Many satellite data users lack the expertise and infrastructure to efficiently and effectively access, pre-process, and utilize the growing volume of space-based data for local, regional, and national decision-making (Barker et al., 2022; Chue Hong et al., 2021). This represents a significant obstacle to realizing the full potential of and achieving successful utilization of space-based imagery data. In response to this challenge, various countries and international organizations have expressed a strong desire for support from the Committee on Earth Observation Satellites (CEOS), a pioneering advocate of the CEOS Analysis Ready Data (ARD) initiative (Sazonov et al., 2019).

The CEOS ARD initiative focuses on streamlining access to and processing of satellite data, transforming it into CEOS Analysis Ready Data for Land (CARD4L) products. These products are specifically designed to facilitate seamless time-series analysis without requiring supplementary acquisition information. By systematically and consistently providing CARD4L data, the burden on global satellite data users is expected to be significantly reduced, ultimately enhancing the usability of the data. The delivery of CARD4L data will adhere to the Guiding Principles of Findable, Accessible, Interoperable, and Reusable (FAIR) including various methods such as systematic data processing, hosting platforms, and toolkits made available to users (Wilkinson et al. 2016; Musen et al., 2022; Jacobsen et al., 2020; Weigel et al., 2020).

However, the sheer volume of data generated by the extensive Earth observation data and services provided by over 300 satellites poses a substantial challenge for analysts, scientists, and even non-experts (FrontierSI, 2020). This emphasizes the urgent need to establish a comprehensive FAIRified data model framework for computational workflows, aimed at fully unlocking the potential of Earth observation products in the environmental sector and beyond. Recent advancements in storage and computing power have not only made this cost-effective but also feasible to process and analyze data across various scales. Machine Learning (ML), a fundamental component of modern science and industry, significantly simplifies scientific analysis by efficiently identifying patterns, outliers, and discrepancies in datasets, streamlining data preprocessing, and promoting the development of more accurate, robust, and scalable applications (Peng et al. 2023).

Extensive research has been conducted in various domains focusing on the FAIRified data model framework integrated with Machine Learning (ML). One notable outcome of this research is the development of the Source-augmented Partial Convolution v2 model (SAPC2), which serves as an innovative solution for pixel reconstruction. SAPC2, built upon a partial convolution-enabled U-Net framework, leverages a complete source temporally adjacent to the reconstruction process. It employs an encoder-decoder structure to extract high-level features (Chen M, 2020). Traditionally, many applications have tended to disregard observations affected by cloud coverage or sensor saturation. A recent study has shed light on the issue of errors of commission arising from the Fmask technique. It emphasizes the importance of continued inclusion and enhancement of quality assurance bands in Analysis-Ready Data (ARD). The study advises users to utilize pixel quality flagging to mitigate potential biases under varying conditions (Ernst, 2018). This approach offers significant potential for standardizing the documentation of workflows and increasing trust in EO data products, thereby increasing productivity and utilization in environmental sector and other sectors. Furthermore, in-depth research efforts have been dedicated to dynamic environmental simulations, covering the intricate interplay between human activities and land-use changes (Searchinger et al., 2018; Newbold et al., 2015), climate dynamics (Findell et al., 2017), water resource management (Spera et al., 2016), and the socioeconomic system (Hostert et al., 2011).

Overall, this research advocates for a comprehensive approach that seamlessly incorporates the FAIR Guiding Principles into machine learning workflows. This integration aims to facilitate the generation of Analysis Ready Data (ARD) to significantly improve efficiency and reproducibility in the field of land observation and monitoring. The central tenet of this work underscores the critical significance of standardized data management procedures and automated workflows in empowering data-driven investigations in the environmental sector. By embracing this integrated framework, the global scientific community can fully harness the untapped potential of ARD products. This approach fosters collaborative efforts and paves the way for groundbreaking discoveries. Furthermore, it actively promotes interoperability between public and commercial data sources, enabling a wide array of applications. This approach is a cornerstone of a more sustainable and informed approach to land management, ensuring the optimal utilization of Earth Observation (EO) products across a multitude of sectors.

In the Mount Lofty Ranges, there are three stringybark eucalypt species: Eucalyptus baxteri (brown stringybark), Eucalyptus obliqua (messmate stringybark) and Eucalyptus macrorhyncha (red stringybark). All three species show signs of dieback, resulting in the reduction of overall forest health with an increase in the death rate of the trees. Anthropogenic climate change is causing an increase in extreme weather events, such as the occurrence of prolonged and successional droughts, placing these stringybarks at further risk of dieback.

Effective management of the conservation efforts for stringybarks within the Mount Lofty Ranges in South Australia requires accurate knowledge of the amount and extent of the vegetation health changes and how local topography can influence the presence of unhealthy vegetation. Advances in remote sensing techniques using satellite or airborne (derived using sensors on planes or remotely piloted aircraft (RPA)) imagery allow for the assessment of vegetation, including its structure, distribution, health, species information and spatiotemporal dynamics across the landscape. Remote sensing allows discrete investigation across inaccessible or fragile ecosystems to identify spatiotemporal patterns, which is especially important for conservation efforts.

