating the performance of the developed method. • Comparing the outcome with the existing literature. • Achieving a considerable improvement in inferring the trip purpose. Smart card transactions are known as a rich and continuous source of public transit data, but they miss some important attributes about trips and passengers. One of these missing attributes is the trip purpose attribute. This paper proposes a novel method to infer the trip purpose attribute from the sequences of trips of passengers instead of separate trips. The proposed method infers the trip purpose attribute (a missing attribute in the smart card data) from the temporal attributes (available attributes in the smart card data). First, the relation between the temporal attributes and the trip purpose attribute is learnt by discovering clusters of passengers in the Household Travel Survey dataset while each passenger is represented by one sequence of trips. Then, the discovered clusters are utilized to infer the trip purpose of smart card transactions by allocating each passenger to the closest clusters. The proposed method is implemented on the smart card and HTS datasets from southeast Queensland, Australia. The evaluation results showed a considerable improvement in inferring the trip purpose compared to the results published in the literature. Notably, the effect of considering the trip sequence was more significant than considering land use variables. [ABSTRACT FROM AUTHOR]

Across much of the world, wind gust data are continuously measured by Automatic Weather Stations (AWS). However, the meteorological origin of individual extreme gust events within these datasets are seldom automatically assigned. To overcome this, Self-Organizing Maps (SOM) are proposed here as an automated tool to classify gust events within 1-min AWS data. In this paper, this method is specifically used to distinguish between wind gust events of convective (often broadly termed non-synoptic or thunderstorm) and non-convective origin, with the latter events further sub-classified as either, wind only, transition, or other. The efficacy of a range of different SOMs and input variables were assessed, and it was found that those that utilised gust wind speed, temperature, and pressure generally outperformed other models when classifying wind gusts. Applying this approach in the Australian context, all wind gusts of convective origin greater than 70 ​km ​h−1 (19.4 ​m ​s−1) and 90 ​km ​h−1 (25 ​m ​s−1) were identified at 306 AWS across Australia and a climatology of seasonal and annual convective wind gust occurrence developed and discussed. • Gusts from 1-min weather station data are categorised using machine-learning. • Self-Organizing Maps are shown to categorise storm modes accurately and efficiently. • Convective gusts are best classified using wind speed, pressure and temperature data. • Convective gust climatology developed for Australia. [ABSTRACT FROM AUTHOR]

• Machine learning models using acoustic indices can distinguish time of day in audio. • Such models may misclassify samples from dawn and day. • Models may need to be trained (calibrated) for each observation site. • Signal-to-noise ratio, spectral entropy and spectral cover appear most informative. Environmental sounds, such as bird calls, insects, animal and human activities, support monitoring the health of an area being listened to. Historically these observations needed to be made in the field, but in recent decades non-intrusive acoustic recorders can be deployed for long periods instead, reducing time spent in the field and increasing the volume of raw data collected. The volume of data that can be collected makes human-based processing impractical, so automated analysis approaches are required. Based on the observation that different times of the day exhibit characteristically different soundscapes, this paper investigates predictive (i.e., machine learning) models that use acoustic indices (a calculated representation of some aspect of the recording) to learn and later identify the gross time of day (dawn, day, evening or night). The analysis was based on recordings from north-west Tasmania, Australia, captured in Spring 2017, with 1-min segments of audio sampled at regular intervals across each day. No attempt was made to eliminate unwanted noise (such as wind and rain) before the audio was processed. While audio recordings will typically have accompanying time stamps, this study can be used as the basis for future work in environmental acoustics on: the preferred machine learning classifier; portability of models across sites; the quantity of data required for training; and feature selection. [ABSTRACT FROM AUTHOR]

