Monday, March 30, 2026

Whose Judgement Will Cities Learn From?

 Over the past few weeks, I’ve been working through a simulation of Kochi’s development dynamics - trying to understand how policies like TDR, FSI, and conservation incentives actually interact in practice. Check them out if you are interested.

Run the simulation (browser, no install)
https://ajithvyas.github.io/kochi-tdr-model/TDR_Kochi_Baseline_v05a_web.html

→ Click Setup → GO and let it run (~200 ticks)

Interactive policy dashboard
https://kochi-tdr-sandbox.streamlit.app
→ Test different policy combinations and see how outcomes shift

Full paper (method + findings)

https://zenodo.org/records/19249811

All that work led me to a broader question: not just how we simulate cities, but how these simulations begin to feed into decision-making, and increasingly, into AI systems that learn from such data. This short note is an attempt to think through that shift, and what it might mean for urban designers.

Whose Judgement Will Cities Learn From?

From simulation to decision support

Ajith Vyas Venugopalan, Architect, Urban Designer, Urban Researcher

30 Mar 2026

One of the more interesting properties of an agent-based model is that it doesn't produce a single answer. It produces a landscape of possible outcomes, and that landscape itself is information.

Rather than running every combination manually, you define key variables with meaningful threshold values. Together, these form a behaviour space: a structured map of how the system responds under different policy conditions. In this work, that space is visualised through the dashboard. But it can also be exported as synthetic datasets - each scenario becoming a structured input-output pair, with policy configurations as inputs and spatial or economic outcomes as outputs.

This opens two directions worth taking seriously.

The first is econometric. These datasets allow us to quantify how strongly each variable drives outcomes - moving the model from exploration toward genuine decision support. In the Indian context, this matters in a specific way: our planning systems are full of policies that exist on paper but have never been empirically tested against each other. FSI bonuses, TDR, heritage overlays, CRZ buffers - they interact constantly, but we rarely have structured evidence of how. Synthetic data from calibrated simulations can begin to fill that gap.

The second direction is generative AI. The same datasets can train models that learn the relationship between policy inputs and spatial outcomes - making it possible to generate and evaluate design alternatives based on learned patterns, not isolated scenarios. This is not speculative. It is already the direction that tools like Autodesk Forma, Delve (https://www.bluelabellabs.com/work/delve/), and emerging urban foundation models are heading.

The specific role urban designers can play, and why it matters

This is where I think the profession has an underappreciated opportunity, especially in India.

In machine learning, there is a practice called Reinforcement Learning from Human Feedback (RLHF). In language models, human evaluators assess outputs and signal what is better or worse, and the model learns from that signal. The quality of the system depends directly on the quality and consistency of human judgement brought to that evaluation.

Urban designers are, in a very precise sense, positioned to perform this role for spatial AI systems.

Consider what experienced urban designers actually carry: the ability to read a street section and sense whether it will feel safe at night, to look at a land use mix and anticipate conflict or vitality, to recognise when a setback regulation is producing dead frontage rather than amenity. This is not vague intuition. It is pattern recognition built from years of navigating the gap between what regulations say and what cities actually do.

In the Indian context, that gap is particularly wide. Our cities carry layers of informal adaptation - setbacks converted to shops, FARs exceeded and regularised, roads that exist on master plans but not on ground. A purely algorithmic system trained on formal data will systematically misread this. Human designers who understand how Indian cities actually function (not just how they are planned) are essential correctives.

Concretely, this positions urban designers to contribute at two stages of emerging AI workflows:

At the pre-training stage: defining what variables matter, how spatial outcomes should be measured, and which relationships the model should learn. This is not a technical task — it is a design task. Deciding that pedestrian permeability matters more than plot coverage in a given context is a judgement call, and it shapes everything downstream.

At the inference stage: evaluating generated alternatives - flagging when an algorithmically optimal layout is socially implausible, when a density configuration ignores informal use patterns, or when a policy scenario is technically feasible but contextually absurd. In India especially, this requires someone who understands the distance between what a model can optimise and what a city can absorb.

A reframing worth considering

The anxiety in design professions about automation often frames the question as: will machines replace designers? That framing is probably not the useful one.

The more interesting question is: whose judgement will the machines learn from?

If urban designers do not engage with simulation, synthetic data, and AI workflows, those systems will be built anyway - trained on whatever data is available, evaluated by whoever is willing to do the evaluation. The values and spatial intelligence embedded in those systems will reflect that.

Developing fluency in agent-based modelling and structured data thinking is not, then, simply a technical upgrade. It is a way of ensuring that the accumulated spatial knowledge of the profession - including the hard-won, India-specific knowledge of how cities here actually work - remains part of how future design systems are built and used.

That seems worth doing deliberately, rather than leaving to chance.

Thursday, March 5, 2026

Kerala 2023: Visualising Built Intensity from Satellite-Derived Building Volume

 


I have been experimenting with the World Settlement Footprint 3D (WSF-3D) dataset to explore what Kerala’s settlement structure looks like when we move to look at built volume.

Using QGIS, I processed the global WSF-3D data, clipped it to Kerala, and classified the resulting raster to produce this map of building volume intensity.

Each pixel in the map represents roughly 90 m × 90 m on the ground. The value associated with that pixel reflects the estimated volume of built structures within that space, combining information on both building height and building footprint density derived from satellite observations.

