United Nations Institute for Training and Research

Rapid response to natural hazards, such as floods, is essential to mitigate loss of life and the reduction of suffering. For emergency response teams, access to timely and accurate data is essential. Satellite imagery offers a rich source of information which can be analysed to help determine regions affected by a disaster. Much remote sensing flood analysis is semi-automated, with time consuming manual components requiring hours to complete. In this study, we present a fully automated approach to the rapid flood mapping currently carried out by many non-governmental, national and international organisations. We design a Convolutional Neural Network (CNN) based method which isolates the flooded pixels in freely available Copernicus Sentinel-1 Synthetic Aperture Radar (SAR) imagery, requiring no optical bands and minimal pre-processing. We test a variety of CNN architectures and train our models on flood masks generated using a combination of classical semi-automated techniques and extensive manual cleaning and visual inspection. Our methodology reduces the time required to develop a flood map by 80%, while achieving strong performance over a wide range of locations and environmental conditions. Given the open-source data and the minimal image cleaning required, this methodology can also be integrated into end-to-end pipelines for more timely and continuous flood monitoring.

Importance: Financial toxicity (FT) is the negative impact of cost of care on financial well-being. Patients with breast cancer are at risk for incurring high out-of-pocket costs given the long-term need for multidisciplinary care and expensive treatments. Objective: To quantify the FT rate of patients with breast cancer and identify particularly vulnerable patient populations nationally and internationally. Data Sources: A systematic review and meta-analysis were conducted. Four databases-Embase, PubMed, Global Index Medicus, and Global Health (EBSCO)-were queried from inception to February 2021. Data analysis was performed from March to December 2022. Study Selection: A comprehensive database search was performed for full-text, English-language articles reporting FT among patients with breast cancer. Two independent reviewers conducted study screening and selection; 462 articles underwent full-text review. Data Extraction and Synthesis: A standardized data extraction tool was developed and validated by 2 independent authors; study quality was also assessed. Variables assessed included race, income, insurance status, education status, employment, urban or rural status, and cancer stage and treatment. Pooled estimates of FT rates and their 95% CIs were obtained using the random-effects model. Main Outcomes and Measures: FT was the primary outcome and was evaluated using quantitative FT measures, including rate of patients experiencing FT, and qualitative FT measures, including patient-reported outcome measures or patient-reported severity and interviews. The rates of patients in high-income, middle-income, and low-income countries who incurred FT according to out-of-pocket cost, income, or patient-reported impact of expenditures during breast cancer diagnosis and treatment were reported as a meta-analysis. Results: Of the 11 086 articles retrieved, 34 were included in the study. Most studies were from high-income countries (24 studies), and the rest were from low- and middle-income countries (10 studies). The sample size of included studies ranged from 5 to 2445 people. There was significant heterogeneity in the definition of FT. FT rate was pooled from 18 articles. The pooled FT rate was 35.3% (95% CI, 27.3%-44.4%) in high-income countries and 78.8% (95% CI, 60.4%-90.0%) in low- and middle-income countries. Conclusions and Relevance: Substantial FT is associated with breast cancer treatment worldwide. Although the FT rate was higher in low- and middle-income countries, more than 30% of patients in high-income countries also incurred FT. Policies designed to offset the burden of direct medical and nonmedical costs are required to improve the financial health of vulnerable patients with breast cancer.

OBJECTIVE: China has about 350 million smokers, more commonly men. Using data from National Health Service Surveys conducted in 1993, 1998 and 2003, we (i) estimated trends in smoking prevalence and cessation according to sociodemographic variables and (ii) analysed cessation rates, quitting intentions, reasons for quitting and reasons for relapsing. METHODS: Data were collected from approximately 57 000 households and 200 000 individuals in each survey year. Household members > 15 years of age were interviewed about their smoking habits, quitting intentions and attitudes towards smoking. We present descriptive data stratified by age, sex, income level and rural versus urban residence. FINDINGS: In China, current smoking in those > 15 years old declined 60-49% in men and 5-3.2% in women over 1993-2003. The decline was more marked in urban areas. However, heavy smoking (≥ 20 cigarettes daily) increased substantially overall and doubled in men. The average age of uptake also dropped by about 3 years. In 2003, 7.9% of smokers reported intending to quit, and 6% of people who had ever smoked reported having quit. Of former smokers, 40.6% quit because of illness, 26.9% to prevent disease and 10.9% for financial reasons. CONCLUSION: Smoking prevalence declined in China over the study period, perhaps due to the combined effect of smoking cessation, reduced uptake in women and selective mortality among men over 40 years of age. However, heavy smoking increased. People in China rarely quit or intend to quit smoking, except at older ages. Further tobacco control efforts are urgently needed, especially in rural areas.

