Deep Learning Based Over-the-Air Training of Wireless Communication Systems without Feedback.

In trainable wireless communications systems, the use of deep learning for over-the-air training aims to address the discontinuity in backpropagation learning caused by the channel environment. The primary methods supporting this learning procedure either directly approximate the backpropagation gradients using techniques derived from reinforcement learning, or explicitly model the channel environment by training a generative channel model. In both cases, over-the-air training of transmitter and receiver requires a feedback channel to sound the channel environment and obtain measurements of the learning objective. The use of continuous feedback not only demands extra system resources but also makes the training process more susceptible to adversarial attacks. Conversely, opting for a feedback-free approach to train the models over the forward link, exclusively on the receiver side, could pose challenges to reliably end the training process without intermittent testing over the actual channel environment. In this article, we propose a novel method for the over-the-air training of wireless communication systems that does not require a feedback channel to train the transmitter and receiver. Random samples are transmitted through the channel environment to train a mixture density network to approximate the channel distribution on the receiver side of the network. The transmitter and receiver models are trained with the resulting channel model, and the transmitter can be deployed after training. We show that the block error rate measurements obtained with the simulated channel are suitable for monitoring as a stopping criterion during the training process. The resulting method is demonstrated to have equivalent performance to the end-to-end autoencoder training on small message sequences.

Channel-Agnostic Training of Transmitter and Receiver for Wireless Communications.

Wireless communications systems are traditionally designed by independently optimising signal processing functions based on a mathematical model. Deep learning-enabled communications have demonstrated end-to-end design by jointly optimising all components with respect to the communications environment. In the end-to-end approach, an assumed channel model is necessary to support training of the transmitter and receiver. This limitation has motivated recent work on over-the-air training to explore disjoint training for the transmitter and receiver without an assumed channel. These methods approximate the channel through a generative adversarial model or perform gradient approximation through reinforcement learning or similar methods. However, the generative adversarial model adds complexity by requiring an additional discriminator during training, while reinforcement learning methods require multiple forward passes to approximate the gradient and are sensitive to high variance in the error signal. A third, collaborative agent-based approach relies on an echo protocol to conduct training without channel assumptions. However, the coordination between agents increases the complexity and channel usage during training. In this article, we propose a simpler approach for disjoint training in which a local receiver model approximates the remote receiver model and is used to train the local transmitter. This simplified approach performs well under several different channel conditions, has equivalent performance to end-to-end training, and is well suited to adaptation to changing channel environments.

Explainable AI approach with original vegetation data classifies spatio-temporal nitrogen in flows from ungauged catchments to the Great Barrier Reef.

Transfer of processed data and parameters to ungauged catchments from the most similar gauged counterpart is a common technique in water quality modelling. But catchment similarities for Dissolved Inorganic Nitrogen (DIN) are ill posed, which affects the predictive capability of models reliant on such methods for simulating DIN. Spatial data proxies to classify catchments for most similar DIN responses are a demonstrated solution, yet their applicability to ungauged catchments is unexplored. We adopted a neural network pattern recognition model (ANN-PR) and explainable artificial intelligence approach (SHAP-XAI) to match all ungauged catchments that flow to the Great Barrier Reef to gauged ones based on proxy spatial data. Catchment match suitability was verified using a neural network water quality (ANN-WQ) simulator trained on gauged catchment datasets, tested by simulating DIN for matched catchments in unsupervised learning scenarios. We show that discriminating training data to DIN regime benefits ANN-WQ simulation performance in unsupervised scenarios ( p< 0.05). This phenomenon demonstrates that proxy spatial data is a useful tool to classify catchments with similar DIN regimes. Catchments lacking similarity with gauged ones are identified as priority monitoring areas to gain observed data for all DIN regimes in catchments that flow to the Great Barrier Reef, Australia.

Automated detection of airflow obstructive diseases: A systematic review of the last decade (2013-2022).