Higher values therefore indicate areas where buildings are taller and more densely concentrated, while lower values correspond to more dispersed or low-rise settlements.

The map hints at a practical planning challenge: Kerala’s risk, infrastructure demand, and service catchments don’t align neatly with a few municipal boundaries. Built intensity behaves like a state-scale system, which is why corridor-level mobility, drainage, housing, and hazard planning often matter as much as city-level projects. Such spatial signatures suggest that Kerala’s urbanisation operates as a networked regional system, where infrastructure, mobility, and economic flows shape settlement intensity.

Data source: DLR World Settlement Footprint 3D (WSF-3D)
Map processing and visualisation: Ajith Vyas Venugopalan


Tuesday, February 24, 2026

Proposed: Kerala Urban Monsoon Infrastructure Mission (KUMIM)

 

Kerala’s urban crisis is not primarily a crisis of insufficient infrastructure. It is a crisis of monsoon misalignment.

Across the State, roads are widened, flyovers erected, canals partially revived, and drainage works sanctioned. Yet every intense rainfall exposes the same fragility: waterlogging at junctions, transport paralysis, property damage, economic slowdown, and a quiet erosion of public confidence. In a geography defined by high rainfall, short catchments, tidal interfaces, backwaters, and midland slopes, urban development has proceeded as if hydrology were an afterthought rather than the structuring force of settlement.

The Kerala Urban Monsoon Infrastructure Mission (KUMIM) proposes a structural shift. It is not another drainage scheme. It is a statewide urban design and governance doctrine that positions hydrology as the organizing logic of urban development. Streets, canals, public spaces, transit corridors, redevelopment zones, and land-use permissions must be conceived as components of a coherent stormwater performance system rather than as isolated projects delivered by separate departments.

Kerala’s settlement morphology is fundamentally distinct from compact metropolitan regions elsewhere in India. It is a linear, ribboned, water-interlaced landscape stretching from coast to highlands, with high population density and deep ecological interdependence. Urban expansion has largely followed plot-by-plot approvals and incremental road improvements rather than watershed-based planning. The result is a water-abundant geography experiencing progressive surface hardening without proportional hydrological recalibration.

At present, there is no unified, city-scale hydro-spatial asset registry linking drains, culverts, canals, road elevations, retention areas, outfalls, tidal gates, and pumping systems. There is no legally defined stormwater performance benchmark against which projects are evaluated. Budget heads allocate funds to roads, irrigation, ports, local bodies, housing, and urban development, but none of these are structurally integrated around measurable monsoon performance outcomes. The Annual Plan and Demands for Grants for 2026–27 articulate sectoral investments across irrigation, flood control, roads, urban development, and public works, yet the hydrological coherence of these investments remains implicit rather than explicit.

KUMIM addresses this gap through five foundational pillars.

First, the creation of a Statewide Hydro-Spatial Asset Registry. Every urban local body would map and digitize its complete stormwater network, including primary and secondary drains, canal sections, culverts, bridge openings, road crown levels, natural watercourses, encroachments, and discharge points. This registry would not remain a static GIS archive but become a decision-making instrument linked to planning permissions and capital works approvals.

Second, the introduction of legally enforceable Stormwater Performance Benchmarks. Each urban project above a defined threshold (public or private) would be required to demonstrate that post-development runoff does not exceed pre-development peak discharge beyond a specified limit for defined rainfall return periods. Streets would be classified not only by traffic hierarchy but by drainage function. Redevelopment zones would carry runoff budgets. Public buildings would integrate detention and percolation as standard components rather than optional sustainability features.

Third, watershed-based micro-zoning within urban jurisdictions. Municipal boundaries rarely align with hydrological boundaries. KUMIM would require that all urban planning and infrastructure works be evaluated at the scale of functional catchments. This would transform the logic of road design, canal rehabilitation, and land readjustment. Instead of widening a road and subsequently “adjusting” drains, design would begin with flow paths, retention nodes, and discharge sequencing.

Fourth, convergence of sectoral investments. The State Plan outlay for 2026–27 includes substantial allocations across irrigation and flood control, roads and bridges, inland water transport, housing, and urban development. KUMIM proposes that a defined proportion of these allocations be tagged as Monsoon-Performance Linked Expenditure. This does not necessarily require new money. It requires that existing allocations be structured around shared hydrological metrics. Roads become linear drainage corridors; canals become public blue-green spines; transport hubs become elevated, flood-secure nodes; public spaces double as retention landscapes.

Fifth, institutional reform through a Monsoon Infrastructure Cell at the State level, supported by technical units within major municipal corporations and municipalities. This cell would standardize data formats, rainfall intensity assumptions, modelling protocols, and design codes. It would also produce an annual Urban Monsoon Performance Report benchmarking cities against measurable indicators: flood duration, critical junction waterlogging frequency, canal carrying capacity, percentage of permeable surface, and maintenance compliance.

The economic rationale for KUMIM is compelling. Recurring monsoon disruption imposes cumulative costs, lost working hours, vehicle damage, public health impacts, infrastructure deterioration, and depressed investment confidence. These costs are diffused and therefore politically underestimated. By converting hydrological resilience into a quantifiable performance metric, KUMIM reframes monsoon adaptation as economic stabilization policy.

