Search

Current applications of Graph Neural Networks in citywide short-term crash risk prediction have been limited by a gridded representation of space, which restricts the network's capability to effectively capture the spatial and temporal dependency of crash occurrences. In addition, a grided representation does not match most geographic units used for administrative purposes, limiting the use of crash risk predictions by practitioners. This paper applies a gated localised diffusion graph neural network (GLDNet) model to compare the use of two alternative geographic units, Mesh Block (MB) and grid, to forecast locations where crashes are likely to occur in a future time window. The GLDNet relies on a graph-based representation of geographic units and a weighted loss function to address the sparsity of crash occurrences. The tests are performed using crash data from the City of Melbourne, Australia, over a period of one year. The predictions are made at six-hour intervals, and the results show that the GLDNet consistently outperforms baseline methods, with differences in prediction accuracy from 10% to 21% in relation to historical average and benchmark deep learning models. In terms of geographic units, the MB-based GLDNet performed better than its grid counterpart, with differences in prediction accuracy of up to 12.3%. The better performance stems from the underlying information attached to the MB units (i.e., land use) and the network properties (i.e., degree of centrality), which enhance the GLDNet capability to identify crash risk in both central and peripherical areas. Regarding its applicability, the MB-based GLDNet directly integrates with other data sources, which provides contextual information about crash hotspots that helps decision-makers develop police patrolling and rescuing strategies. [ABSTRACT FROM AUTHOR]

In recent years, deep learning (DL) approaches have been proven effective in addressing high nonlinear relationships within complex systems. Although various scientific studies have primarily focused on optimizing model architecture and enhancing its computational efficiency through hybridization, they have neglected the crucial aspect of selecting appropriate predictor variables (PV) and their influence on the model's predictions. In this paper, a new multi-phase stochastic DL model is designed with a feature selection framework for monthly streamflow prediction. The multi-phase hybrid MCMC–BC–BiLSTM–BiGRU model is based on bidirectional long short-term memory (BiLSTM) and bidirectional gated recurrent unit (BiGRU) integrated with Markov Chain Monte Carlo (MCMC) based bivariate copulas (BC). First, Ant Colony Optimization (ACO) algorithm was employed for screening optimal PV, and then significant antecedent streamflow was coupled with it to generate optimized input combinations. In addition, 25 different MCMC–BC models were adopted for each input combination to determine the dependency of previous month's streamflow on current and future streamflow. Finally, best-fitted MCMC–BC model was integrated with hybrid BILSTM–BiGRU model to predict streamflow at nine different catchments in the Victoria region of the Upper Murray Basin (UMB), Australia. The experimental results show that the multi-phase hybrid MCMC–BC–BiLSTM–BiGRU model showed remarkable performance in comparison to its benchmark counterparts with respect to different robust statistical error metrics. Therefore, this study demonstrates that stochastic DL techniques can be effectively employed as a promising alternative predictive tool for upstream discharge predictions with high consistency and accuracy, specifically when a statistically significant relationship with the antecedent streamflow exists. [ABSTRACT FROM AUTHOR]

In past few decades, there was a tremendous enhancement in natural disaster and their effects on economy and population. An adverse events like floods, wildfires, cyclones, earthquakes, tsunamis, etc., are regarded as a natural disaster once it strikes the vulnerable population areas. An early tracking of susceptibility areas and immediate tracking of affected areas might help in facilitating rescue and early warnings to the public. To achieve autonomous natural disaster prediction, this paper makes use of current developments in remote sensing, which speed up the availability of aerial/satellite data and are reinforced by progress in the computing sector. The aerial/satellite imageries are employed for acquiring the data from areas of Queensland-Australia that are more prone to natural disaster in an eagle-eye perspective. Since there were several techniques employed so far for the automatic prediction of natural disaster susceptibilities, there were some limitations like reduced rate of accuracy and so on. So as to overcome these limitations, deep learning based automated process is employed for predicting the natural disaster areas and probability of event occurrences. The main intention of the work is to detect the natural disaster occurrence from the sensed data which aids in providing warning to public and to safeguard them by taking necessary actions. Initially, remote sensing data is pre-processed and the features are extracted using Adaptive linear Internal embedding algorithm-based feature extraction (ALIE-FE). The extracted features are selected using Recursive Wrapper-based feature subset selection. To estimate best fitness function and to enhance the prediction accuracy, the optimization process is carried using Bio-Inspired Squirrel Search Optimization algorithm (BI-SSOA). Finally, the classification is carried by means of Deep learning based Multi-layer Alex Net classifier (DBMLA) approach. The simulation is carried and the outcomes attained are estimated for predicting flood susceptibility and wildfire susceptibility. The proposed BISSOA-DBMLA offers sensitivity of 98%, specificity of 99%, and TSS of 97%. The proposed system offers 98.99% classification accuracy. Accuracy, sensitivity, specificity, TSS, and area under the curve (AUC) are used to evaluate the efficacy of the suggested system in light of the achieved results from other approaches. To demonstrate the efficacy of the suggested mechanism, the achieved results are compared with those of current approaches. [ABSTRACT FROM AUTHOR]

