The team chose two deliberately contrasting case cities: Hong Kong and Zurich. Hong Kong is one of the densest vertical metropolises on Earth, a subtropical city where compact high-rise development presses against steep green terrain and a heavily engineered coastline. Zurich, by contrast, is a mid-sized European city with a temperate climate, lower densities, and a long tradition of green infrastructure planning. If consistent form–function relationships could be detected across two such different urban contexts, the researchers reasoned, those relationships would be far more convincing as general principles of sustainable urban design than findings drawn from a single city.

To capture multifunctionality, the study analyzed five key urban functions spanning social, ecological, and infrastructure domains: heat mitigation, pluvial flood regulation, bird diversity, a mortality-derived health outcome, and small business vitality. This selection is significant because most previous studies have evaluated urban functions in isolation—asking, for example, how tree canopy affects temperature, or how street connectivity affects commerce—without examining how the same physical features perform across multiple functions simultaneously. By assessing several functions together, the researchers could identify where benefits align into synergies and where they collide into trade-offs, the two currencies of multifunctional assessment.

The technical heart of the study lies in characterizing urban form and linking it statistically to each function across the two cities. Urban form descriptors included the coverage of impervious surfaces such as asphalt, concrete, and rooftops; the configuration of green space, including the size and shape irregularity of green patches; and the proximity of urban locations to water bodies. Each of these form variables was then associated with spatially explicit measures of the five functions, allowing the team to compare the direction, magnitude, and spatial heterogeneity of relationships in Hong Kong against those in Zurich. This comparative framework, built around a clearly defined and representative indicator set, is one of the study’s principal methodological contributions.

Some results were strikingly consistent across both cities. Increased impervious surface coverage was negatively associated with both pluvial flood regulation and heat mitigation—hardly a surprise to urban climatologists and hydrologists, since sealed surfaces prevent rainfall infiltration and store and re-emit heat—but the consistency of the signal in two climatically and morphologically different cities strengthens the case that reducing impervious cover is a robust, transferable design lever. Conversely, proximity to water was positively associated with both flood and heat mitigation functions, and was tentatively associated with the mortality-derived health outcome as well. Water, in other words, emerged as a rare form element whose benefits appear to ripple across multiple domains at once, echoing the growing international interest in blue-green infrastructure.

Green space, however, told a more complicated and arguably more interesting story. Rather than acting as a universal good, the form of green space was associated with urban functions in diverse ways that can involve genuine trade-offs. The most vivid example reported in the study concerns patch shape: irregular green patches—those with convoluted, ragged edges rather than compact outlines—were associated with higher bird diversity but lower pluvial flood mitigation capacity. Ecologists have long known that complex habitat edges can support richer avian communities, but the same irregular geometry appears to diminish the hydrological performance of green areas. For planners, this means a single prescription such as add more greenery cannot be applied blindly; the geometry of that greenery matters, and it matters differently for different functions.

Although the overall direction of the form–function relationships was generally consistent between Hong Kong and Zurich, the magnitude and spatial heterogeneity of those relationships differed, and the authors relate these differences to city-specific characteristics. In practical terms, the same increment of impervious surface or the same change in green patch configuration does not buy or cost the same amount of cooling, drainage capacity, biodiversity, health benefit, or commercial vitality in a subtropical vertical city as it does in a temperate European one. Local climate, topography, building morphology, and existing ecological conditions all modulate how strongly a given form element expresses its functional consequences. This is a caution against copy-pasting design guidelines across continents, but also an argument for the kind of diagnostic, city-specific assessment the study’s framework enables.

The inclusion of mortality-derived health outcomes and small business vitality alongside the more conventional ecological and hydrological indicators is what gives the study its cross-domain ambition. Heat and flooding are environmental hazards; bird diversity is an ecological signature; but mortality-based health measures and the vitality of small businesses are profoundly human concerns. By showing that urban form is simultaneously associated with functions within and across these ecological and human domains, the study makes the case that the city is best understood as an integrated system in which a planning decision in one domain inevitably transmits consequences into others. A street tree strategy is a public health strategy is, potentially, an economic strategy.

