Topics Webinar | EO&GEO Series: Investigating State-of-the-Art Machine Learning Approaches in Vegetation Analysis Through Earth Observation Data
the chairs
Welcome to the Investigating State-of-the-Art Machine Learning Approaches in Vegetation Analysis Through Earth Observation Data Webinar!
Vegetation cover maps, whether they focus on structural attributes, ecological aspects, or biomass content, are invaluable for understanding Earth's ecosystems in a spatial context.
The advent of Earth Observation data has transformed vegetation mapping and trend analysis, offering data with various spatial and spectral resolutions on a global scale. Vegetation mapping and analysis provide critical insights into the distribution and density of vegetation, while also highlighting the impact of overall environmental changes on biodiversity and ecosystems. An accurate interpretation of this remote sensing data necessitates sophisticated analytical techniques to manage its complexity and vastness.
Join us for an insightful webinar that explores cutting-edge machine learning methodologies and their role in vegetation analysis using Earth Observation (EO) data. This webinar features four scholars presenting their latest research on how machine learning and EO data can enhance vegetation monitoring and mapping. It will facilitate the sharing of insights and ideas among participants while opening opportunities for collaborative efforts.
We are privileged to have esteemed research scientists and academics from recognized research institutions and universities in Australia. They will share their valuable insights and research findings on the effective application of machine learning technology in Earth observation data in obtaining essential information related to climate change, land use planning, ecosystem conservation, weed management, and agricultural management.
Date: 15 May 2025
Time: 7:00 a.m. CEST | 3:00 p.m. AEST | 1:00 p.m. CST
Webinar ID: 854 2945 1681
Webinar Secretariat: journal.webinar@mdpi.com
Meet the Event Chairs
Meet Our Speakers
Dr. Arnick Abdollahi
Research Fellow, Transdisciplinary School, University of Technology Sydney (UTS);
Dr. Arnick Abdollahi is a research fellow at the University of Technology Sydney (UTS), specializing in Earth and space science informatics, artificial intelligence (AI), and environmental science. He completed his Ph.D. at UTS and was a postdoctoral fellow at the Australian National University’s Bushfire Research Centre, where he led AI initiatives to enhance bushfire resilience. His research has advanced the analysis of bushfire behaviour, promoted the responsible use of AI in environmental monitoring, and influenced national strategies for remote sensing and risk management.
Currently, he manages a national initiative developing an AI-powered grazing planner to support sustainable livestock farming in the face of climate variability and bushfire threats. Dr. Abdollahi has received several grants and accolades, including recognition in the 2024 Australian AI Awards and the 2025 Australian Space Awards.
Dr. Catherine Ticehurst
Senior Research Scientist, Environment, CSIRO (Commonwealth Scientific and Industrial Research Organisation);
Dr Catherine Ticehurst received her PhD in Geomatic Engineering (modelling SAR polarimetry in urban environments) at the University of NSW. She started working at the CSIRO in 1998 where she has been working in what is now the Landscape Observation group at CSIRO Environment, mapping and monitoring a variety of vegetation and wetland environments using a range of current and emerging airborne and satellite earth observation technologies. Research areas include: Mapping surface water dynamics at regional scales; Developing relationships between biophysical parameters of vegetation and remote sensing data (airborne and spaceborne SAR, hyperspectral and multi-spectral airborne and spaceborne optical data); NDVI time-series analysis for monitoring crops; Radar polarimetry, including polarisation signature decomposition, and its relationship with mangrove and rainforest environments; High-resolution crown delineation and classification in high-biodiversity vegetation environments; Data integration and image processing methods, including programming in python; Application of LiDAR altimetry for mapping vegetation height and surface water height; Extracting and using Analysis Ready Data within an Open Data Cube using Jupyter Notebooks.
Dr. Sanjeev Kumar Srivastava
Associate Professor, Sustainability Research Cluster, University of the Sunshine Coast, Queensland;
Dr Sanjeev Kumar Srivastava, PhD Geographical Sciences Australian National University, works as an Associate Professor in Geospatial Analysis at the University of the Sunshine Coast. He uses geospatial analytics to conserve earth resources. His research interests include mapping wildfire fuel distribution, post-burn areas, vegetation regrowth, and ecosystem monitoring, utilising analysis of both field-based and remote sensing data. Within the School of Science, Technology, and Engineering, he leads a research cluster, ‘Geospatial Analytics for the Conservation and Management of Earth Resources’. While working at the University of the Sunshine Coast, he has led projects funded by SmartSat CRC, the Asia-Pacific Network for Global Change Research, the Queensland Fire Department, and local councils.