Future soil moisture (SM) estimation is a practically useful task for eco-hydrologists, agriculturists, and stakeholders in environment health monitoring to generate comprehensive understanding of hydro-physical and soil dynamic system. This paper demonstrates the capability of a hybridised long short-term memory (LSTM) predictive framework to emulate SM under global warming scenarios. The proposed model is developed by integrating Boruta-random forest (BRF) feature selection and capturing significant antecedent memory of SM behaviour were applied to estimate the future SM using Coupled Model Intercomparison Phase-5 (CMIP5) repository. The BRF is adapted to extract pertinent features in hydro-meteorological variables intrinsically related to SM, and therefore, is used to construct a hybridised deep learning (i.e., BRF-LSTM) model. To establish the viability of deep learning model for SM estimation until 2100, five stations closely matched to the global climate model grid are selected in Australia's Murray Darling Basin. The performance skill of BRF-LSTM model is compared against standalone models (i.e., LSTM, SVR, and MARS). The results showed that the hybrid deep learning model (i.e., BRF-LSTM) with a feature selection capability could significantly outperform the standalone models for both warming simulations. The proposed hybrid model also demonstrated superiority in SM estimation with over 95% of all predictive errors lying below 0.02 mm, and low relative root means square error (≈ 1.06% for RCP4.5 and ≈ 1.888% for RCP8.5) to outperform all the benchmark models. This study demonstrates the capability of LSTM algorithm coupled with BRF feature selection to simulate future soil moisture under climate change, and so, can be successfully implemented in hydrology, agriculture, soil use management and environmental management. [ABSTRACT FROM AUTHOR]

In many developed countries, photovoltaic solar power, which is considered the most cost-effective renewable energy source, accounts for a major portion of electricity production. The photovoltaic (PV) power generation is unpredictable and imprecise due to its high variation that can be caused of meteorological elements, to reduce the negative influence of the use of PV power, accurate PV power prediction is of crucial significance for the secure and efficient operation of photovoltaic power system operation. In light of this, we propose a long short-term memory (LSTM) autoencoder (AE) for photovoltaic power forecasting. Initially, to generate encoded sequences the LSTM-encoder extracts the characteristics from the input data. Then the LSTM-decoder decoded the encoded sequences to advance them to the last dense layer for photovoltaic power prediction. Furthermore, we conducted experiments using a 23.40 kW PV power plants dataset from DKASC in Australia. The results have confirmed that the LSTM-AE model can achieve better prediction accuracy than the benchmark deep learning methods, in terms of mean absolute error (MAE), mean square error (MSE), mean bias error (MBE), root mean square error (RMSE) and coefficient of determination (R 2 ) performance measures. When the results are analyzed, the LSTM-AE model gives the best results with average RMSE, MAE, and R 2 to 0.0762 kW, 0.0389 kW, and 99.93 % , respectively. The experimental results confirm that proposed method with the highest R 2 values and minimum forecasting errors compared to the benchmark models can effectively improve stable performance and achieve better accurate photovoltaic power forecasting. [ABSTRACT FROM AUTHOR]