The environmental rationale is equally urgent. Kerala’s midland slopes, reclaimed wetlands, and coastal margins are ecologically sensitive interfaces. Surface sealing without retention amplifies flash flooding downstream. Canal neglect converts drainage channels into stagnation zones. Climate variability intensifies rainfall events, compressing discharge windows. KUMIM does not treat climate change as an abstract global discourse but as a local hydraulic design condition.

The urban design implications are transformative. Streets cease to be purely vehicular conduits and become calibrated surface-water systems. Canal edges become structured public realms rather than residual backyards. Redevelopment regulations incorporate floodable plazas and stepped embankments. Housing layouts align with micro-topography. Transit corridors are engineered to remain operable under defined storm intensities. The city becomes legible as a layered hydraulic landscape.

KUMIM is therefore not a project list. It is a doctrine. It calls for a shift from reactive pumping and post-flood relief to anticipatory design and measurable performance. It aligns engineering, planning, budgeting, and governance around a single organizing principle: monsoon coherence.

Kerala has historically demonstrated institutional innovation in decentralization, public health, and social development. The Fourteenth Five-Year Plan positions 2026–27 as the culminating year of a strategic cycle. KUMIM proposes that the next strategic leap be the institutionalization of hydrology as urban policy.

If Kerala is a water state, its cities must become water-literate systems. The Kerala Urban Monsoon Infrastructure Mission offers a structured pathway toward that transformation, where every road, canal, culvert, and redevelopment approval contributes to a coherent, measurable, and resilient monsoon infrastructure framework.

The crisis is not of rain. It is of design logic. KUMIM seeks to correct that logic at scale.

Wednesday, February 18, 2026

Beyond the Map: Quantifying Kerala’s 2020–2025 Urban Transition

 

Over the past few weeks, many of you interacted with my earlier GIS-based analysis of Kerala’s urbanisation pattern, where I used GHS-SMOD rasters (2020 and 2025) to create village-level maps of settlement classes and transition patterns.

That study generated a lot of interest, especially around where change was happening and how strongly Kerala’s corridor-led development was reflected in the spatial data.

This new work continues from that point,
but attempts something different: by moving from visual interpretation to statistical explanation.

Why this second stage?

Maps tell us where patterns appear,
but econometrics helps us understand why they occur.

In architecture and planning, we often read patterns intuitively, by looking at maps, densities, sections, corridors, and street networks. But when we want to measure which factors actually drive those patterns, and how strongly, we need a different toolkit.

That toolkit is econometrics.

A quick, non-technical explainer: What is econometrics?

Econometrics is simply: a set of statistical methods that help us quantify relationships in real-world data.

It is not about finance or economics alone; urban researchers, transport planners, public health experts, and environmental scientists all use it.

Three broad types are especially common:

1. Cross-sectional models (like OLS): Used when we want to know how variables relate at a single point in time. E.g., Does highway proximity correlate with higher density?

2. Time-series models: Used for forecasting how something evolves over time. E.g., Predicting population or land price changes.

3. Binary or logistic models (used in this study): Used when the outcome is Yes/No. E.g., Did a village urbanise between 2020 and 2025?

Logistic models allow us to study odds; how much more likely a transition becomes when certain factors are present.

This is exactly what we need to interpret Kerala’s transition map more rigorously.

 

What this study attempts

Using 1,533 villages as spatial units, the analysis brings together:

  • Raster-derived settlement classes (2020 & 2025)
  • Neighbourhood urbanity (adjacency-based mean urban class)
  • Accessibility distances to

a)      nearest highway

b)     nearest railway station

c)      nearest airport

  • District fixed effects
  • Binary and ordered transition variables derived from GIS

The central question becomes:

What factors actually drove Kerala’s village-level settlement transitions between 2020 and 2025?

 

Data Used

From QGIS, each village polygon was enriched with:

Settlement data

  • SMOD 2020 class
  • SMOD 2025 class
  • Cleaned transition variable (up_clean: 1 = upgraded, 0 = no change/downgrade)
  • Transition magnitude (d_us: ordered step-up measure)

Neighbourhood data

  • Mean urbanity of touching neighbours (us20_mean)
  • Count of neighbouring villages

Accessibility measures

  • Distance to nearest highway
  • Distance to nearest railway station
  • Distance to nearest airport

All of these were exported from QGIS into a CSV, forming the basis of the R data frame.


Methods in Simple Language

Most architects and planners don’t use econometrics daily, so here is the essence:

What econometrics does here is that it tells us which factors actually drive a pattern, and how strongly.

The model used is Logistic regression, a method used when the outcome is Yes/No.
Here, the question is: What makes a village more likely to urbanise (upgrade its SMOD class) between 2020 and 2025?

The primary outcome, up_clean, is a binary indicator equal to 1 if a village upgraded its dominant SMOD class between 2020 and 2025, and 0 otherwise. For village i, the probability of upgrade is modelled using a logistic link:

where the linear predictor is:

ηi ​= β0​ + β1​air_HubDisti​ + β2​rail_HubDisti​ + β3​highway_HubDisti ​+ β4​us20i + β5​us20_meani

This baseline specification tests five theoretically motivated effects:

  • Accessibility effects: closer proximity to airports and highways is expected to increase transition probability; the effect of railway distance is empirically ambiguous and treated as exploratory.
  • Baseline settlement type: villages already suburban or urban in 2020 are expected to have lower upgrade probability (less room to transition).
  • Neighbourhood urbanity: villages surrounded by more urban neighbours are hypothesised to exhibit higher transition probabilities due to spatial spillovers.