BACKGROUND AND OBJECTIVE: Obstructive airway diseases, including asthma and Chronic Obstructive Pulmonary Disease (COPD), are two of the most common chronic respiratory health problems. Both of these conditions require health professional expertise in making a diagnosis. Hence, this process is time intensive for healthcare providers and the diagnostic quality is subject to intra- and inter- operator variability. In this study we investigate the role of automated detection of obstructive airway diseases to reduce cost and improve diagnostic quality. METHODS: We investigated the existing body of evidence and applied Preferred Reporting Items for Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to search records in IEEE, Google scholar, and PubMed databases. We identified 65 papers that were published from 2013 to 2022 and these papers cover 67 different studies. The review process was structured according to the medical data that was used for disease detection. We identified six main categories, namely air flow, genetic, imaging, signals, and miscellaneous. For each of these categories, we report both disease detection methods and their performance. RESULTS: We found that medical imaging was used in 14 of the reviewed studies as data for automated obstructive airway disease detection. Genetics and physiological signals were used in 13 studies. Medical records and air flow were used in 9 and 7 studies, respectively. Most papers were published in 2020 and we found three times more work on Machine Learning (ML) when compared to Deep Learning (DL). Statistical analysis shows that DL techniques achieve higher Accuracy (ACC) when compared to ML. Convolutional Neural Network (CNN) is the most common DL classifier and Support Vector Machine (SVM) is the most widely used ML classifier. During our review, we discovered only two publicly available asthma and COPD datasets. Most studies used private clinical datasets, so data size and data composition are inconsistent. CONCLUSIONS: Our review results indicate that Artificial Intelligence (AI) can improve both decision quality and efficiency of health professionals during COPD and asthma diagnosis. However, we found several limitations in this review, such as a lack of dataset consistency, a limited dataset and remote monitoring was not sufficiently explored. We appeal to society to accept and trust computer aided airflow obstructive diseases diagnosis and we encourage health professionals to work closely with AI scientists to promote automated detection in clinical practice and hospital settings.

Enhanced joint hybrid deep neural network explainable artificial intelligence model for 1-hr ahead solar ultraviolet index prediction.

BACKGROUND AND OBJECTIVE: Exposure to solar ultraviolet (UV) radiation can cause malignant keratinocyte cancer and eye disease. Developing a user-friendly, portable, real-time solar UV alert system especially or wearable electronic mobile devices can help reduce the exposure to UV as a key measure for personal and occupational management of the UV risks. This research aims to design artificial intelligence-inspired early warning tool tailored for short-term forecasting of UV index (UVI) integrating satellite-derived and ground-based predictors for Australian hotspots receiving high UV exposures. The study further improves the trustworthiness of the newly designed tool using an explainable artificial intelligence approach. METHODS: An enhanced joint hybrid explainable deep neural network model (called EJH-X-DNN) is constructed involving two phases of feature selection and hyperparameter tuning using Bayesian optimization. A comprehensive assessment of EJH-X- DNN is conducted with six other competing benchmarked models. The proposed model is explained locally and globally using robust model-agnostic explainable artificial intelligence frameworks such as Local Interpretable Model-Agnostic Explanations (LIME), Shapley additive explanations (SHAP), and permutation feature importance (PFI). RESULTS: The newly proposed model outperformed all benchmarked models for forecasting hourly horizons UVI, with correlation coefficients of 0.900, 0.960, 0.897, and 0.913, respectively, for Darwin, Alice Springs, Townsville, and Emerald hotspots. According to the combined local and global explainable model outcomes, the site-based results indicate that antecedent lagged memory of UVI and solar zenith angle are influential features. Predictions made by EJH-X-DNN model are strongly influenced by factors such as ozone effect, cloud conditions, and precipitation. CONCLUSION: With its superiority and skillful interpretation, the UVI prediction system reaffirms its benefits for providing real-time UV alerts to mitigate risks of skin and eye health complications, reducing healthcare costs and contributing to outdoor exposure policy.

Brain tumor detection and screening using artificial intelligence techniques: Current trends and future perspectives.

