̽��ֱ�� of Cambridge - Ronita Bardhan

Turbocharging the race to protect nature and climate with AI

lw355 — Sun, 06 Apr 2025 17:00:51 +0000

Rebalancing the planet must happen faster. Cambridge researchers are using AI to help.

Wrong trees in the wrong place can make cities hotter at night, study reveals

ta385 — Tue, 10 Dec 2024 09:45:00 +0000

Temperatures in cities are rising across the globe and urban heat stress is already a major problem causing illness, death, a surge in energy use to cool buildings down, heat-related social inequality issues and problems with urban infrastructure.

Some cities have already started implementing mitigation strategies, with tree planting prominent among them. But a ̽��ֱ�� of Cambridge-led study now warns that planting the wrong species or the wrong combination of trees in suboptimal locations or arrangements can limit their benefits.

̽��ֱ��study, published today in Communications Earth & Environment found that urban trees can lower pedestrian-level air temperature by up to 12°C. Its authors found that the introduction of trees reduced peak monthly temperatures to below 26°C in 83% of the cities studied, meeting the ‘thermal comfort threshold’. However, they also found that this cooling ability varies significantly around the world and is influenced by tree species traits, urban layout and climate conditions.

“Our study busts the myth that trees are the ultimate panacea for overheating cities across the globe,” said Dr Ronita Bardhan, Associate Professor of Sustainable Built Environment at Cambridge's Dept. of Architecture.

“Trees have a crucial role to play in cooling cities down but we need to plant them much more strategically to maximise the benefits which they can provide.”

Previous research on the cooling effects of urban trees has focused on specific climates or regions, and considered case studies in a fragmented way, leaving major gaps in our knowledge about unique tree cooling mechanisms and how these interact with diverse urban features.

To overcome this, the authors of this study analysed the findings of 182 studies – concerning 17 climates in 110 global cities or regions – published between 2010 and 2023, offering the first comprehensive global assessment of urban tree cooling.

During the day, trees cool cities in three ways: by blocking solar radiation; through evaporation of water via pores in their leaves; and by foliage aerodynamically changing airflow. At night, however, tree canopies can trap longwave radiation from the ground surface, due to aerodynamic resistance and ‘stomatal closure’ – the closing of microscopic pores on the surface of leaves partly in response to heat and drought stress.

Variation by climate type

̽��ֱ��study found that urban trees generally cool cities more in hot and dry climates, and less in hot humid climates.

In the ‘tropical wet and dry or savanna’ climate, trees can cool cities by as much as 12 °C, as recorded in Nigeria. However, it was in this same climate that trees also warmed cities most at night, by up to 0.8°C.

Trees performed well in arid climates, cooling cities by just over 9°C and warming them at night by 0.4 °C.

In tropical rainforest climates, where humidity is higher, the daytime cooling effect dropped to approximately 2°C while the nighttime heating effect was 0.8 °C.

In temperate climates, trees can cool cities by up to 6°C and warm them by 1.5°C.

Using trees more strategically

̽��ֱ��study points out that cities which have more open urban layouts are more likely to feature a mix of evergreen and deciduous trees of varying sizes. This, the researchers found, tends to result in greater cooling in temperate, continental and tropical climates.

̽��ֱ��combined use of trees in these climates generally results in 0.5 °C more cooling than in cities where only deciduous or evergreen trees feature. This is because mixed trees can balance seasonal shading and sunlight, providing three-dimensional cooling at various heights.

In arid climates, however, the researchers found that evergreen species dominate and cool more effectively in the specific context of compact urban layouts such as Cairo in Egypt, or Dubai in UAE.

In general, trees cooled more effectively in open and low-rise cities in dry climates. In open urban layouts, cooling can be improved by about 0.4 °C because their larger green spaces allow for more and larger tree canopies and a greater mix of tree species.

“Our study provides context-specific greening guidelines for urban planners to more effectively harness tree cooling in the face of global warming,” Dr Ronita Bardhan said.

“Our results emphasize that urban planners not only need to give cities more green spaces, they need to plant the right mix of trees in optimal positions to maximize cooling benefits.”

