Over the last few months there has been extreme drought in Amazonia. This may be related to warming of the North Atlantic and Gulf of Mexico, the same feature that helped generate unusually violent hurricanes and contributed to 2005 breaking the record as the most active year for Atlantic tropical cyclones since records began. The Amazon drought may have been a similarly unusual event. In western Amazonia particularly this may have been the most intense drought since weather records began in this region in the mid 20th-century. By October, river stage levels along the middle and lower reaches of the Amazon river had reached the lowest marks for 35 to 60 years, which indicates that most of the vast Amazon basin (about 5 million km2) has seen exceptionally dry conditions for many months. The drought led to a state of emergency in parts of Brazil, where boats could no longer be used to supply towns and villages with essential supplies. Reports from Amazonian towns such as Iquitos (Peru), Leticia (Colombia), and Manaus (Brazil) suggest that temperatures approached, and perhaps exceeded, their all-time temperature records. The drought appears to be ending now. This project will attempt to assess the impacts of this unusual event on the Amazon forest / which harbours more carbon and more species than any other ecosystem on earth. Water is essential for plant growth, so the growth rates of trees may have been severely reduced, and also the rates of tree death may have increased. Changes in rates of tree growth and death impact on the amount of carbon stored. However, at the moment, the severity of these effects is not known. However strong these effects may (or may not) have been, the drought does represent a scientific opportunity that must be seized, because it may provide a window into the future. Human-driven climate change is expected to increase temperatures substantially in this region (by 2 to 5 Celsius within the century), and probably to diminish rainfall. Studying the effects of this drought in detail on the structure of forest canopies, the structure of leaves and branches, and how different species and types of tree respond, can provide the information to make predictions of how Amazonian forests might look in future. This research team is in a unique position to study the effects of this drought. A network of long term monitoring plots has been established over the last five years, building on plots established as long ago as 1970. With our South American colleagues these plots are regularly monitored, and many were remeasured during the last 12 months. In a few, select sites, we have also been looking frequently (as often as every fortnight) at short-term ecological processes such as leaf litter-fall, and measuring the weather that the plots are experiencing. In the proposed research we set out a strategy for measuring the effect that this remarkable drought has had. Not only will we return as soon as possible to make the long-term measurements such as tree growth, death, in as many plots as possible, but we will also make the high-intensity, short-term measurements (such as litterfall) for an additional year following the drought so that we can understand in more detail how Amazon forests recover from the drought. Together with this intensive fieldwork and subsequent laboratory analyses we will also synthesize existing weather data from across the Amazon to understand the precise magnitude, intensity, and distribution of the drought, and also satellite-based measurements of forest canopy properties to understand how the extreme conditions have affected the larger region, and to put our localised fieldwork results in context of the whole region. The overall outcome of the project will be to discover just how serious this event has been for plants in the region, and therefore to allow us to make much better predictions of what might happen in the future.

Over the last few months there has been extreme drought in Amazonia. This may be related to warming of the North Atlantic and Gulf of Mexico, the same feature that helped generate unusually violent hurricanes and contributed to 2005 breaking the record as the most active year for Atlantic tropical cyclones since records began. The Amazon drought may have been a similarly unusual event. In western Amazonia particularly this may have been the most intense drought since weather records began in this region in the mid 20th-century. By October, river stage levels along the middle and lower reaches of the Amazon river had reached the lowest marks for 35 to 60 years, which indicates that most of the vast Amazon basin (about 5 million km2) has seen exceptionally dry conditions for many months. The drought led to a state of emergency in parts of Brazil, where boats could no longer be used to supply towns and villages with essential supplies. Reports from Amazonian towns such as Iquitos (Peru), Leticia (Colombia), and Manaus (Brazil) suggest that temperatures approached, and perhaps exceeded, their all-time temperature records. The drought appears to be ending now. This project will attempt to assess the impacts of this unusual event on the Amazon forest / which harbours more carbon and more species than any other ecosystem on earth. Water is essential for plant growth, so the growth rates of trees may have been severely reduced, and also the rates of tree death may have increased. Changes in rates of tree growth and death impact on the amount of carbon stored. However, at the moment, the severity of these effects is not known. However strong these effects may (or may not) have been, the drought does represent a scientific opportunity that must be seized, because it may provide a window into the future. Human-driven climate change is expected to increase temperatures substantially in this region (by 2 to 5 Celsius within the century), and probably to diminish rainfall. Studying the effects of this drought in detail on the structure of forest canopies, the structure of leaves and branches, and how different species and types of tree respond, can provide the information to make predictions of how Amazonian forests might look in future. This research team is in a unique position to study the effects of this drought. A network of long term monitoring plots has been established over the last five years, building on plots established as long ago as 1970. With our South American colleagues these plots are regularly monitored, and many were remeasured during the last 12 months. In a few, select sites, we have also been looking frequently (as often as every fortnight) at short-term ecological processes such as leaf litter-fall, and measuring the weather that the plots are experiencing. In the proposed research we set out a strategy for measuring the effect that this remarkable drought has had. Not only will we return as soon as possible to make the long-term measurements such as tree growth, death, in as many plots as possible, but we will also make the high-intensity, short-term measurements (such as litterfall) for an additional year following the drought so that we can understand in more detail how Amazon forests recover from the drought. Together with this intensive fieldwork and subsequent laboratory analyses we will also synthesize existing weather data from across the Amazon to understand the precise magnitude, intensity, and distribution of the drought, and also satellite-based measurements of forest canopy properties to understand how the extreme conditions have affected the larger region, and to put our localised fieldwork results in context of the whole region. The overall outcome of the project will be to discover just how serious this event has been for plants in the region, and therefore to allow us to make much better predictions of what might happen in the future.