For practitioners, the implications are twofold. First, synergies should be actively hunted: form elements such as water proximity, which appear to deliver benefits across several functions, represent high-leverage interventions in the urban fabric. Second, trade-offs must be made explicit and balanced deliberately rather than discovered after the fact. The study’s multifunctional assessment framework provides a template for doing exactly that—mapping where functions align and conflict within a defined indicator set, and using those maps to guide zoning, greening, and infrastructure decisions. As cities worldwide confront intensifying heat, more extreme rainfall, biodiversity loss, and economic pressure on neighborhood commerce, the message of this research is that the shape of the city is not a neutral backdrop but an active determinant of how many things a city can do well at once.

The work was funded in part by the Future Cities Lab Global programme, supported by the National Research Foundation of Singapore under its CREATE programme and ETH Zurich, with contributions from the National University of Singapore, Nanyang Technological University, and the Singapore University of Technology and Design, and Yue Zhu received additional support from the Science and Technology Development Fund of the Macao SAR. Published open access in npj Urban Sustainability, the study establishes a comparative foundation that other cities can adapt—provided they respect the central lesson of Hong Kong and Zurich: the relationships are real and repeatable, but their strength and spatial texture are always local.

Subject of Research: Associations between urban form and multifunctionality across ecological and human urban functions in Hong Kong and Zurich

Article Title: Associations between urban form and urban multifunctionality: a comparative study

Article References: Zhu, Y., Burlando, P., Zhang, Y., Huang, J., Chi, D., Wang, J., Qiu, Y., Manoli, G., Fatichi, S., & Tan, P. Y. (2026). Associations between urban form and urban multifunctionality: a comparative study. npj Urban Sustainability. https://doi.org/10.1038/s42949-026-00481-3

Image Credits: AI Generated

DOI: 10.1038/s42949-026-00481-3

Keywords: urban form, urban multifunctionality, heat mitigation, pluvial flood regulation, bird diversity, green space, impervious surfaces, blue-green infrastructure, Hong Kong, Zurich, urban sustainability, comparative study

The study, published in the journal Theoretical and Applied Climatology, was led by Kajesh Gadekar and Aneesh Mathew, who combined satellite imagery, spectral indices, and machine learning into a single analytical framework. To track how the city’s surface changed, the team classified multi-temporal Landsat imagery into land use and land cover categories, revealing the steady march of construction across Chennai’s fringes. To quantify the heat island itself, they turned to nighttime land surface temperature data from the Moderate Resolution Imaging Spectroradiometer, or MODIS, instrument, which allowed them to compute annual and seasonal heat island intensities consistently across the entire two-decade window. Nighttime measurements are particularly revealing for urban climate science because that is when the thermal contrast between dense cities and their rural surroundings is most pronounced, as built-up materials continue radiating stored heat long after sunset while rural soils and vegetation cool quickly.

One of the most striking findings is seasonal. Counterintuitively, the urban heat island in Chennai was strongest in winter, not summer, peaking at 2.21 degrees Celsius in 2018. The explanation lies in the physics of the surrounding landscape. During the monsoon and post-monsoon months, rural areas around the city are moist and vegetated, so a large fraction of incoming solar energy is consumed by evapotranspiration rather than heating the ground. The city, by contrast, remains dry and impervious year-round, so its surfaces warm efficiently and hold that warmth into the night. The result is a large urban-rural temperature differential precisely when residents might least expect it. Summer heat islands, while lower in intensity, still showed significant peaks in the urban core, underscoring the role of construction materials such as concrete and bitumen in retaining heat even during the hottest months of the year.

To understand what drives these temperature patterns at the level of individual pixels, the researchers computed a suite of environmental predictors from satellite data. These included the Enhanced Vegetation Index, a measure of green biomass; the Normalized Difference Built-up Index, which flags impervious construction; the Modified Normalized Difference Water Index, which captures surface moisture and open water; the Modified Bare Soil Index, which identifies exposed earth; and Aerosol Optical Depth, a proxy for atmospheric particulate loading. They added elevation, latitude, and longitude to account for terrain and geographic position. Correlation analysis between land surface temperature and these parameters revealed a coherent physical story. Vegetation and elevation were negatively correlated with temperature, meaning greener and higher ground runs cooler. Built-up index and aerosol loading were positively correlated, confirming that denser construction and hazier air accompany hotter surfaces.