“Urban planners should plan for future warmer climates by choosing resilient species which will continue to thrive and maintain cooling benefits,” said Dr Bardhan, a Fellow of Selwyn College, Cambridge.

Matching trees to urban forms

̽��ֱ��study goes further, arguing that species selection and placement needs to be compatible with urban forms. ̽��ֱ��orientation of the ‘street canyon’, local climate zones, aspect ratio, visible sky ratio and other urban features that influence the effects of trees all need to be carefully considered.

Although a higher degree of tree canopy cover in street canyons generally results in more cooling effects, excessively high cover may trap heat at the pedestrian level, especially in compact urban zones in high temperature climates. In such locations, narrow species and sparse planting strategies are recommended.

̽��ֱ��researchers emphasise that we cannot rely entirely on trees to cool cities, and that solutions such as solar shading and reflective materials will continue to play an important role.

̽��ֱ��researchers have developed an interactive database and map to enable users to estimate the cooling efficacy of strategies based on data from cities with similar climates and urban structures.

Reference

H Li et al., ‘Cooling efficacy of trees across cities is determined by background climate, urban morphology, and tree trait’, Communications Earth & Environment (2024). DOI: 10.1038/s43247-024-01908-4

While trees can cool some cities significantly during the day, new research shows that tree canopies can also trap heat and raise temperatures at night. ̽��ֱ��study aims to help urban planners choose the best combinations of trees and planting locations to combat urban heat stress.

Trees have a crucial role to play in cooling cities down but we need to plant them much more strategically to maximise the benefits which they can provide

Ronita Bardhan

hannahisabelnic via Flikr (Public domain)

Trees in an Indian city street. Photo: hannahisabelnic via Flikr (Public domain)

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Licence type:

Public Domain

Green jobs for graduates

plc32 — Wed, 21 Feb 2024 14:47:24 +0000

Green industry experts gave Cambridge students a tour of careers in the environment during a two-week Green Careers Festival, including how to land a green job.

A habitable planet for healthy humans

plc32 — Wed, 13 Dec 2023 17:28:42 +0000

Cambridge Zero symposium gathers researchers to examine the connections between planetary and public health.

AI trained to identify least green homes by Cambridge researchers

ta385 — Thu, 02 Nov 2023 08:00:00 +0000

‘Hard-to-decarbonize’ (HtD) houses are responsible for over a quarter of all direct housing emissions – a major obstacle to achieving net zero – but are rarely identified or targeted for improvement.

Now a new ‘deep learning’ model trained by researchers from Cambridge ̽��ֱ��’s Department of Architecture promises to make it far easier, faster and cheaper to identify these high priority problem properties and develop strategies to improve their green credentials.

Houses can be ‘hard to decarbonize’ for various reasons including their age, structure, location, social-economic barriers and availability of data. Policymakers have tended to focus mostly on generic buildings or specific hard-to-decarbonise technologies but the study, published in the journal Sustainable Cities and Society, could help to change this.

Maoran Sun, an urban researcher and data scientist, and his PhD supervisor Dr Ronita Bardhan (Selwyn College), who leads Cambridge’s Sustainable Design Group, show that their AI model can classify HtD houses with 90% precision and expect this to rise as they add more data, work which is already underway.

Dr Bardhan said: “This is the first time that AI has been trained to identify hard-to-decarbonize buildings using open source data to achieve this.

“Policymakers need to know how many houses they have to decarbonize, but they often lack the resources to perform detail audits on every house. Our model can direct them to high priority houses, saving them precious time and resources.”

̽��ֱ��model also helps authorities to understand the geographical distribution of HtD houses, enabling them to efficiently target and deploy interventions efficiently.

̽��ֱ��researchers trained their AI model using data for their home city of Cambridge, in the United Kingdom. They fed in data from Energy Performance Certificates (EPCs) as well as data from street view images, aerial view images, land surface temperature and building stock. In total, their model identified 700 HtD houses and 635 non-HtD houses. All of the data used was open source.