The African Union was established in July 2002 by African leaders, evolving from the Organization of African Unity (OAU). However the idea of the African Union can be traced to the Pan-Africanist movement. Timothy Murithi looks at the emergence of Pan-Africanism and how it was institutionalized through the Pan-African Congress and the OAU. He argues that the African Union represents the third phase of the institutionalization of Pan-Africanism. The book examines the limitations of the OAU and discusses whether the African Union can adopt a more interventionist stance in dealing with peacebuilding and development in Africa. The volume assesses the African Union's peace and security institutions and analyzes how it is beginning to collaborate with civil society. It takes a critical look at the Union's New Partnership for Africa's Development (NEPAD) and argues that Africa needs to adopt a developmental and governance agenda that will be much more responsive towards improving the well-being and livelihood of its peoples.

The coordination of humanitarian relief, e.g. in a natural disaster or a conflict situation, is often complicated by a scarcity of data to inform planning. Remote sensing imagery, from satellites or drones, can give important insights into conditions on the ground, including in areas which are difficult to access. Applications include situation awareness after natural disasters, structural damage assessment in conflict, monitoring human rights violations or population estimation in settlements. We review machine learning approaches for automating these problems, and discuss their potential and limitations. We also provide a case study of experiments using deep learning methods to count the numbers of structures in multiple refugee settlements in Africa and the Middle East. We find that while high levels of accuracy are possible, there is considerable variation in the characteristics of imagery collected from different sensors and regions. In this, as in the other applications discussed in the paper, critical inferences must be made from a relatively small amount of pixel data. We, therefore, consider that using machine learning systems as an augmentation of human analysts is a reasonable strategy to transition from current fully manual operational pipelines to ones which are both more efficient and have the necessary levels of quality control.This article is part of a discussion meeting issue 'The growing ubiquity of algorithms in society: implications, impacts and innovations'.

A fundamental fact about human minds is that they are never truly alone: all minds are steeped in situated interaction. That social interaction matters is recognized by any experimentalist who seeks to exclude its influence by studying individuals in isolation. On this view, interaction complicates cognition. Here, we explore the more radical stance that interaction co-constitutes cognition: that we benefit from looking beyond single minds toward cognition as a process involving interacting minds. All around the cognitive sciences, there are approaches that put interaction center stage. Their diverse and pluralistic origins may obscure the fact that collectively, they harbor insights and methods that can respecify foundational assumptions and fuel novel interdisciplinary work. What might the cognitive sciences gain from stronger interactional foundations? This represents, we believe, one of the key questions for the future. Writing as a transdisciplinary collective assembled from across the classic cognitive science hexagon and beyond, we highlight the opportunity for a figure-ground reversal that puts interaction at the heart of cognition. The interactive stance is a way of seeing that deserves to be a key part of the conceptual toolkit of cognitive scientists.

Accurate and fine-grained information about the extent of damage to buildings is essential for humanitarian relief and disaster response. However, as the most commonly used architecture in remote sensing interpretation tasks, Convolutional Neural Networks (CNNs) have limited ability to model the non-local relationship between pixels. Recently, Transformer architecture first proposed for modeling long-range dependency in natural language processing has shown promising results in computer vision tasks. Considering the frontier advances of Transformer architecture in the computer vision field, in this paper, we present a Transformer-based damage assessment architecture (DamFormer). In DamFormer, a siamese Transformer encoder is first constructed to extract non-local and representative deep features from input multitemporal image-pairs. Then, a multitemporal fusion module is designed to fuse information for downstream tasks. Finally, a lightweight dual-tasks decoder aggregates multi-level features for final prediction. To the best of our knowledge, it is the first time that such a deep Transformer-based network is proposed for multitemporal remote sensing interpretation tasks. The experimental results on the large-scale damage assessment dataset xBD demonstrate the potential of the Transformer-based architecture.