The baseline model provides the foundational insight into the structural correlates of transition before adjusting for district-level differences.

 

This type of model returns:

  • coefficients → direction & magnitude of influence
  • odds ratios → how much the probability changes
  • significance levels (*, **, ***) → how confidently we can trust the effect

Model 1: Logit Results

=============================================================

                                  Dependent variable:       

                          -----------------------------------

                          Probability of Urbanisation Upgrade

-------------------------------------------------------------

Distance to Airport                   -0.00001***           

                                       (0.00000)            

                                                            

Distance to Railway                    0.00001*             

                                       (0.00001)            

                                                            

Distance to Highway                   -0.0002***            

                                       (0.00003)            

                                                            

Suburban (base=Rural)                  -3.744***            

                                        (0.271)             

                                                            

Dense (base=Rural)                     -5.320***            

                                        (0.574)             

                                                            

Urban Core (base=Rural)                 -26.406             

                                       (514.802)            

                                                            

Neighbour Urbanity (2020)              1.918***             

                                        (0.200)             

                                                            

Constant                               2.732***             

                                        (0.361)             

                                                            

-------------------------------------------------------------

Observations                             1,529              

Log Likelihood                         -601.518             

Akaike Inf. Crit.                      1,219.037            

=============================================================

Note:                             *p<0.1; **p<0.05; ***p<0.01

Table 2: Regression result of baseline Model1

How to Read This Table (Very Simply)

Most planners are not trained to interpret econometric tables, so here is the clue sheet:

  • Positive value → increases the chance of urbanisation
  • Negative value → decreases the chance
  • *** → highly reliable
  • ** → fairly reliable
  • * → weakly reliable
  • blank → could be noise

For example:

  • “Highway distance = negative & ***”
    → the farther a village is from a highway, the much less likely it is to urbanise.
  • “Neighbour urbanity = positive & ***”
    → villages surrounded by more urban villages almost always transition themselves.

These help us move from visual intuitionmeasurable evidence.

To make this concrete, here is what the actual model values mean:

  • Highway Distance (−0.0002, *** )
    Every additional 1 km from a highway reduces the odds of urbanising by about 20%.
    Villages 5 km away have almost half the transition probability of those close to the highway.
  • Airport Distance (−0.00001, *** )
    Being 10 km farther from an airport lowers the odds by roughly 10%.
  • Railway Distance (+0.00001, * )
    A weak positive effect (statistically marginal) reflecting Kerala’s already railway-dense belts.
  • Neighbour Urbanity (1.918, *** )
    Villages surrounded by more urban neighbours are 6–7 times more likely to urbanise themselves.
    Urbanisation spreads spatially.
  • Baseline Class (compared to Rural):
    Suburban → 97% lower odds
    Dense Urban → 99% lower odds
    Urban Core → almost zero odds
    (Simply because they have little “headroom” to shift further up.)

These quantified effects transform the earlier GIS pattern from an intuitive observation into evidence-backed understanding.

What the results reveal

1. Transport accessibility matters a lot.

2. Neighbourhood effects are powerful.

3. District boundaries matter far less than we think.

Why this matters for us architects, planners, and in policy conversations

This combined GIS + econometric approach moves us from:

“It looks like a pattern” → “This is the measurable reason behind the pattern.”

For planning discussions, infrastructure prioritisation, LAP preparation, or regional mobility strategies, evidence like this helps shift debates from intuition to measurable drivers.

And for young designers or researchers, this demonstrates how spatial and statistical thinking can complement each other; visualisation tells us what is happening, econometrics tells us why.



Monday, February 9, 2026

The Pillars at Vyttila: What They Reveal About Kochi‘s Planning

 Every commuter who passes through Vyttila carries a small private irritation. It sits there each morning, somewhere between the steering wheel and the bumper ahead. You approach the junction from Tripunithura or Kadavanthara, and just as the signal opens, a concrete pillar suddenly appears to sit illogically and insensitively in the middle of everything, spreading chaos all around. Buses swing wide to avoid it. Autos squeeze between edges that were never meant to be edges. Near-misses are negotiated like practiced, last-minute reflexes. A flyover and the metro line glide overhead, elegant and modern, while below it traffic performs an elaborate daily dance of compromise.

What few commuters realize is that each of these elements; the flyover, the metro viaduct, the bus terminal, the service roads, even the traffic signals were conceived and delivered as separate projects by separate institutions. None of them were designed as parts of a single integrated system. The awkward geometry that drivers curse every day is therefore not an engineering accident. It is the physical outcome of many independent decisions taken in isolation from one another.

The pillars of the Vyttila flyover are not merely pieces of infrastructure. They are physical reminders of a deeper problem: different parts of the city are designed by different agencies, at different times, with different priorities, and without a single mind guiding them. What looks like a badly placed column is actually the visible tip of an invisible institutional iceberg.

Behind that single pillar lies an entire chain of disconnected processes. One agency prepared the flyover design years ago with a narrow mandate to improve vehicular movement. Another agency later introduced the metro line with its own technical constraints and safety requirements. Yet another body manages the bus operations and terminal layouts. The city corporation controls local streets and drainage, while traffic police handle day-to-day management. Each actor responded to its own brief, its own budget cycle, and its own deadlines. Coordination was assumed; it was never institutionally guaranteed.