Forecast models of solar radiation incorporating cloud effects are useful tools to evaluate the impact of stochastic behaviour of cloud movement, real-time integration of photovoltaic energy in power grids, skin cancer and eye disease risk minimisation through solar ultraviolet (UV) index prediction and bio-photosynthetic processes through the modelling of solar photosynthetic photon flux density (PPFD). This research has developed deep learning hybrid model (i.e., CNN-LSTM) to factor in role of cloud effects integrating the merits of convolutional neural networks with long short-term memory networks to forecast near real-time (i.e., 5-min) PPFD in a sub-tropical region Queensland, Australia. The prescribed CLSTM model is trained with real-time sky images that depict stochastic cloud movements captured through a total sky imager (TSI-440) utilising advanced sky image segmentation to reveal cloud chromatic features into their statistical values, and to purposely factor in the cloud variation to optimise the CLSTM model. The model, with its competing algorithms (i.e., CNN, LSTM, deep neural network, extreme learning machine and multivariate adaptive regression spline), are trained with 17 distinct cloud cover inputs considering the chromaticity of red, blue, thin, and opaque cloud statistics, supplemented by solar zenith angle (SZA) to predict short-term PPFD. The models developed with cloud inputs yield accurate results, outperforming the SZA-based models while the best testing performance is recorded by the objective method (i.e., CLSTM) tested over a 7-day measurement period. Specifically, CLSTM yields a testing performance with correlation coefficient r = 0.92, root mean square error RMSE = 210.31 μ mol of photons m−2 s−1, mean absolute error MAE = 150.24 μ mol of photons m−2 s−1, including a relative error of RRMSE = 24.92% MAPE = 38.01%, and Nash Sutcliffe's coefficient ENS = 0.85, and Legate and McCabe's Index LM = 0.68 using cloud cover in addition to the SZA as an input. The study shows the importance of cloud inclusion in forecasting solar radiation and evaluating the risk with practical implications in monitoring solar energy, greenhouses and high-value agricultural operations affected by stochastic behaviour of clouds. Additional methodological refinements such as retraining the CLSTM model for hourly and seasonal time scales may aid in the promotion of agricultural crop farming and environmental risk evaluation applications such as predicting the solar UV index and direct normal solar irradiance for renewable energy monitoring systems. [ABSTRACT FROM AUTHOR]

Natural disasters like bushfires pose a catastrophic threat to the Australia and the world's territorial areas. This fire spreads in a wide area within seconds, and therefore, it is complicated and challenging to mitigate. To minimize risk and increase resilience, identifying bushfire occurrences beforehand and takes necessary actions is critically important. This study focuses on using deep learning technology for predicting bushfire occurrences using real weather data in any given location. Real-time and off-line weather data was collected using Weather Underground API, from 2012 to 2017 ( N = 128 , 329 ). The obtained weather data are temperature, dew point, pressure, wind speed, wind direction, humidity, and daily rain. An algorithm was developed to collect this data automatically from any destination. Six different optimizer models were analyzed that use in deep learning technology. Then, the comparison was carried out to identify the best model. Selecting an optimizer for training the neural network, in this case, deep learning is a challenging task. Six best optimizers were chosen to compare and identify the best optimizer to estimate potential fire occurrences in given locations. The six optimizers; Adagrad, Adadelta, RMSprop, Adam, Nadam, and SGD were compared based on their processing time, prediction accuracy and error. Our findings suggest Adagrad optimizer provides less prediction time which is a critical factor for fast-spreading bushfires. Our work provides a data collection model for disaster prediction, which could be utilized to collect climatic characteristics and topographical characteristics in with larger samples. The developed methodology could be utilized as a natural disaster prediction model for precise predictions with less error and processing time using real-time data. This study provides an enhanced understanding of finding the locations that fire starts or spot fires which are more likely to occur, and lead to identifying of fire starts that are more likely to spread. [ABSTRACT FROM AUTHOR]

A test of core knowledge within a health sciences topic was developed and validated using the partial credit model of Rasch analysis (Masters 1982). The SOLO Taxonomy (Biggs and Collis 1982) was used as the theoretical basis to determine speech pathology students' depth of understanding of key features of a complex physiological process (swallowing) as depicted in their written descriptions. Rasch analysis revealed those features that fitted the empirical model and those that needed to be revised or discarded. Students' mastery of the retained features was used to calibrate scaled scores that could be employed for a variety of comparative purposes. This study provides evidence that use of the SOLO Taxonomy can be extended to provide precise and reliable quantitative scores. Consequently valid tests of student knowledge in a range of distinct topic areas can be designed to reflect both the quality of student learning as well as its quantity, a feature that offers potential for assessment in general. [ABSTRACT FROM AUTHOR]