Housing development in London has a new weapon: AI

Data from an AI learning model that mapped the London Borough of Lewisham suggests the capital’s targets for ‘small site’ development could be radically increased, says Russell Curtis

When the latest iteration of the London Plan was adopted in 2021, for the first time in its 20-year history the policy demanded that the capital’s 35 planning authorities deliver a proportion of their overall housing targets on small sites – that is, with an area of no more than 0.25ha. The figures varied across the city, but the total number of homes to be found on these pockets of land stood at 120,000 – just under a quarter of the overall housing target for the whole of London.

This number was way below that originally proposed by the London mayor in 2018. Alongside a ‘presumption in favour’ of development on small sites close to public transport, the earlier version of his plan compelled planning authorities to find space on small sites for a quarter of a million homes, with the outer boroughs expected to deliver the lion’s share.

The pushback was inevitable, with London Assembly member Andrew Boff claiming, hyperbolically, that this amounted to a ‘war on the suburbs’. With the GLA lacking convincing data to demonstrate the figures were achievable, the targets were slashed before adoption.

But quiet, in the background, progressive boroughs knuckled down and got on with putting plans in place to promote intensification. In 2020 – nearly a year before the final version of the London Plan was adopted – Lewisham Council appointed RCKa and Ash Sakula to prepare dedicated guidance for new homes on its small sites. Just six months after the London Plan became official policy, Lewisham’s Small Sites SPD was formally adopted.

Two years on, as Sadiq Khan looks towards what’s increasingly likely to be a third and final term, he will be considering updates to the London Plan to cement his legacy as the mayor who did the most to tackle the city’s profound housing crisis. Small sites are likely to be a key focus of this work, and it would be a shrewd move to ramp up the small sites targets accordingly. But the question remains over whether there is sufficient data to justify this increase. To counter resistance to suburban intensification (as happened in Croydon) the new plan will need to be backed with robust evidence of the quantity and distribution of these sites.

So where are they? And how many? We tried to find out.

Land Registry data tells us that there are some 66,000 freeholds in Lewisham, and about 85 per cent of these meet the small-site criteria. Armed with our intimate knowledge of the Lewisham SPD and the site “types” it identifies, we set about mapping every one of them. Having built up a vast library of sites, based on the SPD, we trained an AI to categorise a bunch: backland, infill, amenity space and so on. Then, setting our learning model on the remainder of the borough, we created a complete map of Lewisham, including the location, size – and a rough idea of capacity – of every development opportunity from Deptford to Beckenham.

What we found was striking. While Lewisham’s London Plan 10-year small sites target is currently 3,790, based on early outputs from our data we think there might be capacity for two to three times this number. In fact, our AI model shows that there are enough sites to deliver Lewisham’s target on just two types alone. And as we trawl through the data, the AI improves. Ultimately, our plan is to apply the learning model to capture the whole of London.

Now, just because a site is developable it doesn’t mean it will come forward. The AI makes no distinction between public and private ownership, and many of the sites it has picked out will not provide new homes: some are private gardens, others active builder’s yards and occupied garages. But by establishing a policy landscape that makes planning less risky – as Lewisham has done – boroughs can go a long way to meeting these targets.

Extrapolating these figures across the rest of London, we think there’s sufficient capacity for at least 350,000 homes. Backed by our AI, there can be no more arguing over targets when we know not just how many sites there are. We can even point to them on a map. This is a huge opportunity, and those boroughs still lacking a dedicated small-sites policy should be compelled to implement it as soon as they can. It’s time to take small sites seriously.

This article was originally published in the Architects’ Journal.

No aspect of planning policy is quite as divisive, or as misunderstood, as the green belt. Covering some 16,000km², England’s 14 green belts occupy one-eighth of England’s total area (equivalent to three-quarters of the area of Wales, if that’s your preferred unit of measurement).

London’s metropolitan green belt alone stretches from Haslemere in Hampshire to the North Sea—a distance of some 100 miles—and with an area of over half a million hectares is over three times larger than the city itself.

Although its origins precede the Second World War, the green belt was formally established by the Town and Country Planning Act of 1947, which allowed planning authorities to protect open space with this designation. And while the policy has been extremely successful in achieving its original objective of constraining urban expansion, three-quarters of a century on, it’s surely time to reform this anachronistic policy and ensure it meets the needs of the modern world.