Maoran Sun said: “We trained our model using the limited EPC data which was available. Now the model can predict for the city’s other houses without the need for any EPC data.”

Bardhan added: “This data is available freely and our model can even be used in countries where datasets are very patchy. ̽��ֱ��framework enables users to feed in multi-source datasets for identification of HtD houses.”

Sun and Bardhan are now working on an even more advanced framework which will bring additional data layers relating to factors including energy use, poverty levels and thermal images of building facades. They expect this to increase the model’s accuracy but also to provide even more detailed information.

̽��ֱ��model is already capable of identifying specific parts of buildings, such as roofs and windows, which are losing most heat, and whether a building is old or modern. But the researchers are confident they can significantly increase detail and accuracy.

They are already training AI models based on other UK cities using thermal images of buildings, and are collaborating with a space products-based organisation to benefit from higher resolution thermal images from new satellites. Bardhan has been part of the NSIP – UK Space Agency program where she collaborated with the Department of Astronomy and Cambridge Zero on using high resolution thermal infrared space telescopes for globally monitoring the energy efficiency of buildings.

Sun said: “Our models will increasingly help residents and authorities to target retrofitting interventions to particular building features like walls, windows and other elements.”

Bardhan explains that, until now, decarbonization policy decisions have been based on evidence derived from limited datasets, but is optimistic about AI’s power to change this.

“We can now deal with far larger datasets. Moving forward with climate change, we need adaptation strategies based on evidence of the kind provided by our model. Even very simple street view photographs can offer a wealth of information without putting anyone at risk.”

̽��ֱ��researchers argue that by making data more visible and accessible to the public, it will become much easier to build consensus around efforts to achieve net zero.

“Empowering people with their own data makes it much easier for them to negotiate for support,” Bardhan said.

She added: “There is a lot of talk about the need for specialised skills to achieve decarbonisation but these are simple data sets and we can make this model very user friendly and accessible for the authorities and individual residents.”

Cambridge as a study site

Cambridge is an atypical city but informative site on which to base the initial model. Bardhan notes that Cambridge is relatively affluent meaning that there is a greater willingness and financial ability to decarbonise houses.

“Cambridge isn’t ‘hard to reach’ for decarbonisation in that sense,” Bardhan said. “But the city’s housing stock is quite old and building bylaws prevent retrofitting and the use of modern materials in some of the more historically important properties. So it faces interesting challenges.”

̽��ֱ��researchers will discuss their findings with Cambridge City Council. Bardhan previously worked with the Council to assess council houses for heat loss. They will also continue to work with colleagues at Cambridge Zero and the ̽��ֱ��’s Decarbonisation Network.

Reference

M Sun & R Bardhan, ‘Identifying Hard-to-Decarbonize houses from multi-source data in Cambridge, UK’, Sustainable Cities and Society (2023). DOI: 10.1016/j.scs.2023.105015

First of its kind AI-model can help policymakers efficiently identify and prioritize houses for retrofitting and other decarbonizing measures.

This is the first time that AI has been trained to identify hard-to-decarbonize buildings

Ronita Bardhan

Street view images of houses in Cambridge, UK, identifying building features. Red represents region contributing most to the 'Hard-to-decarbonize' identification. Blue represents low contribution.

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Licence type:

Attribution-Noncommerical

COP must reverse rising pessimism over building sector decarbonisation

ta385 — Thu, 17 Nov 2022 09:05:00 +0000

Negativity on Twitter about decarbonising the built environment has increased by around a third since 2014, according to a new analysis of more than 250,000 tweets featuring #emissions and #building between 2009 and 2021.

̽��ֱ��pessimistic trend has followed the launch of major climate action reports. ̽��ֱ��study, published in Nature Scientific Reports, reveals that expressions of ‘fear’ in Twitter dialogue increased by around 60% following the launch of the IPCC’s Fifth Assessment Report on Climate Change in 2015.

̽��ֱ��researchers, from Cambridge, Boston, Sussex and Aarhus Universities and Caltech, also found that ‘sadness’ increased by around 30% following the IPCC Special Report on Global Warming 1.5˚C in November 2019; while debate in November 2020 over lobbying of builders and utility companies over non-compliance with new building codes in the US triggered a spike in ‘anger’.