A brain tumor is an abnormal mass of tissue located inside the skull. In addition to putting pressure on the healthy parts of the brain, it can lead to significant health problems. Depending on the region of the brain tumor, it can cause a wide range of health issues. As malignant brain tumors grow rapidly, the mortality rate of individuals with this cancer can increase substantially with each passing week. Hence it is vital to detect these tumors early so that preventive measures can be taken at the initial stages. Computer-aided diagnostic (CAD) systems, in coordination with artificial intelligence (AI) techniques, have a vital role in the early detection of this disorder. In this review, we studied 124 research articles published from 2000 to 2022. Here, the challenges faced by CAD systems based on different modalities are highlighted along with the current requirements of this domain and future prospects in this area of research.

Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach.

Quantum machine learning (QML) has attracted significant research attention over the last decade. Multiple models have been developed to demonstrate the practical applications of the quantum properties. In this study, we first demonstrate that the previously proposed quanvolutional neural network (QuanvNN) using a randomly generated quantum circuit improves the image classification accuracy of a fully connected neural network against the Modified National Institute of Standards and Technology (MNIST) dataset and the Canadian Institute for Advanced Research 10 class (CIFAR-10) dataset from 92.0% to 93.0% and from 30.5% to 34.9%, respectively. We then propose a new model referred to as a Neural Network with Quantum Entanglement (NNQE) using a strongly entangled quantum circuit combined with Hadamard gates. The new model further improves the image classification accuracy of MNIST and CIFAR-10 to 93.8% and 36.0%, respectively. Unlike other QML methods, the proposed method does not require optimization of the parameters inside the quantum circuits; hence, it requires only limited use of the quantum circuit. Given the small number of qubits and relatively shallow depth of the proposed quantum circuit, the proposed method is well suited for implementation in noisy intermediate-scale quantum computers. While promising results were obtained by the proposed method when applied to the MNIST and CIFAR-10 datasets, a test against a more complicated German Traffic Sign Recognition Benchmark (GTSRB) dataset degraded the image classification accuracy from 82.2% to 73.4%. The exact causes of the performance improvement and degradation are currently an open question, prompting further research on the understanding and design of suitable quantum circuits for image classification neural networks for colored and complex data.

Developing a novel hybrid method based on dispersion entropy and adaptive boosting algorithm for human activity recognition.

BACKGROUND: With the rapid development of technology, human activity recognition (HAR) from sensor data has become a key element for many real-world applications, such as healthcare, disease diagnosis and smart home systems. Although there have been several studies conducted on HAR, traditional methods remain inadequate in balancing efficiency, accuracy and speed. Moreover, existing studies have not identified a solution to managing imbalanced data in different activities groups of HAR, although that is major issue in determining satisfactory performance. METHODS: this study proposes a new hybrid approach involving hierarchical dispersion entropy (HDE) and Adaptive Boosting with convolutional neural networks (AdaB_CNN) for classifying human activities, such as running downstairs/upstairs, walking and other daily activities, from sensor data. The proposed model is comprised of the following steps: firstly, HAR data are segmented into intervals using a sliding window technique, and then the segmented data are decomposed into different frequency bands. Following this, the dispersion entropy of different frequency bands is computed to produce a feature vector set. Then, the extracted features are reduced using Joint Approximate Diagonalization of Eigenmatrices (JADE) to further eliminate redundant information. The final feature vector set is then fed into the AdaB_CNN method to classify human activities. RESULTS: The proposed approach is tested on three publicly available datasets: WISDM, UCI_HAR 2012, and PAMAP2. The experimental results demonstrate that the proposed model attains a superior performance in HAR to most current methods. CONCLUSIONS: The findings reveal that the proposed HDE based AdaB_CNN model has the capability to efficiently recognize different activities from sensor technologies. It has the potential to be implemented in a hardware system to classify human activity.

Pattern recognition describing spatio-temporal drivers of catchment classification for water quality.