Much like traditional dyadic mentoring experiences, group mentorship has been practiced since time immemorial. Benjamin Franklin, for example, as a young entrepreneur created the Leather Apron Club, a group mentoring experience for a select group of Philadelphia tradesmen. Since the late 1990s, when group mentoring became a serious focus of academic research, scholarship has focused primarily on the rationale for group mentoring and has explored the outcomes. As a community of scholars and practitioners, we have yet to fully explore or explain what we mean by group mentoring. In this article, I bring attention to, establish a foundation, and set appropriate parameters for group mentorship.

The orphan nuclear receptors FXR and LXRalpha have become challenging targets for the discovery of new therapeutic agents. Bile acids and hydroxysterol intermediates are the respective natural ligands of these two structurally and functionally closely related receptors. Both FXR and LXRalpha; are thought to play a major role in the control of cholesterol catabolism by regulating the expression of cholesterol 7alpha-hydroxylase, the rate limiting enzyme of bile acid synthesis. Reverse cholesterol transport might also be affected by FXR and LXR since they control the expression of PLTP and CETP, two proteins involved in the transfer of phospholipid, cholesterol and cholesteryl esters among plasma lipoproteins. A new class of potent synthetic activators of FXR, the 1,1-bisphosphonate esters, has been discovered which up regulate the Intestinal Bile Acid Binding Protein gene (I-BABP) as demonstrated for chenodeoxycholic acid, however there are no known synthetic activators yet identified for LXRalpha. The evaluation of FXR as a potential target for the development of drugs affecting plasma cholesterol can take advantage of the fact that the activators of FXR (farnesol, bile acids and the 1,1-bisphosphonate esters) have been studied in various in vitro and in vivo models. Administration of chenodeoxycholic acid to animals and man did not result in the increase in plasma cholesterol expected from a decrease in cholesterol 7alpha-hydroxylase expression. Like farnesol, the 1,1-bisphosphonate esters increase the rate of degradation of HMGCoA reductase and have the unexpected property of inducing hypocholesterolemia in normal animals. The natural and synthetic FXR agonists trigger differentiation, inhibit cell proliferation and are potent inducers of apoptosis. The 1,1-bisphosphonate ester SR-45023A (Apomine) is presently being developed as an antineoplastic drug.

Training an imbalanced dataset can cause classifiers to overfit the majority class and increase the possibility of information loss for the minority class. Moreover, accuracy may not give a clear picture of the classifier’s performance. This paper utilized decision tree (DT), support vector machine (SVM), artificial neural networks (ANN), K-nearest neighbors (KNN) and Naïve Bayes (NB) besides ensemble models like random forest (RF) and gradient boosting (GB), which use bagging and boosting methods, three sampling approaches and seven performance metrics to investigate the effect of class imbalance on water quality data. Based on the results, the best model was gradient boosting without resampling for almost all metrics except balanced accuracy, sensitivity and area under the curve (AUC), followed by random forest model without resampling in term of specificity, precision and AUC. However, in term of balanced accuracy and sensitivity, the highest performance was achieved by random forest with a random under-sampling dataset. Focusing on each performance metric separately, the results showed that for specificity and precision, it is better not to preprocess all the ensemble classifiers. Nevertheless, the results for balanced accuracy and sensitivity showed improvement for both ensemble classifiers when using all the resampled dataset.

