Download the imported WorldCover chip and boroughs. Mask class 0 and pixels whose centres fall outside Newham. Report named values valid_pixels, tree_pct (class 10 / valid, two decimals) and built_pct (class 50 / valid, two decimals). Work offline from the TIFF; the online Python runner does not mount it.
A London borough analyst needs a repeatable first screen for places where built cover is high and mapped tree cover is low. They receive a 2021 ESA WorldCover class chip clipped to Newham and the borough boundary. The result is a queue for field verification; it does not say where trees can legally or safely be planted.
Complete three handoffs: quantify the source pixels, deliver a GIS grid of class shares, and map cells that meet the agreed screen. Every measurement uses pixel centres inside the Newham polygon. A grid cell is included when its centre is inside the borough; its shares count only valid pixels that are also inside the borough. WorldCover classes describe land cover, not street-level canopy, land ownership or heat exposure.
These are where the teaching is. Read them twice.
London City Hall publishes green infrastructure mapping tools to support decisions by boroughs and delivery partners (https://www.london.gov.uk/programmes-strategies/environment-and-climate-change/parks-green-spaces-and-biodiversity/green-infrastructure-maps-and-tools). ESA WorldCover 2021 is a 10 m global land-cover product (https://esa-worldcover.org/en/release-worldcover-map-2021). The imported chip is a measured derivative for this exercise; its cells are screening units, not official planting sites.
Work the problem in whatever tool you like, then enter the answers here.
valid_pixelstree_pctbuilt_pct3 scored, 0 informational
Valid Newham pixels
33%Tree-class share
33%Built-class share
33%