The predictive heart of the study lies in its comparison of two machine learning algorithms trained to estimate land surface temperature from those environmental predictors. The team tested Random Forest, an ensemble method that averages the outputs of many decision trees, against Extreme Gradient Boosting, known as XGBoost, which builds trees sequentially so that each new one corrects the errors of its predecessors. XGBoost emerged as the clear winner, achieving a testing coefficient of determination of 0.8417, meaning it explained more than 84 percent of the variance in observed temperatures. Its error metrics were correspondingly tight, with a mean absolute error of 0.5796 degrees Celsius, a mean squared error of 0.4275 degrees Celsius squared, and a root mean squared error of 0.6538 degrees Celsius. Random Forest performed respectably but trailed on every metric, and the gap confirms that gradient boosting’s iterative error correction is particularly well suited to the nonlinear relationships linking land cover, moisture, aerosols, and surface temperature.

The seasonal breakdown of model performance adds further confidence. XGBoost achieved its highest coefficient of determination in winter, at 0.8805, and a strong 0.799 in summer, with error metrics remaining within acceptable ranges in both seasons. That robustness matters because a model that only works in one season would be of limited use for city planners trying to anticipate thermal stress throughout the year. Spatial validation reinforced the picture: predicted temperatures deviated minimally from observations, especially in dense urban areas where the Enhanced Vegetation Index remains relatively stable and the thermal signal is dominated by built surfaces. In rural zones, prediction errors were larger, a consequence of dynamic vegetation phenology and more varied terrain, where crop cycles and soil moisture swings introduce variability that static predictors struggle to capture.

What makes this study resonate far beyond Chennai is its methodological template. By fusing remote sensing, geospatial analysis, and machine learning into a single pipeline, the researchers demonstrated a repeatable way to diagnose how land cover transformation reshapes a city’s thermal climate. The approach requires no dense network of ground weather stations, which many rapidly urbanizing cities in the Global South lack. Instead, freely available satellite data from Landsat and MODIS, combined with open-source machine learning tools, can produce spatially explicit temperature maps and intensity estimates at annual and seasonal resolution. For the dozens of coastal megacities expected to absorb enormous population growth in the coming decades, that is a powerful and accessible diagnostic instrument.

The implications for planning are concrete. The study’s findings provide quantitative evidence for prioritizing vegetation conservation, blue-green infrastructure, and thermally sensitive land-use planning in rapidly urbanizing coastal cities. In practice, that means protecting remaining green corridors and wetlands before they are paved, integrating parks, lakes, and vegetated buffers into new development, and treating surface materials as a design variable rather than an afterthought. Because the analysis shows vegetation-related indicators contribute directly to cooling while built-up expansion intensifies the heat island, the model can be used prospectively: planners can simulate how a proposed land use scenario would alter surface temperatures before a single foundation is poured. The XGBoost model’s accuracy makes such scenario testing credible at the neighborhood scale.

Chennai’s two-decade record is, in effect, a controlled experiment in what happens when a humid coastal city converts its cooling infrastructure into heat-storing mass. The doubling of annual heat island intensity, the winter peaks above two degrees Celsius, and the near-tripling of built-up area together trace a clear causal chain from land use decision to thermal outcome. As climate change raises baseline temperatures across South Asia, the additional heat generated by urban form will compound the burden on residents, particularly those in dense, low-income neighborhoods with little tree cover. Studies of this kind turn that burden from an invisible background condition into a measurable, modelable, and therefore manageable quantity. The heat island, the research makes clear, is not an inevitable byproduct of urban growth. It is the predictable consequence of specific land cover choices, and it can be reversed the same way it was created, one surface at a time.

Subject of Research: Urban heat island dynamics, land use change, and machine learning-based land surface temperature prediction in Chennai, India

Article Title: Spatiotemporal Dynamics of Urban Heat Islands in Chennai: A Two-Decade Study on Land Use Changes and Predictive Modeling

Article References: Gadekar, K., & Mathew, A. (2026). Spatiotemporal Dynamics of Urban Heat Islands in Chennai: A Two-Decade Study on Land Use Changes and Predictive Modeling. Theoretical and Applied Climatology, 157(10), Article 611. https://doi.org/10.1007/s00704-026-06496-1