Many cities around the world face frequent problems with flooding, which is expected to get worse due to anthropogenic climate change and further urbanization. To tackle these problems often local infrastructural adaptation measures are proposed. In this study a chain of state-of-the-art models is presented that can be used to evaluate the benefits of such measures. Also, a method is presented to calculate the costs of not responding to a changing environment that is slowly aggravating floods. These methods are applied to a case study in the city of Colombo in Sri Lanka. Colombo faces problems with floods that are expected to get worse by further wetland reduction and climate change. Several local measures (infrastructural interventions) are proposed to tackle that problem. This paper shows a method to quantify the expected reduction in future flood damages resulting from the proposed measures, and compares the risk reduction to the proposed measure costs. This is done by creating probabilistic inundation depth maps using a 1D2D hydrodynamic model. A detailed flood damage model and socio-economic development scenarios are then applied to estimate damage with and without the measures. An economic analysis is done to demonstrate the benefits of the measures, which can be used by decision makers. Additionally, calculations are carried out of future flood risk increases when wetland reduction in Colombo continues. In this case, the effect of stopping wetland encroachment is found to be larger than the effect of the structural adaptation measures.

The international community has pledged through the Sustainable Development Goals to eliminate neglected tropical diseases by 2030. Authors from 19 institutions around the world call for urgent reflection and a change in mind-set to garner support and hasten progress towards achieving this fast approaching target. They advocate for an empowering approach that will propel political momentum, milestones and targets for accountability, new science in drug development and increased funding particularly from G20 countries.

The present work considers the use of Most-Favoured-Nation (MFN) clauses within Bilateral Investment Treaties (BITs), or other International Investment Agreements (IIAs), to import provisions, not included in the IIA (such as fair and equitable treatment provisions or umbrella clauses), by investment arbitral tribunals. Many tribunals have allowed the use of MFN clauses for this purpose, imported the absent standard in the treaty, and have subsequently considered whether or not there was compliance with the imported provision. This study analyses whether this is a proper use of MFN clauses in IIAs. It first examines the practice of some investment tribunals of importing substantive provisions through MFN clauses. Secondly, it analyses whether MFN clauses can be used to import a substantive provision in order to include a new obligation and, at the same time, confer jurisdiction to decide on breaches of imported provisions. In doing so it explores the nature, scope, and limits of MFN clauses as well as the principle of consent to international jurisdiction. Thirdly, it considers how tribunals should proceed when faced with this type of argument, focusing on the interpretation of the elements of MFN clauses. It is suggested that typical MFN clauses included in IIAs should not be used to import treaty provisions.

Tearful crying is a ubiquitous and likely uniquely human phenomenon. Scholars have argued that emotional tears serve an attachment function: Tears are thought to act as a social glue by evoking social support intentions. Initial experimental studies supported this proposition across several methodologies, but these were conducted almost exclusively on participants from North America and Europe, resulting in limited generalizability. This project examined the tears-social support intentions effect and possible mediating and moderating variables in a fully pre-registered study across 7007 participants (24,886 ratings) and 41 countries spanning all populated continents. Participants were presented with four pictures out of 100 possible targets with or without digitally-added tears. We confirmed the main prediction that seeing a tearful individual elicits the intention to support, d = 0.49 [0.43, 0.55]. Our data suggest that this effect could be mediated by perceiving the crying target as warmer and more helpless, feeling more connected, as well as feeling more empathic concern for the crier, but not by an increase in personal distress of the observer. The effect was moderated by the situational valence, identifying the target as part of one's group, and trait empathic concern. A neutral situation, high trait empathic concern, and low identification increased the effect. We observed high heterogeneity across countries that was, via split-half validation, best explained by country-level GDP per capita and subjective well-being with stronger effects for higher-scoring countries. These findings suggest that tears can function as social glue, providing one possible explanation why emotional crying persists into adulthood.

Strengthening capacity for research is of vital relevance to global health since research is fundamental to the improvement of health everywhere, but the capacity to do research varies enormously between countries. External donors broadly agree on the exigence to support national efforts to strengthen the capacity for health research in low-income and middleincome countries. Current levels of external funding may support the concentration of activities in pursuit of excellence in some countries without achieving the aims of equity to ensure all countries can benefit from producing research. Key elements for debate as external donors and partner countries pursue the benefits of excellence and equity include: (1) the need for evidence-based decision making, (2) the promotion of standardised collection and open reporting of data, (3) the level of funding which can avoid competition between excellence and equity, (4) revisiting what 'excellence' means, and (5) the implications of a shift to local leadership and knowledge in driving development practice.

