Computational Informatics

CSIR is a South African research institution with broad and extensive experience in the domain of fire, ranging from policy work to basic research into fire and ecology. One of the more visible fire-related applications that CSIR has been involved in is known as the Advanced Fire Information System (AFIS), a joint initiative with Eskom, the South African electricity utility. The application utilises results from remotely sensed data to infer fire occurrence and trigger alarms to Eskom operators based on proximity of fire events to Eskom infrastructure, notably transmission lines and towers. This paper describes the Meraka Institute (African Advanced Institute for ICT -a National Research Centre affiliated with CSIR) view of the future of AFIS. Meraka intends to migrate AFIS from a narrowly focussed, 'black-box' application to one servicing users in multiple fire-related scenarios. Future AFIS versions would be based on an open framework of geospatial web services, ontologies and software agents. We aim to draw upon the deep organisational knowledge of fire and fire processes that is held by CSIR and its partners to produce a system that can supply highly tuned, meaningful and customised fire alerts to users. We hope to evolve AFIS from a single use application into an agent-based platform enabling rapid development and deployment of new fire-related applications through concept-based queries of data and knowledge repositories. We believe that AFIS is representative of the evolution that many geospatial applications on the web may have to follow, from being tightly coupled, software dependent applications, through being loosely-coupled, web service and standards-oriented applications to a point where they provide geo-information to the semantic web.

The technological demands required to successfully practice either targeted irrigation control and/or deficit irrigation strategies are currently reliant on numerical models which are often underutilised due to their complexity and low operational focus. A simple and practical real-time control system is proposed using a model-data fusion approach, which integrates information from soil water representation models and heterogeneous sensor data sources. The system uses real-time soil moisture measurements provided by an in situ sensor network to generate site-specific soil water retention curves. This information is then used to predict the rate of soil drying. The decision to irrigate is made when soil water content drops below a pre-defined threshold and when the probability of rainfall is low. A deficit strategy can be incorporated by lowering the irrigation "refill" point and setting the fill amount to a proportion of field capacity. Computer simulations show how significant water savings can be achieved through improved utilisation of rainfall water by plants, spatially targeted irrigation application, and precision timing through adaptive control

The Sensor Web is an emerging technology concept that promises to revolutionise the way water information is collected and disseminated. A Sensor Web is a group of interoperable web services, which all comply with a specific set of information models and interface specifications. The Open Geospatial Consortium (OGC) is developing information models and service interface specifications for Sensor Web Enablement (SWE). These standards and specifications provide the basic building blocks for Sensor Webs. SWE is an approach to break down information silos, improve availability of data from sensors and promote the development of new applications that are driven by real-time real world information.

Key concepts in disaster response are level of preparedness, response times, sustaining the response and coordinating the response. Effective disaster response requires a well-developed command and control framework that promotes the flow of information. The Sensor Web is an emerging technology concept that can enhance the tempo of disaster response. We describe how a satellite-based system for regional wild fire detection is being evolved into a fully-fledged Sensor Web application.

An ever-increasing number of sensor resources are being exposed via the World Wide Web. Discovery, selection and use of these sensors and their observations require a robust sensor information model, but the homogenous description of sensor metadata is a complex and difficult task. Currently, the only available robust model is SensorML, which is intentionally designed in a very generic way. Due to this genericness, interoperability can hardly be achieved without the definition of application profiles that further constrain the use and expressiveness of the root language. So far, such SensorML profiles have only been developed up to a limited extent. This work describes a new approach for defining sensor metadata, the StarFL model. This language follows a more restrictive approach and incorporates concepts from the recently published Semantic Sensor Network Ontology to overcome the key issues users are experiencing with SensorML. StarFL defines a restricted vocabulary and model for s...

CSIR is a South African research institution with broad and extensive experience in the domain of fire, ranging from policy work to basic research into fire and ecology. One of the more visible fire-related applications that CSIR has been involved in is known as the Advanced Fire Information System (AFIS), a joint initiative with Eskom, the South African electricity utility. The application utilises results from remotely sensed data to infer fire occurrence and trigger alarms to Eskom operators based on proximity of fire events to Eskom infrastructure, notably transmission lines and towers. This paper describes the Meraka Institute (African Advanced Institute for ICT – a National Research Centre affiliated with CSIR) view of the future of AFIS. Meraka intends to migrate AFIS from a narrowly focussed, ‘black-box’ application to one servicing users in multiple fire-related scenarios. Future AFIS versions would be based on an open framework of geospatial web services, ontologies and so...