Urban planning is often discussed in abstract terms; density, transit-oriented development, pedestrianization, mixed use. But the lived reality of Kochi is more prosaic. It is experienced as congestion at junctions, missing sidewalks, awkward bus bays, and signal cycles that seem to have been programmed for another planet. What makes Vyttila particularly challenging is the sheer density of institutions compressed into one small geography. Within a small zone operates the Public Works Department, the National Highways Authority, Kochi Metro Rail Ltd, Vyttila Mobility Hub, the Greater Cochin Development Authority, the Kochi Corporation, and a host of utilities and private stakeholders. Each organization has a legitimate role, but none of them has the mandate to see the junction as a whole. The everyday chaos experienced by commuters is therefore less a failure of traffic engineering and more a failure of institutional design. Vyttila embodies all of this in one compact geography. It is Kochi’s largest mobility hub and at the same time one of its most confusing urban spaces.

Today, a Local Area Plan (LAP) is being prepared for Vyttila by CEPT University, Ahmedabad, as part of the implementation process of the Kochi Municipal Corporation Master Plan. On paper, this is exactly what the city needs: a fine-grained plan to bring order to a complex and important location. Yet the question that quietly troubles many professionals is this; will another plan really solve problems that previous plans could not?

Local Area Plans are meant to stitch such fragmented realities together. They map land uses, propose street networks, identify public spaces, and suggest coordinated development controls. In theory, once an LAP is approved, all agencies should align their projects to it. In practice, however, a plan by itself has no budget, no staff, and no authority over project schedules. It can draw a better future on paper, but it cannot compel one department to change priorities for the sake of another. This gap between planning intent and institutional capacity explains the quiet anxiety around yet another plan for Vyttila.

In other words, the limits of the LAP are not about the quality of CEPT’s drawings. They are about the machinery required to execute them. A plan can describe coordination, but it cannot manufacture it. Coordination happens only when budgets, project schedules, and approvals are forced into the same room. Plans, by themselves, coordinate very little. Budgets coordinate a lot more. Institutions coordinate the most.

What the Vyttila story hints at is the absence of a single accountable “area manager” for the node. Not a mega-authority, not another layer of bureaucracy, but a small, empowered coordination cell whose job is to align the agencies already present. Many global cities solve precisely this problem by creating a special-purpose institution for a defined geography; an SPV-like entity that is judged not on reports produced, but on outcomes delivered.

The real story of Vyttila is therefore not only about urban design. It is about how projects are sanctioned, who controls land, how budgets are allocated, and how responsibilities are divided. Until these underlying mechanisms are understood, it is impossible to explain why a junction that has seen so much investment continues to feel so unresolved.

A Junction Designed by Many Hands

Imagine, for a moment, that you are trying to redesign the Vyttila node from scratch. You would quickly discover that there is no single “owner” of the problem. The roads approaching the junction fall under the Public Works Department and the National Highways Authority. The flyover is a separate project. The metro station and its surrounding lands belong to Kochi Metro Rail Ltd. The bus terminal is controlled by the Vyttila Mobility Hub Society. The city corporation manages local streets and drainage. Other agencies own additional parcels nearby. Add to this mix traffic police, utilities, private landowners, and commercial establishments.

Each of these actors has a legitimate mandate. Each also has its own budgets, timelines, political pressures, and institutional cultures. None of these objectives were wrong. But they were rarely harmonized.

The result is what planners politely call “layered infrastructure.” Projects arrive one after another like geological strata, each responding to a narrow brief, rarely to a shared vision. Over time, the gaps between them become the everyday inconveniences that commuters experience.

And beneath this institutional misalignment lies a second challenge: land. Every improvement that citizens expect; safer crossings, proper bus bays, continuous footpaths, a real plaza, eventually confronts the question, “on whose land will this happen?” In Vyttila, ownership is split among multiple public bodies and hundreds of private plot holders. When land is fragmented, coordination becomes cosmetic unless the plan is paired with tools that can pool space, compensate losses, and share gains.

 

When Plans and Agencies Do Not Speak the Same Language

Local Area Plans are supposed to provide coordination. In practice, they rarely do. A plan cannot control project schedules, cannot reallocate budgets, and cannot overrule departmental priorities. An LAP might propose a pedestrian plaza in front of the metro station, but if even one agency disagrees, the idea remains a picture in a report. This is what professionals mean by “institutional misalignment.” The system offers no mechanism to force cooperation.

How Other Cities Handle Places Like Vyttila

Around the world, complex transit nodes similar to Vyttila have been transformed through a simple insight: coordination does not happen because a plan exists. It happens because a dedicated institution exists to implement the plan. Successful cities create special-purpose entities that bring agencies to the same table, align budgets, and resolve conflicts. Without such an institution, even the best LAP remains advisory.

Why Vyttila Needs More Than a Good Design

The CEPT-led LAP can offer Kochi excellent proposals. But design alone cannot fix governance. Pedestrian paths end abruptly at jurisdictional boundaries because no single body feels responsible for the whole. Problems that look technical are often institutional. What Vyttila needs is not just a Local Area Plan, but a Local Area Management Framework.

The Case for a Vyttila Node Authority – Turning Plans into Action

A practical way forward would be to establish a dedicated coordination platform for the Vyttila area; a Vyttila Node Authority or an Integrated Area Management Cell. This need not be a large bureaucracy. It can be a lean, empowered unit hosted by an existing institution such as CSML, or KMRL or the Kochi Corporation, but with explicit statutory backing.