Mapping tweets that caused spikes in emotional engagement revealed that public concerns triangulated around inaction towards emission reduction, the fairness of carbon tax, the politicisation of building codes (distinctively seen for the US) and concerns over environmental degradation. This demonstrates, the researchers argue, “a strong environmental justice discourse.”

̽��ֱ��findings appear on the heels of COP27’s building sector events (10th – 14th November), which sought to promote a just transition and enhancing building resilience with the tagline ‘Build4Tomorrow’.

Lead author Ramit Debnath, Cambridge Zero Fellow at the ̽��ֱ�� of Cambridge and a visiting faculty associate in Computational Social Science at Caltech, said:

“Major climate policy events including COP have emphasised how difficult it is to decarbonise the built environment and this has been reflected in the rise of negative feelings on social media.

“But our research also offers hope – we found that climate policy events can and do foster public engagement, mostly positive, and that this has the power to increase the building sector’s focus on environmental justice.

“To build for tomorrow fairly, global climate action has to incorporate and empower diverse public voices. Policy actions are no longer isolated events in this digital age and demand two-way communication. Policy events and social media have a crucial role to play in this.”

̽��ֱ��study highlights that the building sector is one of the most important and challenging to decarbonise. ̽��ֱ��IPCC suggests that restricting climate change to 1.5˚C requires rapid and extensive changes around energy use, building design, and broader planning of cities and infrastructure. ̽��ֱ��buildings and construction sector currently accounts for around 39% of global energy and process-related carbon emissions. ̽��ֱ��International Energy Agency estimates that to achieve a net-zero carbon building stock by 2050, direct building carbon emissions must decrease by 50%, and indirect building sector emissions must also decrease 60% by 2030.

But decarbonising the building sector is challenging because it involves a complex overlap of people, places and practices that creates a barrier to designing just emission reduction policies. ̽��ֱ��study argues that democratising the decarbonisation process “remains a critical challenge across the local, national and regional scales”.

“Our findings shed light on potential pathways for a people-centric transition to a greener building sector in a net-zero future,” Debnath said.

Using advanced natural language processing and network theory, the researchers found a strong relationship between Twitter activity concerning the building sector and major policy events on climate change. They identify heightened Twitter engagement around developments including: the Paris Agreement’s call for the building sector to reduce its emissions through energy efficiency and address its whole life cycle; COP-23’s ’Human Settlement Day’ which focused on cities, affordable housing and climate action; COP25’s discourse on green/climate finance for residential homes; and COP26’s ’Cities, Region and Built environment Day’.

̽��ֱ��researchers found that despite negative sentiments gaining an increasing share since 2014, positive sentiments have continued to multiply as Twitter engagement has exploded. Across the entire study period (2009–21), positive sentiments have fairly consistently maintained a larger share of the conversation than negative sentiments.

̽��ֱ��study highlights the fact that core topics covered by tweets have changed significantly over time, as new innovations, technologies and issues have emerged. Hashtags associated with COP26, for instance, included #woodforgood and #masstimber, as well as #housingcrisis, #healthybuildings #scaleupnow, and #climatejusticenow, all largely or entirely absent in Twitter conversations between 2009 and 2016.

̽��ֱ��researchers found that discourse on innovative emissions reduction strategies which remain uncommon in the building sector— including use of alternate building materials like cross-laminated timber; implementing climate-sensitive building codes; and the circular economy – inspired Tweets expressing ‘anticipation’.

“COP26 was an extraordinary moment," Debnath said. " ̽��ֱ��Twitter engagement surrounding the event connected public health, the circular economy, affordable housing, and decarbonisation of the built environment like never before.”

“We are seeing a paradigm shift in the building emission discourse towards broader social and environmental justice contexts. Reference to low-carbon alternatives to concrete, housing crisis, scaling-up and climate justice are all part of the growing social justice movement associated with healthy and affordable social housing narratives globally.”