Classification using spatial data is foundational for hydrological modelling, particularly for ungauged areas. However, models developed from classified land use drivers deliver inconsistent water quality results for the same land uses and hinder decision-making guided by those models. This paper explores whether the temporal variation of water quality drivers, such as season and flow, influence inconsistency in the classification, and whether variability is captured in spatial datasets that include original vegetation to represent the variability of biotic responses in areas mapped with the same land use. An Artificial Neural Network Pattern Recognition (ANN-PR) method is used to match catchments by Dissolved Inorganic Nitrogen (DIN) patterns in water quality datasets partitioned into Wet vs Dry Seasons and Increasing vs Retreating flows. Explainable artificial intelligence approaches are then used to classify catchments via spatial feature datasets for each catchment. Catchments matched for sharing patterns in both spatial data and DIN datasets were corroborated and the benefit of partitioning the observed DIN dataset evaluated using Kruskal Wallis method. The highest corroboration rates for spatial data classification with DIN classification were achieved with seasonal partitioning of water quality datasets and significant independence (p < 0.001 to 0.026) from non-partitioned datasets was achieved. This study demonstrated that DIN patterns fall into three categories suited to classification under differing temporal scales with corresponding vegetation types as the indicators. Categories 1 and 3 included dominance of woodlands in their datasets and catchments suited to classify together change depending on temporal scale of the data. Category 2 catchments were dominated by vineforest and classified catchments did not change under different temporal scales. This demonstrates that including original vegetation as a proxy for differences in DIN patterns will help guide future classification where only spatially mapped data is available for ungauged catchments and will better inform data needs for water modelling.

The Great 2011 Thailand flood disaster revisited: Could it have been mitigated by different dam operations based on better weather forecasts?

This paper revisits the 2011 Great Flood in central Thailand to answer one of the hotly debated questions at the time "Could the operation decisions of the flood control structures substantially mitigate the flood impacts in the downstream areas?". Using a numerical modeling approach, we develop a hypothesis such that the two upstream dam reservoirs: Bhumibol and Sirikit had more accurately forecasted the typhoon-triggered abnormal rainfall volumes and released more water earlier to save the storage capacity via 17 different scenarios or alternative operation schemes. We subsequently quantify the potential improvements, or reduced flood impacts in the downstream catchments, solely by changing the operation schemes of these two dam reservoirs, with all other conditions remaining unchanged. We observed that changing the operation schemes could have reduced only the flood depth while offering very limited improvements in terms of inundated areas for the lower Chao Phraya River Basin. Among 17 scenarios simulated, the inundated areas could have been reduced at most by 3.68%. This result justifies the limited role of these mega structures in the upstream during the disaster on one hand, while pointing to the necessity of handling local rainfall differently on the other. The paper expands the discussion into how the government of Thailand has drawn the lessons from the 2011 flood to better prepare themselves against the lurking flood risk in 2021, also triggered by tropical cyclones. The highlighted initiatives, both technical and institutional, could have provided important references for the large river catchment managers in Southeast Asia and with implications of our method beyond the present application region.

Basin management inspiration from impacts of alternating dry and wet conditions on water production and carbon uptake in Murray-Darling Basin.

The impacts of alternating dry and wet conditions on water production and carbon uptake at different scales remain unclear, which limits the integrated management of water and carbon. We quantified the response of runoff efficiency (RE) and plant water-use efficiency (PWUE) to a typical shift from dry to wet episode of 2003-2014 in Australia's Murray-Darling basin using good and specific data products for local application, including Australian Water Availability Project, Penman-Monteith-Leuning Evapotranspiration V2 product, MODIS MCD12Q1 V6 Land Cover Type and MODIS MOD17A3 V055 GPP product. The results show that there are significant power function relationships between RE and precipitation for basin and all ecosystems, while the PWUE had a negative quadratic correlation with precipitation and satisfied the significance levels of 0.05 for basin and the ecosystems except the grassland and cropland. The shrubs can achieve the best water production and carbon uptake under dry conditions, while the evergreen broadleaf trees and evergreen needleleaf trees can obtain the best water production and carbon uptake in wet conditions, respectively. These findings help integrated basin management for balancing water resource production and climate change mitigation.

Coupled online sequential extreme learning machine model with ant colony optimization algorithm for wheat yield prediction.