For such a body to be effective, it would require three concrete instruments that Kochi currently lacks.

First, a legal backbone. The LAP area should be formally notified as a Special Planning and Implementation Zone under Kerala planning law, so that projects within a clearly defined boundary are treated as part of one operational territory rather than as scattered departmental fragments.

Second, a single-window approval framework. Instead of separate clearances from the corporation, PWD, KMRL, utilities, fire services, and traffic police, projects in the node should pass through one composite approval track aligned to the LAP. Predictability is itself a form of coordination.

Third, joint capital planning. Every year, the major actors CSML, KMRL, KSRTC, PWD/NHAI, GCDA, and the KM Corporation should be required to prepare a combined investment calendar for the node. A simple rolling ten-year schedule of who builds what, when, and with whose money is the mundane discipline that successful cities rely on.

Such a unit would also manage shared GIS data, a common project dashboard, and standardized design codes so that streets, plazas, signage, and utilities are built to a single vision. For citizens and developers, the node would offer one predictable interface instead of a maze of offices.

This is how many global transit districts actually function; not through grand master plans, but through patient institutional choreography.

 

The Land Question - Making Space for Change

Even perfect coordination fails if the question of land is ignored. In Vyttila, every serious proposal ultimately collides with fragmented ownership. Without clear mechanisms to manage land and value, even the best-governed LAP will struggle.

Around the world, cities typically rely on three broad models.

The first is consolidated public ownership, where strategic public parcels are pooled into a land bank or development corporation and the district is redeveloped as a single coordinated estate. This approach explains the seamless integration of stations and development in places like Hong Kong.

The second is land readjustment, widely used in Japan and Korea. Here, owners temporarily pool plots, the city deducts land for streets and public spaces, and owners receive back smaller but far more valuable parcels with better access and higher development potential. Infrastructure is paid for through land rather than cash.

The third model keeps ownership fragmented but coordinates through rights and incentives: transferable development rights, air-rights development above public land, and joint development agreements that allow infrastructure and private projects to be integrated without wholesale acquisition.

For Kochi, a pragmatic path lies in a hybrid of these approaches.

The first practical step would be a comprehensive Vyttila land inventory; a legally credible register of who owns what, under what conditions, and with what development potential. Without this, policy remains guesswork.

Once that exists, land can be treated in three distinct buckets.

Strategic public lands: metro precincts, bus terminal sites, key road reserves should be operationally pooled under the node authority so that public projects stop competing with one another.

Private land required for public purposes: small strips for footpaths, junction geometry, pedestrian links, can be addressed through negotiated purchase, readjustment pilots, or TDR rather than blanket acquisition.

The remaining private parcels can stay private, but redevelopment can be shaped through clear form-based rules and contributions to the public realm.

The essential insight is this: coordination does not always require unified ownership. It requires unified value logic. If agencies and owners see clear mutual benefit, cooperation becomes possible without massive land takeovers.

For Vyttila, the most realistic strategy is therefore hybrid governance and hybrid ownership: pool public lands where feasible, leave private lands largely in place, and align redevelopment through TDR, air-rights, design codes, and joint development.

In one line: coordinate value, not necessarily land.

From Frustration to Opportunity

The awkward pillars at Vyttila will not disappear soon. But they can still serve a purpose. They remind us that urban problems are rarely just engineering problems. They are symptoms of how decisions are organized.

Kochi stands at an important moment. With the metro expanding and mobility pressures growing, the city has an opportunity to rethink how it manages its most important node. The CEPT-prepared LAP can become more than another report, if it is paired with new institutional arrangements that bring agencies, budgets, and land into the same conversation.

If that happens, Vyttila can slowly transform from a symbol of confusion into a model of coordinated urban development. If it does not, the daily dance around those concrete pillars will continue.

Good cities are not built only by good designers. They are built by systems that allow many actors to work as if they were one. The real challenge at Vyttila is to create that system.

Friday, February 6, 2026

Mapping Kerala’s Urban Shift, DEGURBA (2020–2025)

 

Abstract

This study maps and quantifies the changing settlement character of Kerala’s villages between 2020 and 2025 using the European Commission’s Global Human Settlement - Settlement Model (GHS-SMOD) dataset. Rather than focusing only on cities, the analysis examines all 1,533 administrative villages of Kerala and classifies each of them according to internationally standardised DEGURBA*(ref: footnote) categories ranging from rural to urban centre. A majority-class zonal statistics method was used to translate global raster data into village-level indicators, enabling direct comparison across the two time periods. The results reveal that 910 villages (nearly 60 percent of Kerala) experienced a shift in their dominant settlement classification within just five years, overwhelmingly in an upward direction along the urban hierarchy. The findings confirm that Kerala’s urbanisation is not concentrated only in major cities but is occurring as a widespread, incremental transformation across ordinary villages. The study demonstrates how global remote-sensing datasets can be converted into locally meaningful insights for planners and researchers seeking to understand distributed urban change.

Introduction

Urbanisation in India is usually described through the growth of large cities; expanding metropolitan regions, rising skylines, and new infrastructure corridors. Kerala, however, does not fit neatly into this conventional narrative. Its settlement pattern has long been recognised as dispersed and corridor-like, with a blurring of distinctions between “urban” and “rural.” As a result, much of Kerala’s transformation happens not within officially designated cities, but across hundreds of ordinary villages.

