Research Scientist (Predictive Modelling)
Bachelor of Science (Environmental Science), Master of Science (Remote sensing and Geographic Information System (GIS), PhD (Ecological Modelling)
Roozbeh is motivated by applying geospatial, statistical and machine learning techniques to solve ecological and agricultural problems. He uses statistical models to understand the interaction between species and the environment and how species respond to environmental changes.
Here at Cesar Australia, Roozbeh supports the team with statistical analysis of lab and field data and he uses predictive models to map the distribution of pest species and how they respond to environmental conditions or pesticide usage. Furthermore, he develops scientific software and applications that are useful for researchers and non-researchers.
Roozbeh grew up in a small town in the south-west of Iran and, being fascinated by the surrounding environment, he completed his undergraduate in environmental science and natural resources engineering. As he was passionate to use novel technologies to aid environmental management, he continued his education in GIS and Remote Sensing where he used machine learning methods to map the potential impact of climate change on Oak trees in the south-west of Iran. To expand his knowledge, he commenced a PhD at Melbourne University in 2017. During his PhD, he developed guidelines and tools for assessing and improving statistical and machine learning predictive models for mapping species distributions.
Shaeri Karimi S, Saintilan N, Wen L, Cox J, Valavi R (2021) Influence of inundation
characteristics on the distribution of dryland floodplain vegetation communities. Ecological
Indicators, 124, 107429.
Elith J, Graham C, Valavi R, Abegg M, Bruce C, Ferrier S, Ford A, Guisan A, Hijmans RJ,
Huettmann F, Lohmann L, Loiselle B, Moritz C, Overton J, Peterson AT, Phillips S,
Richardson K, Williams S, Wiser SK, Wohlgemuth T, Zimmermann NE (2020)
Presence-only and Presence-absence Data for Comparing Species Distribution Modeling
Methods. Biodiversity Informatics, 15, 69–80.
Marshall E, Valavi R, Connor LO, Cadenhead N, Southwell D, Wintle BA, Kujala H (2020)
Quantifying the impact of vegetation‐based metrics on species persistence when choosing
offsets for habitat destruction. Conservation Biology, cobi.13600.
Shafizadeh-Moghadam H, Weng Q, Liu H, Valavi R (2020) Modeling the spatial variation of
urban land surface temperature in relation to environmental and anthropogenic factors: a
case study of Tehran, Iran. GIScience, Remote Sensing, 57, 483–496.
Taghizadeh-Mehrjardi R, Schmidt K, Amirian-Chakan A, Rentschler T, Zeraatpisheh M,
Sarmadian F, Valavi R, Davatgar N, Behrens T, Scholten T (2020) Improving the
Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions by
Stacking Machine Learning Models and Rescanning Covariate Space. Remote Sensing, 26.
Valavi R, Elith J, Lahoz‐Monfort JJ, Guillera‐Arroita G (2019) blockCV: An R package for
generating spatially or environmentally separated folds for k-fold cross-validation of species
distribution models. Methods in Ecology and Evolution, 10, 225–232.
Valavi R, Shafizadeh-Moghadam H, Matkan A, Shakiba A, Mirbagheri B, Kia SH (2019)
Modelling climate change effects on Zagros forests in Iran using individual and ensemble
forecasting approaches. Theoretical and Applied Climatology, 137, 1015–1025.
Hamzehpour N, Shafizadeh-Moghadam H, Valavi R (2019) Exploring the driving forces and
digital mapping of soil organic carbon using remote sensing and soil texture. Catena, 10.
Shaeri Karimi S, Saintilan N, Wen L, Valavi R (2019) Application of Machine Learning to Model
Wetland Inundation Patterns Across a Large Semiarid Floodplain. Water Resources Research,
Shafizadeh-Moghadam H, Valavi R, Shahabi H, Chapi K, Shirzadi A (2018) Novel forecasting
approaches using combination of machine learning and statistical models for flood
susceptibility mapping. Journal of Environmental Management, 217, 1–11.