Inadequate agricultural planning compounded by inaccurate predictions results in an inflated local market rate and prompts higher importation of wheat. To tackle this problem, this research has designed two-phase universal machine learning (ML) model to predict wheat yield (Wpred), utilizing 27 agricultural counties' data within the Agro-ecological zone. The universal model, online sequential extreme learning machines coupled with ant colony optimization (ACO-OSELM) is developed, by incorporating the significant annual yield data lagged at (t - 1) as the model's predictor to generate future yield at 6 test stations. In the first phase, ACO is adopted to search for suitable, statistically relevant data stations for model training, and the corresponding test station by virtue of a feature selection strategy. An annual wheat yield time-series input dataset is constructed utilizing data from each selected training station (1981-2013) and applied against 6 test stations (with each case modelled with 26 station data as the input) to evaluate the hybrid ACO-OSELM model. The partial autocorrelation function is implemented to deduce statistically significant lagged data, and OSELM is applied to generate Wpred. The two-phase hybrid ACO-OSELM model is tested within the 6 agricultural districts (represented as stations) of Punjab province, Pakistan and the results are benchmarked with extreme learning machine (ELM) and random forest (RF) integrated with ACO (i.e., hybrid ACO-ELM and hybrid ACO-RF models, respectively). The performance of the ACO-OSELM model was proven to be good in comparison to ACO-ELM and ACO-RF models. The hybrid ACO-OSELM model revealed its potential to be implemented as a decision-making system for crop yield prediction in areas where a significant association with the historical agricultural crop is well-established.

New double decomposition deep learning methods for river water level forecasting.

Forecasting river water levels or streamflow water levels (SWL) is vital to optimising the practical and sustainable use of available water resources. We propose a new deep learning hybrid model for SWL forecasting using convolutional neural networks (CNN), bi-directional long-short term memory (BiLSTM), and ant colony optimisation (ACO) with a two-phase decomposition approach at the 7-day, 14-day, and 28-day forecast horizons. The newly developed CBILSTM method is coupled with complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and variational mode decomposition (VMD) methods to extract the most significant features within predictor variables to build a hybrid CVMD-CBiLSTM model. We integrate three distinct datasets (satellite-derived, climate mode indices, and ground-based meteorological observations) to improve the forecasting capability of the CVMD-CBiLSTM model, applied at nineteen different gauging stations in the Australian Murray River system. This proposed model returns a significantly accurate performance with ~98% of all prediction errors within less than ±0.020 m and a low relative root mean square of ~0.08%, demonstrating its superiority over several benchmark models. The results show that using the new hybrid deep learning algorithm with ACO feature selection can significantly improve the accuracy of forecasted river water levels, and therefore, the method is attractive for adopting remote sensing data to the model ground-based river flow for strategic water savings planning initiatives and dealing with climate change-induced extreme events such as drought events.

Integrative artificial intelligence models for Australian coastal sediment lead prediction: An investigation of in-situ measurements and meteorological parameters effects.

Heavy metals (HMs) such as Lead (Pb) have played a vital role in increasing the sediments of the Australian bay's ecosystem. Several meteorological parameters (i.e., minimum, maximum and average temperature (Tmin, Tmax and TavgoC), rainfall (Rn mm) and their interactions with the other batch HMs, are hypothesized to have high impact for the decision-making strategies to minimize the impacts of Pb. Three feature selection (FS) algorithms namely the Boruta method, genetic algorithm (GA) and extreme gradient boosting (XGBoost) were investigated to select the highly important predictors for Pb concentration in the coastal bay sediments of Australia. These FS algorithms were statistically evaluated using principal component analysis (PCA) Biplot along with the correlation metrics describing the statistical characteristics that exist in the input and output parameter space of the models. To ensure a high accuracy attained by the applied predictive artificial intelligence (AI) models i.e., XGBoost, support vector machine (SVM) and random forest (RF), an auto-hyper-parameter tuning process using a Grid-search approach was also implemented. Cu, Ni, Ce, and Fe were selected by all the three applied FS algorithms whereas the Tavg and Rn inputs remained the essential parameters identified by GA and Boruta. The order of the FS outcome was XGBoost > GA > Boruta based on the applied statistical examination and the PCA Biplot results and the order of applied AI predictive models was XGBoost-SVM > GA-SVM > Boruta-SVM, where the SVM model remained at the top performance among the other statistical metrics. Based on the Taylor diagram for model evaluation, the RF model was reflected only marginally different so overall, the proposed integrative AI model provided an evidence a robust and reliable predictive technique used for coastal sediment Pb prediction.

