Titus Venverloo

Urban temperatures and heatwave frequency are rising, necessitating targeted adaptation measures such as shade provision. This study quantifies and compares building- and tree-generated shade along pedestrian walkways in 10 cities worldwide, from Stockholm (most northern) to Cape Town (most southern). We distinguish between grey and green shade at high spatial resolution and across temporal scales, offering a clearer understanding of their respective contributions to radiative cooling. Using high-resolution elevation data and aerial imagery, we model dynamic shade patterns across seasons and times of day. These are overlaid with sidewalk polygons from OpenStreetMap to conduct a city-scale, pedestrian-focused analysis. Results show that trees dominate shading at midday - when cooling is most needed - while buildings contribute more during morning and late afternoon, particularly in high-latitude urban canyons. Simulations indicate that tree presence can increase midday shade along pedestrian walkways by up to two orders of magnitude - for example, from near zero to about 10% in Rio de Janeiro, or more moderately, from 8% to 38% in Rome. In Amsterdam, tree shade alone elevates over 40% of sidewalks into a higher shade availability category, underscoring the transformative impact of green infrastructure. Our framework for quantifying green and grey shade highlights the importance of time-sensitive, spatially aware shade analysis in climate-resilient urban planning. All code and data processing workflows are open-source, supporting transparency, reproducibility, and future applications.

Insect biodiversity and abundance are in global decline, potentially leading to a crisis with profound ecological and economic consequences. Methods and technologies to monitor insect species to aid in preservation efforts are rapidly being developed yet their adoption has been slow and focused on specific use cases. We propose a computer vision model that works towards multi-objective insect species identification in real-time and on a large scale. We leverage an image data source with 16 million instances and a recent improvement in the YOLO computer vision architecture to present a quick and open-access method to develop visual AI models to monitor insect species across climatic regions.