Research areas within Landscape Ecology

The Multiscale Gradient Paradigm

Advancing theoretical and analytical frameworks that represent landscapes as continuous, multidimensional gradients of environmental attributes, rather than discrete, categorical patches. This approach minimizes data distortion and more accurately reflects true pattern-process relationships across multiple spatial scales.

AI & Deep Reinforcement Learning in Conservation

Applying cutting-edge machine learning and deep reinforcement learning techniques to sustainability science. This includes optimizing landscape connectivity and orchestrating complex conservation planning to maximize biodiversity outcomes under dynamic environmental scenarios.

Biodiversity Monitoring & Connectivity Modeling

Developing high-resolution ecological resistance models and monitoring frameworks for critical species worldwide. Current focus areas include mapping species occurrences and connectivity for clouded leopards, lions, and pine martens, utilizing tools like Google Earth Engine, R, Python, and UNICOR.

Ecosystem Recovery & Rewilding

Leading large-scale field campaigns and data-driven initiatives to monitor ecosystem recovery, optimize land management and land use plans for multiple objectives, and establish robust, empirical foundations for rewilding efforts.