An interplay of soil salinization and groundwater degradation threatening coexistence of oasis-desert ecosystems.

In salt-affected and groundwater-fed oasis-desert systems, water and salt balance is critically important for stable coexistence of oasis-desert ecosystems, especially in the context of anthropogenic-induced over-development and perturbations due to climate variability that affects the sustainability of human-natural systems. Here, an investigation of the spatio-temporal variability of soil salinity and groundwater dynamics across four different hydrological regions in oasis-desert system is performed. An evaluation of the effects of soil salinization and groundwater degradation interplays on the coexistence of oasis-desert ecosystems in northwestern China is undertaken over 1995-2020, utilizing comprehensive measurements and ecohydrological modelling framework. We note that the process of salt migration and accumulation across different landscapes in oasis-desert system is reshaping, with soil salinization accelerating especially in water-saving agricultural irrigated lands. The continuous decline in groundwater tables, dramatic shifts in groundwater flow patterns and significant degradation of groundwater quality are occurring throughout the watershed. Worse so, a clear temporal-spatial relationship between soil salinization and groundwater degradation appearing to exacerbate the regional water-salt imbalance. Also, the eco-environmental flows are reaching to their limit with watershed closures, although these progressions were largely hidden by regional precipitation and streamflow variability. The oasis-desert ecosystems tend to display bistable dynamics with two preferential configurations of bare and vegetated soils, and soil salinization and groundwater degradation interplays are causing catastrophic shift in the oasis-desert ecosystems. The results highlight the importance of regional adaptive water and salt management to maintain the coexistence of oasis-desert ecosystems in arid areas.

Classification of catchments for nitrogen using Artificial Neural Network Pattern Recognition and spatial data.

In hydrological modelling, classification of catchments is a fundamental task for overcoming deficits in observational datasets. Most attention on this issue has focussed on identifying the catchments with similar hydrological responses for streamflow. Yet, effective methods for catchment classification are currently lacking in respect to Dissolved Inorganic Nitrogen (DIN), a water quality constituent that, at increasing concentrations, is threatening nutrient sensitive environments. Pattern recognition, using standard Artificial Neural Network algorithm is applied, as a novel approach to classify datasets that are considered to be suitable proxies for biological and anthropogenic drivers of observed DIN releases. Eleven gauged Great Barrier Reef (GBR) catchments within Queensland Australia are classified using spatial datasets extracted from ecosystem (e.g. original ecosystem responses to biogeographic, land zone, land form, and soil type attributes) and land use maps. To evaluate the performance of the examined spatial datasets as a proxy for deductive classification, the classification process is repeated inductively, using observed DIN and streamflow data from gauging stations. The ANN-PR method is seen to generate the same classification score format for the differing dataset types, and this facilitates a direct comparison for model output for observed data corroborations. The Kruskal-Wallis test for independence, at p > 0.05, identifies the deductive classification approach as a predictor for classification using DIN observations, which lacks an independence from each other at a p value of 0.01 and 0.02. This study concludes that an ANN-PR method can integrate the ecosystem and land use mapping data to deductively classify the GBR catchments into four regions that also have similar patterns of DIN concentrations. Due to the uniform availability of the mapping data, the findings provide a sound basis for further investigations into the transposing of knowledge from gauged catchments to ungauged areas.

Application of Deep Learning Models for Automated Identification of Parkinson's Disease: A Review (2011-2021).