̽��ֱ��study notes that considering the size of Twitter’s current user base (around 211 million users globally), the number of tweets about emissions in the building sector, remains relatively small.

“It’s crucial that policymakers raise the salience of these issues and develop communications strategies to emphasise the importance of climate action in hard-to-decarbonise sectors like the building sector,” Debnath said.

̽��ֱ��authors of the study intend to continue to analyse social media interaction with further climate policy events, beginning with COP27.

Co-author Professor Benjamin Sovacool, Director of Institute for Global Sustainability at Boston ̽��ֱ�� said: “Some people dismiss Twitter as a poor focus of academic research, given its ability to spread misinformation and fake news. But we instead see it as a lens into the inner workings of how millions of people think, and rethink, about energy and climate change. It offers an incredible opportunity to reveal people’s true intentions, their revealed preferences, in unbiased form on a public forum.”

Co-author Prof R Michael Alvarez, Professor of Political and Computational Social Science at Caltech, said: “This is an innovative and important study, showing how an interdisciplinary and international group of scholars can use big data and machine learning to provide policy guidance on how to decarbonize the build sector. Research like this is critical at this time, to inform the debates at forums like COP27 and to energise additional scholarly work that can help further our goal of democratising climate action.”

Reference

R Debnath, R Bardhan, DU Shah, K Mohaddes, MH Ramage, MR Alvarez, and B Sovacool, ‘Social media enables people-centric climate action in the hard-to-decarbonise building sector’. Nature Scientific Reports (2022). DOI: 10.1038/s41589-022-23624-9

Social media engagement with climate policy events is vital to reducing building emissions and ensuring environmental justice, research led by Cambridge suggests

To build for tomorrow fairly, global climate action has to incorporate and empower diverse public voices

Ramit Debnath

Brian (Ziggy) Liloi. CC licence via Flickr

People installing a living roof in 2012

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Licence type:

Attribution-Noncommerical

Extent of India’s COVID nudge campaign revealed

ta385 — Thu, 17 Sep 2020 07:21:22 +0000

India has reported nearly five million COVID-19 cases and well over 80,000 deaths (as of 17 September 2020), making the country one of the worst hit in the world. But an even greater tragedy may have unfolded had India’s government not used nudge theory to maintain one of the world’s strictest and longest lockdowns in the first quarter of the year. This is the view of a new study by Ramit Debnath and Dr Ronita Bardhan from Cambridge’s Behaviour and Building Performance Group, Department of Architecture.

Using machine learning and AI-based algorithms to analyse almost 400 government press releases, they show how India nudged across 14 key policy areas to influence the behaviour of 1.3 billion people, including government employees, scientists, health professionals, manufacturers, food suppliers and students to help fight COVID-19. ̽��ֱ��researchers argue that nudges from India’s Prime Minister, Narendra Modi, were particularly important in creating herd effect on lockdown and social distancing norms across the nation.

̽��ֱ��study, published in PLoS ONE, found that the government deployed nudge techniques to tackle a wide range of urgent challenges between 15 January and 14 April 2020. Nudging is a design-based public policy approach which uses positive and negative reinforcements to modify the behaviour of a population.

In January and February, policy nudges were focused on evaluating the risk of incoming travellers from China and extending surveillance at international airports. But the narrative soon shifted to address other pressing concerns. By March, nudges sought to impose new restrictions on travel, discouraging people from visiting crowded and public spaces, and strict social distancing. On 24 March, Modi told the nation that “21 days is critical to breaking the infection cycle… or else the country and your family could be set back 21 years”. ̽��ֱ��next day, the country entered phase 1 of lockdown.

̽��ֱ��government nudged to tackle fake news about the virus and to convince the population to strictly adhere to the rules, use masks and wash hand frequently. At the same time, it conducted surveillance in urban areas using smart technologies that included drones, spatial analysis, low-power Bluetooth mobile phone applications and humanoid robots.

Ramit Debnath said: “Nudge-based policy approaches are crucial in a democratic country like India which has a vast population and geo-spatial divide, high levels of illiteracy and an extremely vulnerable health system.”