Abstract- An ever-increasing number of sensor resources are being exposed via the World Wide Web. Discovery, selection and use of these sensors and their observations require a robust sensor information model, but the homogenous description of sensor metadata is a complex and difficult task. Currently, the only available robust model is SensorML, which is intentionally designed in a very generic way. Due to this genericness, interoperability can hardly be achieved without the definition of application profiles that further constrain the use and expressiveness of the root language. So far, such SensorML profiles have only been developed up to a limited extent. This work describes a new approach for defining sensor metadata, the StarFL model. This language follows a more restrictive approach and incorporates concepts from the recently published Semantic Sensor Network Ontology to overcome the key issues users are experiencing with SensorML. StarFL defines a restricted vocabulary and m...

In this paper an autonomous feature clustering framework has been proposed for performance and reliability evaluation of an environmental sensor network. Environmental time series were statistically preprocessed to extract multiple semantic features. A novel hybrid clustering framework was designed based on Principal Component Analysis (PCA), Guided Self-Organizing Map (G-SOM), and Fuzzy-C-Means (FCM) to cluster the historical multi-feature space into probabilistic state classes. Finally a dynamic performance annotation mechanism was developed based on Maximum (Bayesian) Probability Rule (MPR) to quantify the performance of an individual sensor node and network. Based on the results from this framework, a "data quality knowledge map" was visualized to demonstrate the effectiveness of this framework.

This paper investigates novel supervised machine learning (SML) techniques for bulk soil moisture estimation using cosmic ray sensor. The cosmic ray soil moisture measuring probes are deployed across Australia as a part of CosmOz sensor network. These probes are brand new sensing technology still evaluated. The primary purpose of this paper is to find an alternative well-established SML-based method to estimate bulk soil moisture directly from the cosmic ray sensors that would effectively replace the current calibration equations. The second aspect of this paper is to find an alternative method to replace the cosmic ray sensor's current expensive and timeconsuming field soil sample collection protocol. Data collected over 350 consecutive days from Australian Water Availability Project (AWAP) database and Hydroinnova CRS-1000 cosmic ray soil moisture probe deployed in Tullochgorum, Tasmania are used in this paper. Prediction performances of the four supervised estimators, such as sugano type adaptive neuro-fuzzy inference system (S-ANFIS), multilayer perceptron network, probabilistic neural network, and radial basis function network are evaluated using training and testing paradigms. The best result indicates that S-ANFIS is able to match the results achieved using existing calibration equations with a 87% accuracy. Secondly, AWAP data trained S-ANFIS is able to predict bulk soil moisture directly from cosmic ray neutron counts with a 92% accuracy without using any collected field sample-based measurements. Finally, a novel method is also developed to produce an estimated area average bulk soil moisture grid surface map based on multiple ANFIS and cubic grid surface interpolation. Index Terms-adaptive neuro-fuzzy inference system (ANFIS), cosmic ray sensor, multilayer perceptron network (MLPN), probabilistic neural network (PNN), radial basis function network (RBFN), soil moisture map, supervised machine learning. I. INTRODUCTION T HE Australian Cosmic Ray Sensor Soil Moisture Monitoring Network [1]-[4] is a near-real time continental scale soil moisture monitoring system being developed by the Commonwealth Scientific and Industrial Research Organization, Monash University, Charles Darwin University and the University of New South Wales. CosmOz aims to test the utility of Hydroinnova cosmic ray soil moisture probes

This paper investigates a novel technique based on Fuzzy C means (FCM) algorithm and Adaptive Neuro-Fuzzy Inference System (ANFIS) to estimate soil moisture using cosmic ray soil moisture probes deployed across Australia. These probes are a brand new sensing technology still being evaluated. Preliminary results indicate ANFIS is able to estimate soil moisture with 90% accuracy.

This paper combines data from soil moisture capacitance probes and a cosmic-ray neutron probe in a fuzzy inference system to estimate spatially variable soil moisture in a ∼28 ha circular area at an hourly interval in northeast Tasmania, Australia. The technique uses hourly counts of cosmic-ray neutrons, a network of 25 capacitance probes measuring soil moisture at half hourly intervals and at five depths (0-50 cm), and a multiple adaptive neuro-fuzzy inference system. We quantified soil moisture in the top portion of the soil during wet and dry periods for training and testing periods. After training, the technique provided reliable estimates of temporal pattern of soil moisture at 10-and 20-cm depths during a wet period using input data only from the cosmic-ray neutron probe. There was overprediction of soil moisture during a dry period, which suggests a longer training period representative of the full range of likely conditions might be required. Spatial maps of soil water content produced from the single cosmic-ray neutron probe were similar to those of the capacitance probe.

Ongoing robotic systems are primarily undertaken by large organisations and are closed systems. We describe an extension to the cloud robotics concept that encourages reuse of sensor data collected from robots and sensor networks, and eases the economic and technical burden on small industry and government organisations. This paper describes the innovations currently in development by CSIRO that contribute to improved sustainability, scalability and sensor discovery in robotics using a cloud based data management system. Sensor Web and Linked Open Data principles are implemented to provide standardised interfaces to data sharing and robot tasking.

