The project aims at enhancing the resilience of low-income communities living in disaster prone areas. The focus is on low-lying coastal zones that have a high risks of droughts and floods in selected parts of East Africa, Brazil and North America. It develops the geographic and socio-economic knowledge of persons living in slum and riverbed areas by gathering georeferenced data on infrastructures and information on the natural heritage of project sites. The project team will also investigate technology adoption barriers and diffusion drivers through designing and prototyping an affordable, disaster-resilient, low-income housing system that use sustainable locally-resourced materials. The development of urban spaces is a function of geographic location, economic history, urban development pattern, and therefore governance will have a bearing on resilience. Still, given that development (or lack thereof) of an urban center is an outcome of existing social, economic, and political inequities political inequities; policy packages for disaster preparedness that do not consider the unique circumstances of vulnerable populations can inadvertently cause harm to low- income households. Furthermore, policy packages will include environmental sustainability and public health considerations. The research will also contribute to accurate modelling of climate and extreme weather events at spatiotemporal level to increase the understanding of climate scientists while empowering policy makers in disaster related decision-making. Machine Learning and Big Data Analytics will be used for climate modelling and to identify optimal disaster resilient-housing urban design and planning policy packages considering projected climate change- related extreme weather scenarios between the current time and 2050. Whilst Big Climate Data is amenable to long-term climate prediction, data for localized and seasonal predictions is still uncertain and sparse. Machine Learning has potential to handle this uncertainty and data sparsity as other applications have demonstrated that it can work with either big data or sparse data.

The GCRF African Science for Weather Information and Forecasting Techniques (GCRF African-SWIFT) programme aims to develop a sustainable research capability in tropical weather forecasting which will enhance the livelihood of African populations and improve the economies of their countries. Improved forecasts will address key aspects of the UK Aid strategy. The results will be translatable beyond the partner countries to other nations of Africa and the developing world more widely. In order to improve African weather prediction, fundamental scientific research is needed, in the physics of tropical weather systems, evaluation and presentation of complex model and satellite data, and communication and exploitation of forecasts. The programme will develop research capability to yield ongoing forecasting improvements in the coming decades. The overall aims of the project are to: I. Make research advances needed for significant improvements in weather forecasts in Africa, and the tropics more generally, from the hourly to the seasonal timescale. II. Build capability among UK and African partners to improve, maintain and evaluate operational tropical forecasts in future. III. Assist African partners in developing capacity for sustained training of forecasters, in partnership with African academic institutions and international agencies. Our strategy to increase research capability with societal impact is to build upon existing partnerships between forecasting centres and universities within four partner countries (Senegal, Ghana, Nigeria and Kenya) and within the UK. In-country partnerships combine the strengths of academic and operational perspectives and provide sustainability. The project is embedded within the long-term structures and strategies for international coordination for the region. Specifically, our programme addresses the aims of the World Meteorological Organisation (WMO; project partner). The potential applications and benefits are: A. New research capability in observing, modelling and evaluating forecasts of tropical high-impact weather; B. Robust networks of African scientists with capability to advance the science in this field, and pull the science through into operational impact; C. Significant improvements in weather forecasts, as evaluated using tested methods; D. New forecasting tools used operationally for short-term (0-120h) and S2S prediction; E. Significant impact on the regional strategy for provision of user-focussed, quality-controlled weather forecasts, as overseen by the WMO; F. More effective use of weather forecasts to the benefit of African people and nations.

East Africa (EA) has one of the world's fastest growing populations, with maxima around water-bodies and rapid urbanisation. Climate change is adding to existing problems increasing vulnerability of the poorest. HyCRISTAL is driven by EA priorities. EA communities rely on rainfall for food via agriculture. EA's inland lakes are rain-fed and provide water, power and fisheries. For EA's growing cities, climate impacts on water resources will affect water supply & treatment. HyCRISTAL will therefore operate in both urban & rural contexts. Change in water availability will be critical for climate-change impacts in EA, but projections are highly uncertain for rain, lakes, rivers and groundwater, and for extremes. EA "Long-Rains" are observed to be decreasing; while models tend to predict an increase (the "EA Climate paradox") although predictions are not consistent. This uncertainty provides a fundamental limit on the utility of climate information to inform policy. HyCRISTAL will therefore make best use of current projections to quantify uncertainty in user-relevant quantities and provide ground-breaking research to understand and reduce the uncertainty that currently limits decision making. HyCRISTAL will work with users to deliver world-leading climate research quantifying uncertainty from natural variability, uncertainty from climate forcings including those previously unassessed, and uncertainty in response to these forcings; including uncertainties from key processes such as convection and land-atmopshere coupling that are misrepresented in global models. Research will deliver new understanding of the mechanisms that drive the uncertainty in projections. HyCRISTAL will use this information to understand trends, when climate-change signals will emerge and provide a process-based expert judgement on projections. Working with policy makers, inter-disciplinary research (hydrology, economics, engineering, social science, ecology and decision-making) will quantify risks for rural & urban livelihoods, quantify climate impacts and provide the necessary tools to use climate information for decision making. HyCRISTAL will work with partners to co-produce research for decision-making on a 5-40 year timescale, demonstrated in 2 main pilots for urban water and policies to enable adaptive climate-smart rural livelihoods. These cover two of three "areas of need" from the African Ministerial Council on Environment's Comprehensive Framework of African Climate Change Programmes. HyCRISTAL has already engaged 12 partners from across EA. HyCRISTAL's Advisory Board will provide a mechanism for further growing stakeholder engagement. HyCRISTAL will work with the FCFA global & regional projects and CCKE, sharing methods, tools, user needs, expertise & communication. Uniquely, HyCRISTAL will capitalise on the new LVB-HyNEWS, an African-led consortium, governed by the East African Community, the Lake Victoria Basin Commission and National Meteorological and Hydrological agencies, with the African Ministerial Conference on Meteorology as an observer. HyCRISTAL will build EA capacity directly via collaboration (11 of 25 HyCRISTAL Co-Is are African, with 9 full-time in Africa), including data collection and via targeted workshops and teaching. HyCRISTAL will deliver evidence of impact, with new and deep climate science insights that will far outlast its duration. It will support decisions for climate-resilient infrastructure and livelihoods through application of new understanding in its pilots, with common methodological and infrastructure lessons to promote policy and enable transformational change for impact-at-scale. Using a combination of user-led and science-based management tools, HyCRISTAL will ensure the latest physical science, engineering and social-science yield maximum impacts. HyCRISTAL will deliver outstanding outputs across FCFA's aims; synergies with LVB-HyNEWS will add to these and ensure longevity beyond HyCRISTAL.