• Artificial Intelligence
• Remote Sensing
• Environmental Monitoring
• Bushfire
• Earth Observation
• Time-series Image Analysis
• Change Detection
• Risk Modelling and Reduction
• Natural Hazards
• GIS Maps Updating
• Vegetation Dynamics
• Land Cover Analysis
• Advanced Machine Learning
• Explainable AI (XAI)
• Fuel Attributes Dynamics and Spatial Mapping

Dr Abolfazl Abdollahi is a research scientist in the field of Artificial Intelligence (AI), Earth Observation, and Remote Sensing. He completed his Ph.D. at the School of Civil and Environmental Engineering, University of Technology Sydney (UTS). Embarking on a journey through the frontiers of Artificial Intelligence (AI), his Ph.D. endeavor centered on its applications within Earth observation and Remote Sensing. Abolfazl’s research encompassed developing conventional machine learning and deep learning models including CNNs, Deep CNNs, and Generative AI to effectively process various remote sensing products, track vegetation changes, update GIS maps, and analyze dynamic landscapes over time. Additionally, he delved into the realm of Explainable AI (XAI) to guarantee transparency and nurture trust and understanding in AI models.

Abolfazl holds the position of postdoctoral research fellow at the Bushfire Research Centre of Excellence, Australian National University (ANU). In this capacity, he is actively engaged as a project manager in the Bushfire Data Challenges program, which is part of the Australian Research Data Common (ARDC’s) Translational Research Data Challenges initiative. The Bushfire project develops innovative digital infrastructure solutions to current data challenges in bushfire research with the aim of improving Australia’s bushfire resilience, response, and recovery. In collaboration with a list of partners such as TERN, CSIRO, AFAC, and ARDC who are actively involved in the project, the aim is to create aggregated and harmonized datasets for bushfire fuel attributes known to influence the fire behavior processes on a national scale (Australia) using Earth observation techniques and Artificial Intelligence (AI). The project also involves an examination of the spatial distribution of fuels within diverse vegetation and fuel types and an investigation of their response to climate change and bushfire disturbance.

Abolfazl has demonstrated remarkable accomplishments, with a prolific record of publishing numerous scientific papers in esteemed international journals. He also serves as a regular reviewer and academic editor for top-tier journals in his field. Furthermore, he has successfully obtained several competitive grants, awards, paid internships, and scholarships, underscoring the excellence and significance of his research contributions. Throughout his academic journey, he has collaborated with world-renowned experts and worked on interdisciplinary projects. This collaboration has significantly contributed to his knowledge, expertise, and experience in the field.

He has taught undergraduate and graduate courses, such as "Environmental Sensing, Mapping and Modelling", "Risk Assessment and Management", and "Introduction to Information Systems". Additionally, he supervises the research of honours and graduate students in a range of remote sensing and AI topics.

Bushfire Data Challenges Program under the Australian Research Data Common (ARDC)

• The goal of this project is to create aggregated and harmonized datasets for fuel attributes known to influence the fire behavior models on a national scale (Australia) using Earth observation techniques and Artificial Intelligence (AI) to solve the current data challenges in bushfire research with the aim of improving Australia’s bushfire resilience, response, and recovery. The national fuel attributes databases this project will produce will have direct benefits to bushfire planning and response given the fuel data will also be readably available for assessing bushfire risk, predicting fire behaviour, informing suppression efforts and planning prescribed burns.

Forecasting Grass Pollen with Satellite Sensor Time-series, Meteorology Data, and Machine Learning Tools

• In this project, which was a cross-faculty project between the Faculty of Engineering and Science and Health Department at the University of Technology Sydney (UTS), a consistent set of satellite measures of grass cover and seasonal greenness were investigated to evaluate their utility for predicting airborne grass pollen concentrations based on Artificial Intelligence methods.

Land Cover Classification and GIS Maps Updating from Remote Sensing Data Using Deep Convolutional Neural Networks (DCNNs)

• Land cover is the detected bio-physical overlay on the Earth’s surface, including materials like grass, forest, pastures, built-up areas, water body, etc. Reliable information on global land cover is required to assist in the solution of a wide range of environmental problems. The use of deep learning (DL) approaches for the analysis of remote sensing (RS) data is rapidly increasing. DL techniques have provided excellent results in a range of applications, especially in image processing, land cover classification, and maps updating. Thus, this work aims to deepen the understanding of DCNN models for land use/land cover classification based on time series satellite images in the context of large-scale areas.
  

Developing machine learning algorithms to identify forest structural characteristics from earth observation data on a regional scale, Australia [LINK]