The incentives and disincentives for countries to go nuclear comprise a combination of military, political, and economic concerns and motivations. These vary over time for different countries. For countries allied to one of the two nuclear superpowers, concern about their military security is not a predominant factor, while it is the decisive one for the non-nuclear countries who are not under the nuclear umbrella of a superpower and who perceive serious threats to their security. For countries without acute security problems, the political and economic motivations are the predominant ones and these include such incentives as strengthening their independence and increasing their status and prestige in the world. The disincentives are largely potential, ranging from effective security guarantees through adequate supplies of conventional armaments to assurances concerning future supplies of fissile materials. Incentives to go nuclear appear to outweigh the disincentives. Only drastic measures by the nuclear powers in the way of security assurances, nuclear disarmament, and the creation of a more just political and economic world order can serve to prevent the emergence of a proliferated world.

In an article published concurrently in the Journal of International Economic Law , I reach many of the same conclusions as Simon Batifort and J. Benton Heath regarding the use of most favored nation (MFN) clauses to import substantive provisions from other treaties. However, although our conclusions are similar, our reasoning differs in several important respects. In my view, the reasons why MFN clauses cannot be used to import treaty provisions have more to do with the nature of these clauses than their specific text. MFN clauses are primary rules that require performing a comparison and determining whether there is a breach of the provision, and this produces legal effects that run against any attempt at importation. In addition, it is not possible or desirable to interpret MFN clauses in isolation from general international law. Stephan Schill is also correct that Batifort and Heath cannot disclaim the normative implications of their effort to shift the debate over MFN clauses. But Schill confuses the legal effects of MFN clauses with a policy consideration (multilateralization) and misreads the interpretative background that must be considered when applying MFN clauses. Schill also mistakes multilateralization via arbitral interpretations of MFN clauses for true multilateralism, which is the product of states working together in multilateral fora. That distinction matters, too, for Schill's solution might provoke a state-led backlash that will undermine the very multilateralism he seeks to promote.