Image Credits: AI Generated

DOI: 10.1007/s00704-026-06496-1

Keywords: urban heat island, Chennai, land surface temperature, land use land cover change, XGBoost, Random Forest, MODIS, Landsat, remote sensing, machine learning, urbanization, blue-green infrastructure

The research, conducted by Nhat-Duc Hoang of Duy Tan University, focuses on 25 lakes scattered across the urban core of Da Nang, a coastal city of roughly 1.3 million people that has experienced dramatic growth in both population and built-up area over recent decades. Between 1996 and 2015, the city’s built-up footprint expanded by an average of 430.9 hectares per year, and with it came the familiar signature of the urban heat island: surface temperatures in dense districts that consistently exceed those of the surrounding countryside. During the dry season of 2025, multiple heatwaves struck the region, making the timing of the study particularly relevant for understanding how lakes perform under genuine thermal stress.

To measure cooling, the study turned to Landsat 8 satellite imagery, processing the thermal infrared band to retrieve land surface temperature, or LST, for every 30-meter pixel in the study area. Rather than comparing each pixel to an arbitrary local reference, the researchers established a single citywide thermal baseline: the mean surface temperature of all built-up and bare-land pixels, which came out at 40.16 degrees Celsius. Cooling intensity at any location was then defined as the difference between that baseline and the pixel’s own temperature. A positive value means a spot is cooler than typical urban surfaces; a negative value means it is hotter. This approach yields results that are directly meaningful for planners, expressed simply as degrees cooler than the prevailing urban background.

Around each of the 25 lakes, the team delineated a 500-meter buffer zone, a distance chosen because previous empirical studies suggest lake cooling rarely extends beyond that range. Within each buffer, 300 sampling points were randomly generated, producing a dataset of 7,500 locations. Each point was described by 16 conditioning factors spanning five categories: distance to the shoreline, lake morphometric properties such as area, perimeter, shape index, compactness, and elongation ratio, land use and land cover composition, urban morphology metrics including the density of built-up surfaces, bare land, shrubland, and tree canopy, and finally topography and proximity features such as elevation, slope, aspect, distance to rivers, and distance to roads.

The predictive engine at the heart of the study is CatBoost, a gradient boosting algorithm that builds an ensemble of decision trees sequentially, with each new tree trained to correct the residual errors of its predecessors. CatBoost was a deliberate choice for this kind of geospatial problem. Its ordered boosting scheme helps mitigate overfitting, it handles both numerical and categorical predictors in a unified framework, and it trains efficiently on large datasets, including with GPU acceleration. Hyperparameters, including tree depth, learning rate, number of boosting iterations, and L2 regularization, were tuned through five-fold cross-validation within the training data.

The model’s performance was strong. On the training set, it achieved a coefficient of determination of 0.96 with a root mean square error of 0.68 degrees Celsius. On the unseen testing set, which comprised 30 percent of the samples, the model still explained 88 percent of the variance in cooling intensity, with an RMSE of 1.27 degrees. An analysis of error types showed that 64.8 percent of predictions fell within one degree of the observed value, a threshold the author adopted as negligible error given that Landsat-derived LST itself carries intrinsic uncertainties on the order of one degree. In other words, the model’s accuracy approaches the physical limit imposed by the satellite data itself.

But prediction alone was not the goal. To understand why lakes cool the way they do, the study employed SHAP, or SHapley Additive exPlanations, a technique borrowed from cooperative game theory that assigns each feature a contribution value for every individual prediction. Positive SHAP values indicate a feature pushes cooling intensity upward; negative values pull it down. The SHAP analysis revealed that distance to river, the lake’s elongation ratio, built-up density, the Polsby-Popper compactness index, and lake area were the most influential predictors, followed by moderate contributions from shrubland density, shape index, perimeter, bare land density, and distance to shoreline.

Several of the model-inferred patterns carry immediate practical weight. The partial dependence analysis for distance to shoreline showed that the lake’s direct cooling contribution is concentrated within roughly 180 meters of the water’s edge, after which the marginal effect fades toward zero. This estimated effective cooling footprint sits comfortably within ranges reported elsewhere, such as the 100 to 150 meter influence documented for lakes in Dhaka, Bangladesh. Meanwhile, the density thresholds were striking: once bare land density around a lake exceeded roughly 0.3, cooling intensity dropped sharply, and when built-up density surpassed about 0.52, the lake’s cooling contribution turned negative. Conversely, shrubland began to boost cooling once its density exceeded about 0.2, and tree canopy enhanced cooling even at low densities, with the effect rising markedly beyond 0.3.