We propose to set up the basis for an AI-based digital tool for adaptation/mitigation to the impacts of climate change and pollution on respiratory health in an urban setting. This will enable users to explore interactions between exposure to pollutants, changing weather patterns and their effect on respiratory health, accounting for the complex interactions between environment and health. The project has two coupled aspects: 1. AI model to create a digital twin to establish this interaction using asthmatic and healthy subjects as group test case. This will incorporate big data from health cohorts as well as other studies linking exposure to respiratory outcomes and cell response to pollution, as well as air quality and weather data. 2. Building on this exposure-response model, develop AI-based personalised models using deep learning techniques to include individual circumstances (e.g., age, sex, lifestyle, medical history), combined with air pollution exposure to give a prediction of individual respiratory health. Up to 90% of the world's population breathe air with high levels of both indoor and outdoor pollution which takes ~7 million lives each year worldwide. In the UK, it is rated as one of the most serious threats to public health with only cancer, obesity and heart disease eclipsing it. The health risks associated with fine and ultrafine particulate matter (PM2.5 and PM0.1) include development and exacerbating respiratory diseases such as chronic obstructive lung diseases including asthma, respiratory infections and lung cancer. While measures are being taken to curb pollution levels, it is essential for individuals to reduce their personal exposure and abate the ill-health effects of pollution. One way of doing this would be to predict who are those individuals who would be at most risk of developing health ill-effects in the long-term. There is virtually no information of this kind of risk assessment at an individualised level and the most available information at the moment is that those at risk are children, the elderly and those already suffering from chronic lung and cardiovascular disease. The integrated AI modelling will also represent various intervention scenarios (e.g. avoiding certain more polluted travel routes for at-risk people such as asthmatics) to assess reduced exposure and corresponding changes in health outcomes. These biologic parameters of exposure will be integrated with the respiratory responses to pollution in individuals using a combination of cardio-respiratory, physical activity and personal fine particles exposure data from satellite to personal monitors e.g. smart watches. We will also integrate cellular, biochemical and biomarker personal data with the other parameters. We will numerically model the pollution and air flows at the neighbourhood scale and apply an approach centred on the impact of pollution on health to all aspects of modelling, sensor placement and management of the environment as well as the individuals. Thus, any mitigation strategies can be designed to minimize the impact of pollution on health. We develop two unique AI capabilities (1) a new AI method for solving differential equations that we call AI4HFM that can determine the dispersion of pollution through the air and (2) a unique generative method to predict health impacts from pollution levels as well as a level of uncertainty associated with this. This will be combined with reinforcement learning to tailor the AI model for an individual based on information obtained from that individual. Thus the approach may be used to guide healthy activity, prevention, diagnosis and management of respiratory diseases. It will also empower individuals so they can make informed decisions that will influence their health.