Among the marshes of estuary Essex and the undulating hills of Hampshire, there are motorways, waste transfer depots, landfill sites, distribution centres, poultry farms, golf courses and car parks that are all protected from development by the simple virtue of their presence within the green belt. Many areas of otherwise undeveloped space are of limited quality too.

One of the most prominent obstacles to a sensible discussion is the fact that the arguments for and against the green belt have become so utterly polarised. Listening to both sides of the debate, you’d be forgiven for thinking that we face a simple binary choice between the preservation of dwindling landscapes and concreting over every last inch of them. And yet, the green belt has actually grown in recent years. It’s preposterous to claim that it’s under threat.

While we can’t lay the blame for our pitiful national productivity solely at the feet of green-belt policy, it’s clear that our inability to build – whether it’s homes, railways or solar farms – in the places we need, is partly a product of misplaced constraints on development.

Lobby groups like the Campaign for the Protection of Rural England (CPRE) insist that any rethink of the green belt isn’t necessary, but these claims simply don’t stand up to scrutiny. Its latest State of Brownfield report confidently concluded that 1.2 million homes could be built on brownfield land alone, but this is only a quarter of the current shortfall, and certainly insufficient to meet future demands. Furthermore, many of the areas it proposed for new housing aren’t even in the places where need is most acute. I’m not aware of many CPRE members upping sticks from leafy Surrey to the post-industrial wastelands of northern Britain.

There’s a common misconception about the purpose of the green belt in the public sphere, with many mistakenly believing that its purpose is to protect precious rural landscapes. Close to where I live, campaigners against the Cockfosters car park development argued that planning permission should be refused because it would be visible from the green belt, as if the prospect of catching a glimpse of it whilst hurtling along the M25 was a prospect so horrific it didn’t bear thinking about.

In a poorly researched article in the Guardian, Simon Jenkins recently pondered why there wasn’t the same level of protection for the country’s rural parts in the same way that our cities are preserved by Conservation Areas. Any architect or planner could have pointed him towards a whole bunch of protections: AGLV, AONB, Ancient Woodland, SSSI, Ramsar and National Parks, to name a few. Rural areas in fact benefit from far more protections than our towns and cities do, but this is indicative of a wider misunderstanding of planning policy, where green belt is wrongly conflated with other designations that actually do pertain to landscape quality and biodiversity.

It is true that too many open spaces have been relinquished to low-quality, car-dependent sprawl, and nobody – other than the volume housebuilders – wants to see more of that. But, despite what the CPRE claims, we cannot build the homes our country needs on brownfield alone, so some release of open space is inevitable and probably desirable.

There’s a compelling argument that green-belt policy is actually damaging the valuable open spaces that the CPRE is keen to protect. Because building homes is so difficult in places with large areas of green belt, developers target sites beyond it, creating their unsustainable car-dependent sprawl on the outskirts of settlements instead.

Likewise, building new homes on brownfield land far from public transport makes little sense when we could instead cluster them around stations in rural areas, and as an added bonus, give millions of families convenient access to the countryside – something the CPRE claims to support. Not that this should be a free-for-all. Any release of green-belt land for development must be accompanied by robust masterplanning and design codes to ensure that when land is set aside, it is done in a way that is sustainable, accessible, and responsive to local character.

The amount of green belt that would need to be lost to provide a million new homes is so small that it’s little more than a rounding error. Even with modest densities, we’d lose just 1 per cent of the green belt to deliver a million homes. That’s a price worth paying.

Labour’s recent pronouncements in this respect are welcome – if vague . But there are encouraging signs from planning authorities, such as Enfield, that are prepared to tackle this challenge head-on. And emboldened by a lacklustre field of opposition candidates, the mayor of London might revisit his blanket opposition to green-belt release in the next iteration of his city-wide spatial plan. We can but hope.

It’s surely time to set ideology aside and face the fact that an evidence-based review of green-belt policy is long overdue. If we’re to have any chance of facing the challenges of the coming decades, we need to roll up our sleeves and, maybe, loosen our belts.

This article originally appeared in the Architects’ Journal.