With estimates of 81 410–137 880 deaths and 400 000 cases of disability globally every year,1Williams DJ Faiz MA Abela-Ridder B et al.Strategy for a globally coordinated response to a priority neglected tropical disease: snakebite envenoming.PLoS Negl Trop Dis. 2019; 13e0007059Crossref PubMed Scopus (100) Google Scholar, 2Gutiérrez JM Calvete J J Habib AG Harrison RA Williams DJ Warrell DA Snakebite envenoming.Nat Rev Dis Primers. 2017; 317063Crossref PubMed Scopus (315) Google Scholar snakebite envenoming needs urgent attention. WHO launched a road map in May, 2019, and by 2030 hopes to see three million effective treatments produced annually and to halve snakebite-associated deaths and disabilities.1Williams DJ Faiz MA Abela-Ridder B et al.Strategy for a globally coordinated response to a priority neglected tropical disease: snakebite envenoming.PLoS Negl Trop Dis. 2019; 13e0007059Crossref PubMed Scopus (100) Google Scholar Yet, before treating snakebite envenoming, there are fundamental questions: which species of snake has bitten the victim, what are the probable outcomes, and how can we intervene to improve the prognosis? These factors are central to understanding snakebite epidemiology. Globally there are over 3700 snake species, 650 of which are venomous, and of these 250 are medically important.1Williams DJ Faiz MA Abela-Ridder B et al.Strategy for a globally coordinated response to a priority neglected tropical disease: snakebite envenoming.PLoS Negl Trop Dis. 2019; 13e0007059Crossref PubMed Scopus (100) Google Scholar Presumption of the identity of the biting species can result in inappropriate use of antivenoms, which are in scarce supply, costly, and can have side-effects.3Bawaskar HS Bawaskar PH Snakebite envenoming.Lancet. 2019; 393: 131Summary Full Text Full Text PDF PubMed Scopus (7) Google Scholar Giving correct snake taxonomic attribution can improve epidemiological data and the specific coverage of antivenoms against species that occur in given regions and inform selection and use of appropriate antivenoms. In some settings, people who have suffered a snake bite or bystanders will either describe the biting snake, or even capture or kill it, creating additional risk to those involved4Alirol E Sharma SK Bawaskar HS Kuch U Chappuis F Snake bite in south Asia: a review.PLoS Negl Trop Dis. 2010; 4: e603Crossref PubMed Scopus (244) Google Scholar and potentially affecting the ecology of snake populations. But health-care providers, not being snake experts, often struggle to identify the snake and its misidentification can lead to inadequate management of the victim.4Alirol E Sharma SK Bawaskar HS Kuch U Chappuis F Snake bite in south Asia: a review.PLoS Negl Trop Dis. 2010; 4: e603Crossref PubMed Scopus (244) Google Scholar Given that snakebite envenoming is an acute emergency, the ability to rapidly select appropriate treatment (eg, antivenom, ventilatory support) and administer it is paramount.4Alirol E Sharma SK Bawaskar HS Kuch U Chappuis F Snake bite in south Asia: a review.PLoS Negl Trop Dis. 2010; 4: e603Crossref PubMed Scopus (244) Google Scholar Although immunoassays and molecular tools have been developed to identify some snakes, they have limitations (eg, cost, need for technicians, and poor specificity) and are currently only used in Australia and Papua New Guinea.4Alirol E Sharma SK Bawaskar HS Kuch U Chappuis F Snake bite in south Asia: a review.PLoS Negl Trop Dis. 2010; 4: e603Crossref PubMed Scopus (244) Google Scholar, 5Williams HF Layfield HJ Vallance T et al.The urgent need to develop novel strategies for the diagnosis and treatment of snakebites.Toxins. 2019; 11: 363Crossref Scopus (27) Google Scholar Rapid diagnostic tests are emerging, although none have yet been marketed, and their effective deployment in low-income and middle-income countries remains to be seen.5Williams HF Layfield HJ Vallance T et al.The urgent need to develop novel strategies for the diagnosis and treatment of snakebites.Toxins. 2019; 11: 363Crossref Scopus (27) Google Scholar Currently, a syndromic approach is widely used to manage snakebite envenoming, which can also help to infer the identity of the biting snake, but this strategy has limitations.4Alirol E Sharma SK Bawaskar HS Kuch U Chappuis F Snake bite in south Asia: a review.PLoS Negl Trop Dis. 2010; 4: e603Crossref PubMed Scopus (244) Google Scholar The rapid growth in smartphone use and Internet penetration in low-income and middle-income countries, as well as the availability of artificial intelligence (AI)-based animal identification techniques,6Tabak MA Norouzzadeh MS Wolfson DW et al.Machine learning to classify animal species in camera trap images: applications in ecology.Methods Ecol Evol. 2019; 10: 585-590Crossref Scopus (92) Google Scholar provide opportunity for snake identification from photos. For instance, the popular ornithology app Merlin Bird ID recognises more than 3000 American and European birds. If applied to snakes, this technology could improve our knowledge of their global diversity and abundance, particularly in countries where snake bites are a concern. For health workers and patients, this technology has potential to improve identification of biting species, facilitating access to, and appropriate stocking of effective antivenoms, and guiding better treatment by building profiles of endemic snake fauna and their clinical syndromes. The AI revolution in health care should embrace neglected communities who are affected by snakebite with a precision public health approach,7Horton R Offline: In defence of precision public health.Lancet. 