Tropical forests are globally critical centres of biodiversity and carbon storage. These forests face serious threat from deforestation - nearly 97% of permanent forest loss in the past decade has occurred in the tropics (FAO, 2020). Innovative solutions to reduce tropical deforestation are urgently required. International climate treaties recognise forests as an essential resource for mitigating global climate change through carbon capture and storage, but their role in helping humans adapt to rising global temperatures has not yet been assessed. Quantifying the potential contribution of intact and recovering tropical forests to climate change adaptation would shift the paradigm of forest conservation incentives away from promoting global-level mitigation benefits towards demonstrating the value of forests at local and national scales, thereby influencing the actions of those with power over the fate of tropical forests. Strengthening linkages between mitigation and adaptation would also offer new national incentives to achieve global climate targets. Replacing tropical forests with alternative land types disrupts regular water and energy exchanges between the land and the atmosphere, causing higher surface temperatures and changes to the water cycle. These changes exacerbate climate change-driven warming and droughts with severe consequences for human health and crop productivity. The presence of forest could alleviate the damaging effects of global climate change by cooling surrounding non-forest landscapes, reducing the frequency of heatwaves and sustaining inland water supplies. However, the potential for tropical forests to offer such ecosystem-based adaptation, and the dependence of climate services on forest type and degradation status, have not been evaluated. This evaluation is limited by the capability of climate models to capture the complexities of forest-climate interactions, and therefore their ability to reliably predict how tropical deforestation or afforestation may modify future temperature increases. I will lead a team of researchers to deliver the first in-depth assessment of the local and regional climate benefits provided by intact and regenerating tropical forests. My analysis will combine, for the first time, the latest satellite and ground-based measurements, air-mass trajectory modelling and state-of-the-art numerical models to accurately quantify how tropical forests interact with climate at varying spatial scales. Advances in understanding will inform the development of the UK Earth System Model to derive improved predictions of how alternative tropical land-use pathways will influence future climate at regional and global scales. My trans-disciplinary and far-reaching Fellowship will extend beyond detailed physical climate science to consider how ecosystem-based adaptation to climate change has co-benefits for human health, agricultural resilience, sustainable resource management and environmental justice. Results will lead to a step-change in how forests are valued, focus motivations for their preservation on local and national benefits and identify synergies between mitigation and adaptation policies. The proposed research agenda builds on my growing expertise in tropical forests, land-atmosphere interactions, and climate change, to transform routes to forest conservation and adaptation.

This project will propose an urban grammar to describe urban form and will develop artificial intelligence (AI) techniques to learn such a grammar from satellite imagery. Urban form has critical implications for economic productivity, social (in)equality, and the sustainability of both local finances and the environment. Yet, current approaches to measuring the morphology of cities are fragmented and coarse, impeding their appropriate use in decision making and planning. This project will aim to: 1) conceptualise an urban grammar to describe urban form as a combination of "spatial signatures", computable classes describing a unique spatial pattern of urban development (e.g. "fragmented low density", "compact organic", "regular dense"); 2) develop a data-driven typology of spatial signatures as building blocks; 3) create AI techniques that can learn signatures from satellite imagery; and 4) build a computable urban grammar of the UK from high-resolution trajectories of spatial signatures that helps us understand its future evolution. This project proposes to make the conceptual urban grammar computable by leveraging satellite data sources and state-of-the-art machine learning and AI techniques. Satellite technology is undergoing a revolution that is making more and better data available to study societal challenges. However, the potential of satellite data can only be unlocked through the application of refined machine learning and AI algorithms. In this context, we will combine geodemographics, deep learning, transfer learning, sequence analysis, and recurrent neural networks. These approaches expand and complement traditional techniques used in the social sciences by allowing to extract insight from highly unstructured data such as images. In doing so, the methodological aspect of the project will develop methods that will set the foundations of other applications in the social sciences. The framework of the project unfolds in four main stages, or work packages (WPs): 1) Data acquisition - two large sets of data will be brought together and spatially aligned in a consistent database: attributes of urban form, and satellite imagery. 2) Development of a typology of spatial signatures - Using the urban form attributes, geodemographics will be used to build a typology of spatial signatures for the UK at high spatial resolution. 3) Satellite imagery + AI - The typology will be used to train deep learning and transfer learning algorithms to identify spatial signatures automatically and in a scalable way from medium resolution satellite imagery, which will allow us to back cast this approach to imagery from the last three decades. 4) Trajectory analysis - Using sequences of spatial signatures generated in the previous package, we will use machine learning to identify an urban grammar by studying the evolution of urban form in the UK over the last three decades. Academic outputs include journal articles, open source software, and open data products in an effort to reach as wide of an academic audience as possible, and to diversify the delivery channel so that outputs provide value in a range of contexts. The impact strategy is structured around two main areas: establishing constant communication with stakeholders through bi-directional dissemination; and data insights broadcast, which will ensure the data and evidence generated reach their intended users.