This study shifts the focus from cities to villages. Instead of asking how fast Kochi or Kozhikode is growing, it asks a more grounded question: how has the settlement character of Kerala’s villages changed between 2020 and 2025? To answer this, the analysis uses global, standardised spatial data rather than administrative labels, and applies them consistently across the entire state.

The objective is to translate global settlement information into a form that is directly relevant for local planning and governance. By examining every administrative village in Kerala using the same dataset and method, the study seeks to reveal patterns of change that remain invisible in conventional city-centric analyses.

What Do We Mean by “Village”?

For this study, a village is defined strictly as an official administrative village unit of Kerala, based on the Census 2001 spatial framework (with updated boundaries), used as the standard polygon layer for analysis.

Kerala has 1,533 such villages, and every map and statistic in this study refers to these same 1,533 administrative units.

This means the analysis is not about pixels, neighbourhoods, wards, or towns.
It is about real, named villages as recognised in Kerala’s administrative system.

Data Source

The analysis uses the Global Human Settlement – Settlement Model (GHS-SMOD) dataset produced by the European Commission’s Joint Research Centre.

This dataset classifies every 1 km grid cell of the world into standardised settlement categories based on built-up density and population thresholds:

  • Unpopulated
  • Very Low Density Rural
  • Low Density Rural
  • Rural Cluster
  • Suburban / Peri-urban
  • Semi-dense Urban Cluster
  • Dense Urban Cluster
  • Urban Centre

Two time slices of this dataset were used: (https://humansettlement.emergency.copernicus.eu/download.php?ds=smod)

  • GHS-SMOD 2020
  • GHS-SMOD 2025

Using the same global dataset for both years ensures methodological consistency and allows meaningful comparison over time.

Method: From Global Raster to Kerala Villages

The challenge was to convert a global pixel-based dataset into a format meaningful for local planning and governance.

The workflow followed was:

  1. SMOD raster layers for 2020 and 2025 were clipped to the Kerala boundary
  2. Kerala village polygons were overlaid on the raster layers
  3. Zonal statistics were computed for each village
  4. For every village, the majority SMOD class was extracted
  5. Each village was assigned a single dominant class for 2020 and for 2025
  6. A transition matrix was generated to track changes

This “majority class method” converts a complex raster surface into a simple, interpretable question:

What kind of place is this village – mostly rural, suburban, or urban?

(Initial exploratory maps were prepared by directly overlaying Kerala village boundaries on the raw SMOD raster layers for 2020 and 2025. While these maps were useful for visual inspection, they did not provide a systematic basis for comparison because each village contains multiple SMOD classes. The final analysis therefore adopted the majority-class zonal statistics method, which assigns a single dominant category to each village and enables consistent year-to-year comparison.)

Kerala in 2020: The Baseline

The 2020 map shows the dominant settlement character of each village at the start of the period.

 


Map 1: Kerala Village-Level DEGURBA Classification – 2020. Source: GHS-SMOD (JRC, European Commission). Analysis & Mapping: Ajith Vyas Venugopalan, 2026.

The map visually demonstrates that Kerala does not follow the conventional Indian pattern of isolated cities surrounded by rural hinterlands. Instead, it reflects a corridor-like, dispersed urbanisation pattern.

Several patterns are immediately visible:

  • A near-continuous belt of Urban Centres along the western coastal corridor
  • Extensive Suburban and Peri-urban zones spreading inland
  • Clearly rural clusters concentrated in the eastern highlands
  • A corridor-like urban structure rather than isolated, compact cities

Even in 2020, Kerala already appeared less like a typical Indian state and more like a distributed urban region.

 

Kerala in 2025: Intensification of Urban Form

 

Map 2: Kerala Village-Level DEGURBA Classification – 2025 . Source: GHS-SMOD (JRC, European Commission). Analysis & Mapping: Ajith Vyas Venugopalan, 2026

This map captures the accelerating urban diffusion occurring beneath formal city boundaries.

By 2025, the spatial pattern shows clear intensification:

  • Many villages shift into Semi-dense and Dense Urban categories
  • Suburban zones push further eastward
  • Urban Centres expand around Kochi, Kozhikode, Thrissur, and Thiruvananthapuram
  • Areas previously classified as rural show visible upward movement in the urban hierarchy

This is urbanisation not through a few mega-projects, but through hundreds of small, incremental transformations.

 

How Many Villages Actually Changed?

To move beyond visual impressions, the dominant class of each village in 2020 was directly compared with its class in 2025.

 

Map 3: Villages with DEGURBA Class Change (2020–2025) . Source: GHS-SMOD (JRC, European Commission). Analysis & Mapping: Ajith Vyas Venugopalan, 2026

 

A striking proportion of Kerala’s villages show change, highlighting how rapidly settlement structures are evolving, even outside major cities.

Out of 1,533 villages in Kerala:

Indicator

Number

Villages that changed class

910

Villages with no change

623

Percentage showing change

59.4%

Percentage unchanged

40.6%

In just five years:

Nearly three out of every five villages in Kerala altered their dominant settlement character.

This is not a marginal adjustment.
It is evidence of widespread structural transformation.

 

What Kind of Change Took Place?

Not all changes are equal.

Some villages moved only one step up the hierarchy, while others jumped multiple levels.