With the increasing complexity of hydrologic problems, data collection and data analysis are often carried out in distributed heterogeneous systems. Therefore it is critical for users to determine the origin of data and its trustworthiness. Provenance describes the information life cycle of data products. It has been recognised as one of the most promising methods to improve data transparency. However, due to the complexity of the information life cycle involved, it is a challenge to query the provenance information which may be generated by distributed systems, with different vocabularies and conventions, and may involve knowledge of multiple domains. In this paper, we present a semantic knowledge management framework that tracks and integrates provenance information across distributed heterogeneous systems. It is underpinned by the Integrated Knowledge model that describes the domain knowledge and the provenance information involved in the information life cycle of a particular data product. We evaluate the proposed framework in the context of two real-world water information systems.

Objectives: To conduct a systematic survey of published techniques for automated diagnosis and prognosis of COVID-19 diseases using medical imaging, assessing the validity of reported performance and investigating the proposed clinical use-case. To conduct a scoping review into the authors publishing such work. Methods: The Scopus database was queried and studies were screened for article type, and minimum source normalized impact per paper and citations, before manual relevance assessment and a bias assessment derived from a subset of the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). The number of failures of the full CLAIM was adopted as a surrogate for risk-of-bias. Methodological and performance measurements were collected from each technique. Each study was assessed by one author. Comparisons were evaluated for significance with a two-sided independent t-test. Findings: Of 1002 studies identified, 390 remained after screening and 81 after relevance and bias exclusion. The ratio of exclusion for bias was 71%, indicative of a high level of bias in the field. The mean number of CLAIM failures per study was 8.3 ± 3.9 [1,17] (mean ± standard deviation [min,max]). 58% of methods performed diagnosis versus 31% prognosis. Of the diagnostic methods, 38% differentiated COVID-19 from healthy controls. For diagnostic techniques, area under the receiver operating curve (AUC) = 0.924 ± 0.074 [0.810,0.991] and accuracy = 91.7% ± 6.4 [79.0,99.0]. For prognostic techniques, AUC = 0.836 ± 0.126 [0.605,0.980] and accuracy = 78.4% ± 9.4 [62.5,98.0]. CLAIM failures did not correlate with performance, providing confidence that the highest results were not driven by biased papers. Deep learning techniques reported higher AUC (p < 0.05) and accuracy (p < 0.05), but no difference in CLAIM failures was identified. Interpretation: A majority of papers focus on the less clinically impactful diagnosis task, contrasted with prognosis, with a significant portion performing a clinically unnecessary task of differentiating COVID-19 from healthy. Authors should consider the clinical scenario in which their work would be deployed when developing techniques. Nevertheless, studies report superb performance in a potentially impactful application. Future work is warranted in translating techniques into clinical tools.

Terrestrial analogues can provide essential scientific information and technology validation to assist future crewed missions to the Martian surface. This paper analyses the recent literature since 2010 in this area, highlighting key topics, authors, and research groups. It reviews analogue locations, missions, the scientific impact from research activities. The findings indicate that permanent analogue sites enable reproducible science and objective comparison between studies. A standard, open registry of analogue facilities, and associated peer-reviewed research may lead to accelerated and better targeted analogue research.

Several approaches to develop a robust sensor information model have been attempted. For example, the Open Geospatial Consortium (OGC) has developed standard information models to describe sensor observations (Observations and Measurements (O&M)) and sensor devices and procedures to generate observations (Sensor Modelling Language (SensorML)). SensorML was developed primarily to support the description of sensors on moving platforms (e.g. earth observation satellites and aircraft), where the main issue is computing the location of the sensed area on the ground. Though SensorML is very generic and provides a functional view of sensors, it can only be used through the Java library developed by its designers. SensorML is very flexible and allows sensors to be described in multiple ways. This creates interoperability problems at the encoding level. Another sensor information model is the Semantic Sensor Network Ontology (SSNO) developed by the W3C Semantic Sensor Network Incubator Group...

Technological advances are transforming agriculture in many parts of the world. Despite the importance of agriculture to its economy, Australia lags behind other advanced economies in the adoption of digital agricultural technology. The country risks losing its comparative advantage due to a weak policy around digital agriculture. This study combines network analysis and natural language processing to assess 654 public submissions to six government inquiries addressing agricultural innovation, the digital economy, and rural broadband communication networks, held between 2016 and 2018. The analysis shows there is no consistent narrative driving policy development around digital agriculture. A fragmented policy landscape is a concern because it means that current and emerging policies may not address key issues, resulting in sub-optimal outcomes for Australian agriculture.