Dr. Roozbeh Valavi
Senior Research Scientist, CSIRO (Commonwealth Scientific and Industrial Research Organisation);
Dr Roozbeh Valavi is a senior research scientist at CSIRO, specialising in spatial ecology and biodiversity modelling. He develops scalable scientific software for environmental applications, focusing on species distribution modelling and habitat mapping. Previously, he worked at Cesar Australia, applying predictive modelling to forecast agricultural pest invasions and pesticide resistance. During his PhD at The University of Melbourne, he advanced species distribution modelling methods and developed practical tools. He has extensive expertise in R, Python, and C++, as well as ecological modelling, geospatial analysis, machine learning, and scientific software development.
Dr. Kate Giljohann
Research Scientist, Environment CSIRO;
Dr Kate Giljohann is an ecologist and ecological modeller, specialising in research to support environmental decision-making. Her work focuses on the assessment and prediction of change in biodiversity and the impact of novel disturbance regimes and threatening processes on ecological dynamics. Kate’s research merges geospatial analysis, statistical modelling and decision science to address environmental challenges. She has conducted extensive research on fire ecology across southern Australia, including the development and testing of biodiversity resilience metrics, and coupling of biodiversity models with mechanistic fire regime simulations and scenario analysis to explore options for sustaining biodiversity.
Sponsors and Partners
Organizer
Investigating State-of-the-Art Machine Learning Approaches in Vegetation Analysis through Earth Observation Data
Edited by Dr. Arnick Abdollahi and Dr. Chandrama Sarker
Deadline for submission: 25 May 2025
Gaussian Process Regression Hybrid Models for the Top-of-Atmosphere Retrieval of Vegetation Traits Applied to PRISMA and EnMAP Imagery
Authors: Ana B. Pascual-Venteo, Jose L. Garcia, Katja Berger, José Estévez, Jorge Vicent, Adrián Pérez-Suay, Shari Van Wittenberghe and Jochem Verrelst,
Remote Sens. 2024, 16(7), 1211; https://doi.org/10.3390/rs16071211
Advancing Sparse Vegetation Monitoring in the Arctic and Antarctic: A Review of Satellite and UAV Remote Sensing, Machine Learning, and Sensor Fusion
Authors: Arthur Platel, Juan Sandino, Justine Shaw, Barbara Bollard and Felipe Gonzalez
Remote Sens. 2025, 17(9), 1513; https://doi.org/10.3390/rs17091513
A Robust Dual-Mode Machine Learning Framework for Classifying Deforestation Patterns in Amazon Native Lands
Authors: Julia Rodrigues, Mauricio Araújo Dias, Rogério Negri, Sardar Muhammad Hussain and Wallace Casaca,
Land 2024, 13(9), 1427; https://doi.org/10.3390/land13091427
Cover Crop Biomass Predictions with Unmanned Aerial Vehicle Remote Sensing and TensorFlow Machine Learning
Authors: Aakriti Poudel, Dennis Burns, Rejina Adhikari, Dulis Duron, James Hendrix, Thanos Gentimis, Brenda Tubana and Tri Setiyono
Drones 2025, 9(2), 131; https://doi.org/10.3390/drones9020131
Analyzing Decadal Trends of Vegetation Cover in Djibouti Using Landsat and Open Data Cube
Authors: Julee Wardle and Zachary Phillips
Geomatics 2025, 5(1), 6; https://doi.org/10.3390/geomatics5010006
A Comparison of Machine Learning Models for Mapping Tree Species Using WorldView-2 Imagery in the Agroforestry Landscape of West Africa
Authors: Muhammad Usman, Mahnoor Ejaz, Janet E. Nichol, Muhammad Shahid Farid, Sawaid Abbas and Muhammad Hassan Khan
ISPRS Int. J. Geo-Inf. 2023, 12(4), 142; https://doi.org/10.3390/ijgi12040142
The webinar was hosted via Zoom and required registration to attend. The full recording can be found below. In order to learn about future webinars, you can sign up to our newsletter by clicking “Subscribe” at the top of the page.
The webinar explores cutting-edge machine learning and Earth Observation (EO) technology for advanced vegetation analysis and environmental insights. This well-attended webinar featured interdisciplinary discussions and explored a diversity of questions. The speakers shared their valuable insight into innovative approaches to critical environmental challenges, including bushfire-related research, ecological aspects, ecosystem conservation, weed management, and sustainable agricultural management. The session featured expert presentations from Dr. Kate Giljohann, Dr. Roozbeh Valavi, Dr. Catherine Ticehurst (CSIRO), Dr. Sanjeev Kumar Srivastava (University of the Sunshine Coast), and Dr. Arnick Abdollahi (University of Technology Sydney). The webinar was chaired by Dr. Chandrama Sarker (CSIRO) and Dr. Arnick Abdollahi.