 

Map 4: Detailed Transition Map (2020 → 2025) . Source: GHS-SMOD (JRC, European Commission). Analysis & Mapping: Ajith Vyas Venugopalan, 2026

The village-level transition map shows where change occurred; the transition chart explains how that change unfolded. When the 2020 and 2025 classifications are compared village by village, a clear structural pattern emerges: most movement is upward along the urban hierarchy. The dominant shifts are not dramatic leaps from rural to city, but steady step-by-step transitions; from Very Low Rural to Suburban, from Suburban to Dense Urban, and from Semi-dense Urban to full Urban Centre status. This indicates that Kerala’s urbanisation is less about the sudden appearance of new cities and more about the gradual thickening of existing settlements across the state.

Transition Trends

 

Fig 01: Distribution of Village-Level Urban Transitions in Kerala (2020–2025)
Number of villages undergoing specific DEGURBA class transitions between 2020 and 2025. The chart summarises the direction and magnitude of change, showing that most transitions represent upward movement along the urban hierarchy – particularly from rural and suburban categories into semi-dense and dense urban classes. Analysis & Graph: Ajith Vyas Venugopalan, 2026

The numerical distribution of transitions reinforces this interpretation. Out of 1,533 villages, 910 experienced an upward reclassification between 2020 and 2025, while only a very small number showed any downward movement. The largest share of transitions occurred from Very Low Rural and Low Rural categories into Suburban and Semi-dense Urban classes, confirming that peri-urban expansion is the primary mechanism of change. What stands out is the breadth rather than the intensity of transformation: urbanisation in Kerala is occurring simultaneously in hundreds of ordinary villages, not just within established metropolitan cores. The evidence points to a process that is incremental, distributed, and remarkably consistent across the state.

Key Findings

The comparison of village-level classifications between 2020 and 2025 reveals a remarkably rapid transformation of Kerala’s settlement structure. Out of 1,533 administrative villages analysed, 910 villages (nearly 60 percent) changed their dominant DEGURBA class within just five years, while only 623 villages retained the same category. This scale of change confirms that Kerala is experiencing not isolated pockets of growth but a broad, system-wide shift in settlement character. The dominant direction of movement is clearly upward along the urban hierarchy: very low rural areas becoming suburban, suburban areas intensifying into dense urban clusters, and several already-urban locations transitioning into full urban centres.

The transitions also show that Kerala’s urbanisation is fundamentally diffused rather than city-centric. Change is not restricted to Kochi, Kozhikode, or Thiruvananthapuram alone; it is visible across almost every district, including Malappuram, Thrissur, Palakkad, Kannur, and Alappuzha. What emerges is a pattern of incremental but widespread intensification, where villages gradually acquire urban characteristics without necessarily being reclassified administratively. In effect, the analysis highlights a growing mismatch between official labels and on-ground reality: many places still called “villages” now function as suburbs, commuter settlements, or small towns within an increasingly continuous urban region.

Limitations

The analysis presented here has several important limitations that must be recognised. The GHS-SMOD classification relies on global population-density thresholds rather than definitions tailored specifically to Kerala’s unique settlement patterns. The majority-class method, while practical and transparent, inevitably simplifies internal heterogeneity within villages, many of which contain mixed rural and urban characteristics. Large administrative villages, in particular, can include dense town centres as well as sparsely populated agricultural areas. The study also assumes methodological consistency between the 2020 and 2025 SMOD datasets, an assumption that is reasonable but not entirely within the control of the analyst. Despite these constraints, the approach provides a replicable and objective framework for translating global raster data into meaningful, locally interpretable indicators of change.

Conclusion

What emerges from the comparison of 2020 and 2025 is not merely a picture of incremental growth, but evidence of a deeper spatial transformation. Kerala did not simply become more urban in this period; it urbanised in a different way, with change occurring far beyond the traditional confines of major cities. The shift unfolded across hundreds of ordinary villages, reflecting a dispersed and distributed process rather than isolated expansion nodes. By converting global datasets into village-level insights, the study demonstrates how large-scale remote-sensing information can be grounded in local geography and governance. Taken together, the maps tell a clear story: urbanisation in Kerala is no longer a discrete event confined to a few locations, but a continuous and pervasive process reshaping the entire landscape.

Data and Credits

Data Source:
European Commission, Joint Research Centre. Global Human Settlement Layer – Settlement Model (GHS-SMOD). Available at: https://human-settlement.emergency.copernicus.eu

Boundaries Used:
Kerala administrative village polygons

Methodology:
Raster zonal statistics using majority class assignment and transition analysis

Software:
QGIS

Analysis and Cartography:
Ajith Vyas Venugopalan

 



DEGURBA (Degree of Urbanisation) is an internationally used system developed by the European Commission to classify human settlements based on population density and built-up continuity. It does not rely on local administrative definitions of “town” or “village,” but instead uses objective thresholds applied uniformly across the world. The GHS-SMOD dataset used in this study assigns every 1 km grid cell to one of eight categories:

Unpopulated, Very Low Density Rural, Low Density Rural, Rural Cluster, Suburban/Peri-urban, Semi-dense Urban Cluster, Dense Urban Cluster, and Urban Centre.

This approach allows places to be compared on the basis of their physical and demographic characteristics rather than legal status. In the Kerala context, it provides a way to measure urbanisation that is independent of municipal boundaries or official reclassification.