In this PhD research, the extent of dieback will be determined, and vegetation health changes over time will be identified in eucalypt forests using comparative remote sensing techniques to monitor forest health. The aim is to develop and compare different remote sensing methods on a simpler stringybark forest and then apply the developed methods to a more complex stringybark forest. Findings will be used to develop a Remote Sensing and scenario-based framework for dieback analytics, allowing for determining the extent of dieback and vegetation health changes over time for other eucalypt forests.

This research is primarily about water quality parameters mapping and time series forecasting of water nutrients. Additionally, it will develop a dynamic framework capable of concurrently retrieving water quality indicators in the coastal and inland waters through in-situ sensors and satellite imagery. In the future this project will focus on building a real time water quality monitoring and forecasting model for large scale and sustainable long-term usage.

As climates change, and as atmospheric concentrations of CO₂ and other greenhouse gases continue to increase, there is a demand for greater accuracy and precision in methods and models for carbon and water accounting at multiple scales. Furthermore, there is a pressing global need to include managed ecosystems – especially agriculture – in regional, national, and international carbon and water inventories. In this project, we will combine carbon and water flux measurements from our unique mobile eddy covariance (EC) system with Earth observation (EO) satellite data to develop quantitative tools for measuring and assessing carbon capture and storage and water cycles in agricultural systems at landscape scale.

At present, EC installations are overwhelmingly biased to ‘natural’ ecosystems such as forests and shrublands. We will combine our unmatched and unique mobile EC systems for Australian ecosystems with international expertise in cleaning and transforming EC data in preparation for modelling analysis. We will then upscale this combined capacity for quantifying fluxes from EC tower footprints (m² to Ha scales) to larger scales of thousands of km².  This will involve combining mobile EC flux measurements with multispectral and hyperspectral satellite imagery and satellite-based atmospheric measurements via a model that infers the carbon and water fluxes for specific land cover types and atmospheric conditions. The primary outcome of this Phase 1 activity will be a proof-of-concept EC data analysis pipeline suitable for inferring carbon and water fluxes. This project will be a technical demonstrator for a Phase 2 activity to develop an Australian map of the atmosphere-land carbon and water cycles across all agricultural land.

This project aims to develop automated methods for monitoring vegetation structural and functional metrics at fine levels of spatial detail (tree and branch level) across local to regional scales (100s ha) by addressing a missing drone-based LiDAR processing capability. Algorithms will be developed and verified to produce accurate and precise tree and woody vegetation models down to cm accuracy from 3D point cloud data across both native and agricultural landscapes. This aligns with the Maya Nula SmartSat research program. These 3D models will allow vegetation structural and functional baseline metrics to be automatically extracted at both individual tree and entire site levels, namely: stem density, stem diameter, crown height, crown width, woody volume, and aboveground biomass.

Remote sensing represents a useful tool for agriculture thus enabling to intervene in a timely and prudent manner, meeting economic, social and environmental sustainability needs.Wheat and cotton are two of the most important crops in the Australian context. Infact wheat is the main winter dry land crop and cotton the main summer irrigated crop. Although some dry land cropping does occur in some years. Nitrogen is a key nutrient for these infact it is essential for photosynthesis and therefore an insufficient supply will affect both development and production in terms of quality and quantity but sometimes an excessive supply can make plants more susceptible to stress, negatively affect yield and damage local ecosystems. It is important to monitor vegetation nitrogen nutrition via chlorophyll as a proxy for leaf nitrogen content and nitrogen use efficiency and how these may vary according to different application modes (split or singleapplications). Therefore, it is clear the importance of identifying which may be not only the best application strategies for the crops being studied but also the effect that these may have on development, also paying attention to any stress, in particular water stress , which may have influenced the response of the vegetation.The main characteristics that can accompany the study for the evaluation of nitrogen and water nutrition of crops are the height of the crop, the degree of soil coverage, flowering and final yield, availability at sowing and during crop growt period. My proposed thesis aims to investigate the development and yield of wheat and cotton in response to different application strategies of nitrogen and water stress by utilising multispectral and hyperspectral remote sensing and the derivation of data from maps with specific indexes, machine learning and deep learning algorithms and, to increase the level of precision, RTM and SIF (solar-induced chlorophyll fluorescence: an optical signal emitted in the spectral range 650–850 nm from chlorophyll a molecules in vegetation). SIF may be assessed remotely using high-resolution spectral sensors. Recent studies have demonstrated that solar-induced chlorophyll fluorescence (SIF) quantified from hyperspectral imagery is a reliable indicator of photosynthetic activity in the context of precision agriculture and for early stress detection purposes. For these reasons, spectral indicators related to the leaf functioning, as chlorophyll fluorescence, is a potentially important candidate for improving the quantification of N concentration.