The study is careful to frame these thresholds as model-inferred patterns rather than strict physical laws. They emerge from a specific algorithm, a specific dry season, and a specific city, and the author notes that the relationships uncovered represent statistical associations rather than proven causal mechanisms. Other limitations are acknowledged as well: the 30-meter resolution of Landsat thermal data limits the detection of fine-scale variation, the LULC classification introduces its own errors, variables such as building height, sky view factor, and wind conditions were not included, and a sample of 25 lakes may not generalize to other climates or lake types. The random train-test split also means samples from the same lake appeared in both subsets, which may inflate apparent generalization to entirely independent lakes.

Even with those caveats, the implications for urban planning are concrete. The quantified 180-meter cooling footprint gives Da Nang’s planners a data-driven reference for prioritizing interventions and designing lake-adjacent spaces, with the littoral zone emerging as the critical design focus. The results argue for protecting and expanding vegetation around lakes, capping impervious development in the riparian zone, and treating lakes not as isolated amenities but as active components of blue-green infrastructure networks. In a city where heat stress poses serious public health risks, including elevated cardiovascular and respiratory disease burdens, knowing exactly where and how lakes cool the urban fabric transforms them from scenic backdrops into quantifiable, plannable instruments of climate adaptation.

Subject of Research: Geospatial machine learning modeling of the cooling intensity of urban lakes in Da Nang, Vietnam

Article Title: Geospatial modeling of urban lake cooling based on morphometric and urban contexts using tree ensembles and SHAP interpretability

Article References: Hoang, N.-D. (2026). Geospatial modeling of urban lake cooling based on morphometric and urban contexts using tree ensembles and SHAP interpretability. Discover Cities, 3(1), Article 193. https://doi.org/10.1007/s44327-026-00373-2

Image Credits: AI Generated

DOI: 10.1007/s44327-026-00373-2

Keywords: urban lakes, urban heat island, land surface temperature, CatBoost, SHAP, machine learning, remote sensing, Da Nang, cooling intensity, blue-green infrastructure, urban planning, geospatial analysis

The research, led by Dagim Hailu Hurisa and Abebe Tufa Angessa of Ambo University, relied on Landsat satellite images from 2004, 2014 and 2024, processed through a rigorous chain of remote sensing techniques. The team classified the land into six categories—agricultural land, bare land, built-up areas, vegetation, wetlands and water bodies—using a supervised maximum likelihood classification algorithm, and validated the results with hundreds of field-collected GPS points and high-resolution Google Earth imagery. The classified maps achieved overall accuracies above 92 percent in every year, with Kappa coefficients between 0.87 and 0.91, lending strong credibility to the land change story that emerged.

That story is striking. In 2004, Adama was still a largely agrarian landscape: agricultural land covered 38.65 percent of the study area and vegetation nearly 26 percent, while built-up surfaces occupied just under 12 percent. By 2014, agriculture had ballooned to almost 68 percent of the mapped area—a figure the authors caution may partly reflect classification uncertainties tied to the damaged Landsat 7 sensor of that era—before collapsing to about 24 percent by 2024. Meanwhile, built-up land exploded to become the dominant class, absorbing farmland, vegetation, barren ground and even the last fragments of wetland. The transition matrix shows agricultural land alone contributed the largest share of new urban surface, underscoring how peri-urban farmland has become the primary fuel of the city’s growth.

The ecological toll is equally visible. Nearly all of the wetlands mapped in 2004 had been converted to other uses by 2024, with farming and settlement expansion consuming these moisture-rich, flood-buffering landscapes. Vegetation experienced fragmentation and loss in many locations, although the study also detected gains in 2024, likely reflecting urban greening programs, roadside plantations and corridor development initiatives. Water bodies remained small but relatively stable. The net effect, the authors argue, is a city whose natural cooling and hydrological buffers have been steadily dismantled.