• A novel probabilistic PV power forecasting method is proposed based on QCNN. • Two-stage training strategy (TSTS) is proposed to solve the training problem of QCNN. • QCNN possesses an evidently superior effect than four state-of-the-art methods. • TSTS provides references for the training of other quantile deep learning models. Probabilistic forecasting is significant in coping with the strong uncertainty of photovoltaic (PV) power, which provides the occurrence scope and corresponding probability information of PV power for the decision of power systems. Convolutional neural networks (CNNs), one of the most advanced and widely used deep-learning methods, are regarded as a promising method for predicting PV power. This paper proposes a daily-ahead probabilistic PV power forecasting method based on an improved quantile CNN (QCNN). First, the QCNN constructs a feature extraction network based on CNNs to mine the deep features of the PV power influence factors. Thereafter, quantile regression (QR) is employed to generate the PV power probability distribution based on the extracted features. However, QR produces non-differentiable loss functions that significantly hinder the training of QCNNs. To address this problem, a two-stage training strategy is proposed in which a CNN is trained using a deterministic forecasting method, and QR is trained using a linear-programming method. This strategy ensures that the training of QCNNs can avoid the effects of the non-differentiable loss functions such that the QCNN can play a complete role in the prediction. The case of a PV plant in Australia demonstrates that QCNNs produce a considerably superior effect when compared to the quantile extreme learning machine, quantile echo state network, direct QR, and radial basis function neural network. The proposed method can be beneficial in terms of decision-making in power systems. [ABSTRACT FROM AUTHOR]

This paper aims to assess the performance of generalized aboveground biomass (AGB) allometric models in the Australian context by investigating the correlation between the AGB estimates and the lidar-based individual tree parameters. A hybrid tree segmentation algorithm is proposed to segment an airborne lidar point cloud into individual trees. Although the diameter at breast height (DBH) of a tree is a crucial parameter for the AGB estimation, a typical airborne lidar data contains only a few points representing partial DBH, hence a localized DBH regression model is proposed. Principal component analysis is applied to examine the multicollinearity in the input variables and ridge regression is applied to remove the less important variables. Four machine learning techniques, namely random forest, support vector regression, multilayer perceptron and radial basis function, are applied to generate AGB regression models. The qualities of the calibrated AGB models are assessed by calculating the adjusted-coefficient-of-determination, leave-one-out cross-validation, the Akaike information criterion, normalized-mean-square-error and the model efficiency index. The test results indicate that the random forest-based AGB model outperforms other machine learning techniques. It is concluded that, if the environmental conditions of tree samples resemble the study region, the generalized AGB allometric model would perform well with the tree samples regardless of their geographical context. [ABSTRACT FROM AUTHOR]

• Data-driven approaches to study physiological response of sentinel oysters to environmental condition. • Predicting heart rate and shell gape of oysters from environmental water quality variables. • Predicting water quality variables from heart rate and shell gape of oysters. • Application of machine learning models to provide a biological perspective of environmental changes. The research presented in this paper was conducted as part of a project that aimed at using biosensors on sentinel oysters to provide a biological perspective of environmental changes. The physiological response patterns (e.g. heart rate variability, shell gape) of sentinel oysters can provide valuable insight into their exposure to environmental stressors. Sensors were attached to measure both heart rate and shell gape (physiological behaviour) of oysters placed at different depths in the water column. Sensors were also deployed to measure water quality that represents the environmental condition the oysters were in. The objective of this study is to utilise the data from different sensors to investigate how environmental conditions modulate physiological response of oysters. We have utilised a set of machine learning models to develop data-driven approaches that can predict heart rate and shell gape (opening and closing action) of oysters from water quality variables, and vice-versa. The level of prediction accuracy indicates how well environmental conditions influence the physiological response of oysters. The effectiveness of the developed approaches is evaluated using data collected from two different deployments of sensors in South East Tasmania, Australia. Experimental results demonstrate that the presented data-driven approaches can provide accurate predictions of physiological and water quality variables, for the data set considered in this study. The prediction error (in terms of MAPE) for HR and water quality is in the range of 3.17%-8.21% and 0.72%–2.48%, respectively, and classification accuracy (F-Score) for shell gape varies between 0.96 and 0.99. [ABSTRACT FROM AUTHOR]

