This Pilot project aims to demonstrate the AquaWatch system concept for Australian inland and estuarine water bodies. This Pilot project is one of the ‘testbeds’ for new digital monitoring approaches to integrate and visualise ground-based sensor and multiple satellites data streams, combined with modelling application to provide spatially resolved 24/7 information on inland water quality conditions and provide short-term forecasting capability.

In this pilot we will integrate tools and processes for analysing, modelling and forecasting toxic algal bloom. It will highlight the scientific basis for inland water quality monitoring in a multi-sensor space-based system, including crosscalibration process and thereby validating the use of AquaWatch within the Murray-Darling Basin (MDB).

The output will be a ‘a prototype ground-to-space water quality monitoring and forecasting tool’ which is modular and scalable and will inform future operational monitoring and forecasting of toxic algal blooms in the whole of Australian freshwater bodies. This will include a calibrated EO sensor (on-ground and satellite) based BGA blooms detection and monitoring, a prototype computer-based model of blooms forecasting and spatial distribution/maps (dashboard) of waterbodies for a short-term bloom likelihood along with an alert system. Background data on water profile temperature, local meteorological parameters, Chlorophyll-a concentration and cyanobacteria cell counts will be used to develop the prototype early detection and forecasting tools for cyanobacteria biovolume (cell counts) used as triggers for alert levels. This forms an integral part of the AquaWatch mission demonstrating values of an EO based, integrated digital forecasting system to end-user groups for their benefit and adoption. The chlorophyll-a/cell count based results are expected to be used by a wider end-user groups eg., utilities, catchment water managers, river operators, River/Lake tourism and recreation industry, Irrigation industry, aquaculture and mining industries to better manage water bodies. For example, the environmental cost of toxic algal blooms in the Murray River was estimated at $240M/bloom (2010 Ernst & Young Australia report). Results from this project will directly inform operational policy to minimise toxic algal megaevents in future in the Australian inland waters.

An AquaWatch Pilot which is aimed at supporting the Aquaculture Industry in the Spencer Gulf, and the associated need for monitoring environmental impact. This pilot project aims to demonstrate the integration of in-situ sensor data streams and satellite water quality products.

Project activity: This pilot project, working closely with state government agencies and aqua-culturalists, will demonstrate the potential benefits of data derived from in-situ sensors (Hydraspectra, weather station) and earth observation satellites (sentinel 2, LandSat-8) to integrate and visualise multiple space-based observations (maps of sediment, dissolved carbon, chlorophyll-a and diffuse attenuation of light) and ground-based sensor water quality data (temperature, salinity, fluorescence, backscattering, turbidity and hyperspectral reflectance) streams, combined with hydrodynamic model outputs (salinity, temperature, stratification and current vectors).

Expected outputs and outcomes: Project result will be a demonstrator data processing, integration and visualisation tool to support environmental monitoring and sustainable growth of the aquaculture industry. The ultimate aim is the demonstrated value of the integrated technologies, their benefit to end-users and their potential adoption. These are required to inform the development of the AquaWatch mission. Results will be available to inform the relevant industry sectors for commercial development to the benefit of the Australian economy.

The aim of the study is to review how existing and future EO data can be used in combination with data capture with terrestrial methods in a joint data fusion architecture. To create the architecture, standards of the terrestrial and satellite data will be investigated and when required, recommendations for standards’ improvement will be suggested. The proposed architecture will be designed as general, applicable in multiple spatial information areas, the study will focus especially on Urban Heat Islands (UHIs). Approaches to efficient data and information visualisation will be part of the investigation in this research with professionals from different areas than spatial information science as target audience. This contributes to the overall SmartSat CRC topic of Environmental Management. Urban Heat Islands impact the quality of life in many urban centres. Metropolitan areas of Australian cities and urbanised regional centres, in particular, show vulnerability towards UHIs due to challenging climatic conditions.

Knowledge of crop and pasture quality can provide the industry with insights to assist with the grazing management of pastures and input management decisions for crops. Handheld and lab-based spectroscopy have been extensively employed to monitor quality-based plant attributes. The methods employed are time consuming and expensive to implement and do not provide the industry with insights into the temporal trends of the critical variables. High resolution and frequent return time can overcome numerous deficiencies affecting equivalent visible IR and SWIR platforms, that limit the ability to create a viable product around crop and pasture quality. This project would conduct a feasibility analysis that capitalises on existing and planned satellite missions, including the Aquawatch satellites and precursors to test development of new high frequency products for crop and pasture quality across the Australian landscape.

Machine learning has achieved great success in computer vision, natural language processing and other fields, especially in the accuracy of prediction and some may have exceeded the human capabilities. Nevertheless, users still need to understand the reasons for their conclusions in a more detailed and tangible way in application scenarios. Giving strong explainability to the model also helps to ensure its robustness, and usability of the method. This proposal focuses on developing interpretable models for early smoke wild-fire detection from satellite images.

Detecting fires at their early stages is essential to prevent fire caused disasters. Research has been conducted to detect smoke in satellite imagery for fire detection. Unfortunately, the imagery data used in previous research have low spatial resolution and only contain the RGB bands, which are ineffective for early fire detection. Our team (Data Analytics Group at UniSA) has been working on early fire smoke detection with multispectral multi-sensor satellite imagery for one year and the accuracy of wild fire detection can reach more than 90% accuracy. An AI framework of deep learning neural networks that identifies wild fires has been developed. It is necessary to present users with understandable reasons for the detection so the users can validate the detection and assess its severity. Current detection models are deep learning-based and have a black box detection kernel. This project aims to make the detection transparent to users so users can use and interact with the model easily. In the following, we will introduce the main techniques for explaining predictions made by deep learning / black-box
machine learning models.

The objective of this project is to assess the suitability of the Canadian WildFireSat mission for Australian Bushfire Management.