To translate these land changes into thermal terms, the researchers retrieved land surface temperature (LST) from the satellites’ thermal infrared bands, converting raw digital numbers into radiance, then brightness temperature, and finally applying emissivity corrections based on vegetation cover. The results reveal a subtle but consequential shift: maximum LST actually declined from 48.78 degrees Celsius in 2004 to 44.08 degrees in 2024, but minimum LST rose steadily from 22.91 to 24.83 degrees. This narrowing of the temperature range signals what the authors call thermal homogenization—the entire urban landscape warming from below as impervious surfaces store heat by day and release it slowly by night, weakening the contrast between hot cores and cool peripheries.

The spectral index analysis reinforces the same narrative from three independent angles. The Normalized Difference Vegetation Index (NDVI), which tracks vegetation health by comparing near-infrared and red reflectance, showed declining and fragmenting green cover, though with localized recovery in 2024. The Normalized Difference Built-up Index (NDBI), which highlights impervious surfaces through shortwave infrared reflectance, climbed steadily, with its maximum value rising to 0.47 by 2024 as development spread into the city’s western, northwestern and southeastern fringes. Most ominously, the Normalized Difference Water Index (NDWI) revealed a progressive drying of the landscape: peak positive values fell from 0.42 in 2004 to just 0.12 in 2024, and moisture-rich zones shrank into scattered fragments in the city’s south.

The statistical relationships between these indices and LST quantify the physics behind the warming. In 2004, NDVI explained about 33.5 percent of the spatial variation in surface temperature, with a regression slope indicating that each unit increase in vegetation greenness corresponded to roughly 23 degrees of cooling. By 2024, that explanatory power had weakened to under 18 percent and the slope had flattened to about 15 degrees—evidence, the authors suggest, that fragmented and shrinking vegetation patches are losing their capacity to regulate the city’s heat. Conversely, NDBI showed a consistent positive relationship with LST across all three years, explaining roughly 29 to 34 percent of temperature variation, confirming that concrete and asphalt are the city’s principal heat engines. NDWI’s cooling influence, mediated by evaporation and moisture retention, remained real but comparatively weak throughout.

These findings place Adama squarely within a broader pattern documented across Ethiopian cities such as Addis Ababa, Hawassa, Mekelle and Bahir Dar, and across the rapidly urbanizing Global South more generally, where urban areas are expanding at roughly 4 percent per year. What makes the Adama study notable is its integration: rather than examining land cover, temperature and spectral responses in isolation, it weaves them into a single causal picture in which land conversion drives surface change, which drives thermal change. The rising minimum temperatures, the authors emphasize, are a more telling indicator of urban heat island intensification than peak values, because they reflect stored heat in building materials and reduced nighttime cooling efficiency—conditions most dangerous for human health during heat waves.

The study is not without limitations, which the authors candidly acknowledge. The 30-meter resolution of Landsat imagery blurs fine-scale urban features and creates mixed pixels; the anomalous 2014 agricultural peak may partly stem from sensor artifacts; and no ground-based meteorological data were incorporated to complement the satellite-derived temperatures. Socioeconomic drivers of expansion, from population growth to land policy, were also outside the analytical frame. Yet the consistency of the three spectral indicators, each independently corroborating the others, strengthens confidence in the central conclusion: Adama’s growth is dismantling the ecological infrastructure that once kept it cool.

The prescription the authors offer is blue-green infrastructure—protected wetlands, expanded parks, roadside vegetation, water-sensitive design and controlled expansion of the urban footprint—woven into climate-responsive planning before the thermal trajectory becomes locked in. For a city of Adama’s size and speed, the satellite record delivers a warning that is hard to ignore: every hectare of farmland or wetland converted to impervious surface is a small bet against the city’s future livability, and after two decades, the ledger is beginning to show the interest coming due.

Subject of Research: Urbanization-driven land use and land cover change and its effects on land surface temperature and spectral indices in Adama City, Ethiopia

Article Title: Urbanization induced LULC transformation, its effects on land surface temperature and spectral index responses in Adama city, Ethiopia

Article References: Urbanization induced LULC transformation, its effects on land surface temperature and spectral index responses in Adama city, Ethiopia. (n.d.). https://doi.org/10.1007/s44327-026-00358-1

Image Credits: AI Generated

DOI: 10.1007/s44327-026-00358-1

Keywords: urbanization, land use land cover change, land surface temperature, remote sensing, Landsat, spectral indices, NDVI, NDBI, NDWI, urban heat island, Ethiopia, blue-green infrastructure