Ronita Bardhan added: “ ̽��ֱ��government urgently needed to buy time and it had to bring a diverse population together to fight a common struggle – this was a huge challenge. Our findings show that the government needed much more than scientific data to convince people, they appealed to powerful values including patriotism, family, religion and community.”

̽��ֱ��study highlights the role played by the ‘Prime Minister’s Citizen Assistance and Relief in Emergency Situations Fund’ (PM CARES Fund) which was created to nudge the public to make micro-donations and encourage public participation to help tackle the crisis. On 5 April, the Prime Minister nudged people to voluntarily switch off their lights for ten minutes in solidarity with frontline workers. Most of these nudges were made with social media advertisements, SMS forwards and broadcast media.

̽��ֱ��study found that government ministries nudged India’s manufacturing firms to produce PPE, hand sanitiser and masks to meet the national demand, while also seeking to protect the country’s food security and supply chains at a critical time – India’s farmers harvest their winter crops from February to April.

Meanwhile, the government spurred on India’s scientific community to fight the pandemic, releasing funding through the Department of Science and Technology. Research institutions were encouraged to submit proposals to focus on the development of affordable diagnostics, vaccines, antivirals, disease models, and other R&D to study COVID-19.

Scientific innovation during this period included robots for encouraging social distancing in public spaces and healthcare centres; and a contact tracing app (AarogyaSetu) using GPS and Bluetooth. Frequent SMS reminders were used to nudge people to use the app. ̽��ֱ��Ministry of Human Resource Development also nudged the start-up and innovation community in India to participate in the fight for COVID-19 by launching programs like ‘Fight Corona IDEAthon’.

To support education, the government encouraged home-schooling by aggressively advertising the use of the National Digital Library of India. ̽��ֱ��government even harnessed nostalgia to help keep people at home during lockdown by broadcasting popular ‘80s and ‘90s TV shows on the national channel, Doordarshan.

̽��ֱ��study demonstrates how nudge strategies evolved as the crisis unfolded. Between January and the first week of March, for instance, one government ministry (AYUSH) was aggressively nudging people to follow the traditional medicinal practice of Ayurveda and to maintain good health through yoga to increase immunity, while also insisting on disciplined personal hygiene. However, in mid-March, as infection rates increased, the nudges shifted away from traditional treatments to promoting a healthy lifestyle using hashtags like #YOGAathome.

̽��ֱ��researchers used topic modelling, a computational social science method that has its basis in text mining and natural language processing. It automatically analyses text data to determine cluster words for a set of documents.

̽��ֱ��Government started lifting lockdown restrictions on 7 June 2020, and the spread of the virus has since accelerated. But the benefits of the government’s nudge campaign are still being felt, the researchers believe. Ronita Bardhan says: “Behaviour changes encouraged by nudges earlier in the year, including the wearing of masks and social distancing, are still widely maintained across India. These nudges are still helping to save lives.”

̽��ֱ��study does not attempt to assess the success or failure of the Government of India’s policy interventions, rather to understand how context-specific latent nudges were created through policy interventions.

Ramit Debnath is a Gates Cambridge Scholar at Churchill College; Dr Ronita Bardhan is ̽��ֱ�� Lecturer of Sustainability in the Built Environment and a Fellow at Selwyn College.

Reference

R. Debnath R & R. Bardhan, ‘India nudges to contain COVID-19 pandemic: A reactive public policy analysis using machine-learning based topic modelling’, PLoS ONE (2020). DOI: 10.1371/journal.pone.0238972.

̽��ֱ��Government of India’s use of nudge theory in the first three months of the pandemic helped to tackle the virus on numerous fronts, a new study suggests.

̽��ֱ��government urgently needed to buy time and ... bring a diverse population together to fight a common struggle

Ronita Bardhan

Gerd Altmann from Pixabay

India flag face mask.

Yes

Fixing India’s slum rehabilitation housing

ta385 — Thu, 13 Feb 2020 08:00:00 +0000

Millions of new houses being built for former slum-dwellers are failing their residents and fuelling unnecessary energy use. New research aims to improve their design before it’s too late.