Solar power forecasting is important for the reliable and economic operation of power systems with high penetration of solar energy. The solar power forecasts for the day-ahead time horizon are more erroneous than the hour-ahead time horizon. Numerical weather prediction (NWP) variables such as irradiance, cloud cover, precipitation etc. are used as input to day-ahead forecasting models. The uncertainty in NWP varies with weather conditions. Different forecasting algorithms based on a single method are available in the literature. Combination of individual forecasting algorithms increases the accuracy of the forecasts. However, the combined-forecast has yet not been analysed much in the area of day-ahead solar power forecasting. This paper thus explores different combined-forecast methods such as mean, median, linear regression and non-linear regressions using supervised machine learning algorithms. The number of models required for day-ahead solar power forecasts is studied. One for all hour (same) or separate models for each hour of the day are possible. The effects of retraining frequency on the performance of the forecasting models, which is important for the computational burden of the system, are also studied. Forecasting algorithms are applied to three solar plants in Australia. • Different combined-forecasts for day-ahead solar power forecasting were explored. • The number of forecasting models required for solar power forecasting was analysed. • The effect of different retraining frequencies for day-ahead solar power forecasting models was examined. • Several machine-learning based forecasting models were implemented. [ABSTRACT FROM AUTHOR]

Density log data is one of the key physical attributes used for reservoir characterization by quantifying and qualifying lithological attributes in a wellbore. The density log is most often acquired by geophysical wireline logging techniques after drilling. However, wireline logging can be difficult to execute in highly deviated wells and alternative data acquisition such as logging-while-drilling (LWD) can be very costly. This paper describes the process of using instantaneous drilling attributes together with a machine learning algorithm, extreme gradient boosting (XGBoost), to generate a pseudo density log. The mean absolute error (MAE) and root mean square error (RMSE) are used as the evaluation metrics. Case studies are performed using data from six coalbed methane (or coal seam gas) wells in the Surat Basin, Australia. The inputs include drilling data [weight on bit (WOB), rotations per minute (RPM), torque, true vertical depth (TVD) and rate of penetration (ROP)] and LWD data (i.e., natural gamma ray and hole diameter). The MAE of pseudo density log for most wells is between 0.08 and 0.11 g/cc (except Well 4 is 0.16 g/cc), which results in an average error rate less than 5%. It is found that TVD, gamma ray, ROP, and hole diameter are four most important features. Further experiment shows that the model with these four important features has almost the same performance as the model with all features. The proposed machine learning methodology can assist petroleum engineers and geologists in reservoir characterization by generating pseudo density logs from ongoing LWD and drilling data in real time. It can potentially mitigate the need to run wireline logging tools after drilling or costly LWD techniques whilst drilling. • Pseudo density logs of six coal seam gas wells in Surat Basin, Australia are generated using a machine learning method (XGBoost). • Error rate of generated pseudo density logs for most wells is less than 5%. • True vertical depth (TVD), gamma ray, rate of penetration (ROP), and hole diameter are four important parameters. [ABSTRACT FROM AUTHOR]

Identification of the extent of heat altered coals is important for coal mining and resource estimation because alteration directly affects key economic properties such as ash content, volatile matter, specific energy, sulphur, free swell index and beneficiation characteristics. The most reliable method to identify altered coal is through geochemical analysis of drill core samples; however this method is time consuming and costly. Cheaper alternative methods to identify altered coal is by macroscopic observation of non-core drill cuttings, but this is less reliable than core. Geophysical wireline log data is also used to identify altered coal, but with variable success. Over the past decades, Machine Learning methods have proven popular to automatically classify a variety of lithotypes from geophysical log data. However rarely has there been focus on predicting altered coal. In this paper we apply the most recent machine learning methods which include gradient boosted machines, random forests and artificial neural networks to automatically predict altered and non-altered lithotypes using geophysical log data. We use a massive data set comprising of 1230 samples from 263 boreholes from a highly intruded deposit in the Bowen Basin, Eastern Australia. To do this, we calculate each sample's distance from intrusion and predict their relative density from geophysical log inputs including gamma ray, caliper and compensated density. We then train our machine learning methods on 80% of the data to predict alteration class using the calculated distance to intrusion, predicted relative density, and geophysical log gamma ray, as primary inputs. We evaluated each of these machine learning methods on the remaining 20% of the data to determine the best performing model. Finally, using the best performing model we further split the altered and non-altered classification into lithotypes using a decision tree based on geological knowledge of the case study area. The results indicate that of the machine learning algorithms the random forest produced the best results with only 11 misclassifications across the entire data set of 1230 samples which represents <1% error. • Prediction of heat affected coals with a massive dataset and machine learning methods in the Bowen Basin. • Prediction of relative density and classification of altered and non-altered coals. • Lithology group definition based on a decision tree with <1% error. [ABSTRACT FROM AUTHOR]