Parkinson's disease (PD) is the second most common neurodegenerative disorder affecting over 6 million people globally. Although there are symptomatic treatments that can increase the survivability of the disease, there are no curative treatments. The prevalence of PD and disability-adjusted life years continue to increase steadily, leading to a growing burden on patients, their families, society and the economy. Dopaminergic medications can significantly slow down the progression of PD when applied during the early stages. However, these treatments often become less effective with the disease progression. Early diagnosis of PD is crucial for immediate interventions so that the patients can remain self-sufficient for the longest period of time possible. Unfortunately, diagnoses are often late, due to factors such as a global shortage of neurologists skilled in early PD diagnosis. Computer-aided diagnostic (CAD) tools, based on artificial intelligence methods, that can perform automated diagnosis of PD, are gaining attention from healthcare services. In this review, we have identified 63 studies published between January 2011 and July 2021, that proposed deep learning models for an automated diagnosis of PD, using various types of modalities like brain analysis (SPECT, PET, MRI and EEG), and motion symptoms (gait, handwriting, speech and EMG). From these studies, we identify the best performing deep learning model reported for each modality and highlight the current limitations that are hindering the adoption of such CAD tools in healthcare. Finally, we propose new directions to further the studies on deep learning in the automated detection of PD, in the hopes of improving the utility, applicability and impact of such tools to improve early detection of PD globally.

Streamflow prediction using an integrated methodology based on convolutional neural network and long short-term memory networks.

Streamflow (Qflow) prediction is one of the essential steps for the reliable and robust water resources planning and management. It is highly vital for hydropower operation, agricultural planning, and flood control. In this study, the convolution neural network (CNN) and Long-Short-term Memory network (LSTM) are combined to make a new integrated model called CNN-LSTM to predict the hourly Qflow (short-term) at Brisbane River and Teewah Creek, Australia. The CNN layers were used to extract the features of Qflow time-series, while the LSTM networks use these features from CNN for Qflow time series prediction. The proposed CNN-LSTM model is benchmarked against the standalone model CNN, LSTM, and Deep Neural Network models and several conventional artificial intelligence (AI) models. Qflow prediction is conducted for different time intervals with the length of 1-Week, 2-Weeks, 4-Weeks, and 9-Months, respectively. With the help of different performance metrics and graphical analysis visualization, the experimental results reveal that with small residual error between the actual and predicted Qflow, the CNN-LSTM model outperforms all the benchmarked conventional AI models as well as ensemble models for all the time intervals. With 84% of Qflow prediction error below the range of 0.05 m3 s-1, CNN-LSTM demonstrates a better performance compared to 80% and 66% for LSTM and DNN, respectively. In summary, the results reveal that the proposed CNN-LSTM model based on the novel framework yields more accurate predictions. Thus, CNN-LSTM has significant practical value in Qflow prediction.

The role of internal transcribed spacer 2 secondary structures in classifying mycoparasitic Ampelomyces.

Many fungi require specific growth conditions before they can be identified. Direct environmental DNA sequencing is advantageous, although for some taxa, specific primers need to be used for successful amplification of molecular markers. The internal transcribed spacer region is the preferred DNA barcode for fungi. However, inter- and intra-specific distances in ITS sequences highly vary among some fungal groups; consequently, it is not a solely reliable tool for species delineation. Ampelomyces, mycoparasites of the fungal phytopathogen order Erysiphales, can have ITS genetic differences up to 15%; this may lead to misidentification with other closely related unknown fungi. Indeed, Ampelomyces were initially misidentified as other pycnidial mycoparasites, but subsequent research showed that they differ in pycnidia morphology and culture characteristics. We investigated whether the ITS2 nucleotide content and secondary structure was different between Ampelomyces ITS2 sequences and those unrelated to this genus. To this end, we retrieved all ITS sequences referred to as Ampelomyces from the GenBank database. This analysis revealed that fungal ITS environmental DNA sequences are still being deposited in the database under the name Ampelomyces, but they do not belong to this genus. We also detected variations in the conserved hybridization model of the ITS2 proximal 5.8S and 28S stem from two Ampelomyces strains. Moreover, we suggested for the first time that pseudogenes form in the ITS region of this mycoparasite. A phylogenetic analysis based on ITS2 sequences-structures grouped the environmental sequences of putative Ampelomyces into a different clade from the Ampelomyces-containing clades. Indeed, when conducting ITS2 analysis, resolution of genetic distances between Ampelomyces and those putative Ampelomyces improved. Each clade represented a distinct consensus ITS2 S2, which suggested that different pre-ribosomal RNA (pre-rRNA) processes occur across different lineages. This study recommends the use of ITS2 S2s as an important tool to analyse environmental sequencing and unveiling the underlying evolutionary processes.