2018; 392: 1504Summary Full Text Full Text PDF PubMed Scopus (35) Google Scholar going beyond applications in high-income countries that target a few diseases. We have an opportunity to empower communities at risk of snakebite and health-care providers with AI, while building knowledge in snake biology and ecology and capacity to manage snakebite at all levels (eg, from the field, where snake bites occur, to the health facility level, where the victim is treated). Communities at risk are at the frontline and can participate in snake identification directly or indirectly by gathering and sharing data such as snake photos, location, and type of habitat. Additionally, snake experts, who provide the gold standard snake identification and are key to training the AI algorithm, could be integrated in health systems in countries with high frequencies of snakebite. This integration is already the case for other diseases with implications for entomologists or parasitologists. Such a collaborative approach involving communities at risk, health-care providers, and snake experts, all supported by AI, can strengthen health systems in line with WHO's road map (panel).1Williams DJ Faiz MA Abela-Ridder B et al.Strategy for a globally coordinated response to a priority neglected tropical disease: snakebite envenoming.PLoS Negl Trop Dis. 2019; 13e0007059Crossref PubMed Scopus (100) Google ScholarPanelUses of smartphone technology in snakebite•a computer vision algorithm and crowdsourcing (ie, involving the community of snake experts)8Ruiz de Castañeda R Williams DJ Grey F Citizen science could map snake bite risk.Nature. 2019; 571: 478Crossref PubMed Scopus (5) Google Scholar to identify the biting snake from a geo-localised photo taken by the victim, a bystander, or health worker•first aid recommendations for the victim or bystander to avoid common unsafe practices•guidance for urgent access to the nearest snakebite treatment centre by integrating information on road network, modes of transport, terrain specificities, availability of antivenom and other lifesaving health care,9Longbottom J Shearer FM Devine M et al.Vulnerability to snakebite envenoming: a global mapping of hotspots.Lancet. 2018; 392: 673-684Summary Full Text Full Text PDF PubMed Scopus (94) Google Scholar and also letting the bitten person know of how urgent the care needed is•a clinical decision support system for health-care providers to treat the victim •a computer vision algorithm and crowdsourcing (ie, involving the community of snake experts)8Ruiz de Castañeda R Williams DJ Grey F Citizen science could map snake bite risk.Nature. 2019; 571: 478Crossref PubMed Scopus (5) Google Scholar to identify the biting snake from a geo-localised photo taken by the victim, a bystander, or health worker•first aid recommendations for the victim or bystander to avoid common unsafe practices•guidance for urgent access to the nearest snakebite treatment centre by integrating information on road network, modes of transport, terrain specificities, availability of antivenom and other lifesaving health care,9Longbottom J Shearer FM Devine M et al.Vulnerability to snakebite envenoming: a global mapping of hotspots.Lancet. 2018; 392: 673-684Summary Full Text Full Text PDF PubMed Scopus (94) Google Scholar and also letting the bitten person know of how urgent the care needed is•a clinical decision support system for health-care providers to treat the victim A collaborative approach would continually generate eco-epidemiological (eg, snake and snakebite distribution) and clinical (eg, clinical signs, treatment, and patient outcome) data, which would develop the system itself for an improved understanding of snakebite. This would also complement the syndromic approach to snakebite envenoming, by anticipating clinical signs on the basis of snake identity or, in the absence of a snake photo, by matching clinical signs with prevalent snakes in the geographical area where the bite occurred. This AI-based approach needs to be tested in the lab and in the field and depends on the taxonomic and geographical representativeness of the training dataset, availability of smartphones in poor settings, capacity and safety of taking a photo of the biting snake, and availability of information on antivenom stockpiles. In this context, initiatives such as the Snake Identification Service of Sri Lanka and the Big Four Mapping Project in India are highly relevant. Although there are substantial challenges to the use of AI in snake identification and treatment of snakebite envenoming, we can overcome them. The roll out of WHO's road map between 2019 and 2030, together with the leadership of Ministries of Health, can promote AI research and uptake of digital solutions in snakebite-endemic countries. The WHO-International Telecommunication Union Focus Group on AI for Health, created in 2018 for benchmarking the development of AI algorithms, already supports a topic group on AI for snakebite and snake identification.10Wiegand T Krishnamurthy R Kuglitsch M et al.WHO and ITU establish benchmarking process for artificial intelligence in health.Lancet. 2019; 394: 9-11Summary Full Text Full Text PDF PubMed Scopus (14) Google Scholar Our interdisciplinary team drives this group in collaboration with Médecins Sans Frontières, among others addressing snakebite envenoming in the field. Major stakeholders from the digital industry are committing to financially and technically support projects applying AI to global challenges, including snakebite (eg, the Computer Vision for Global Challenges workshop in June, 2019). Collaborations across sectors, including the engagement of communities and the role of non-governmental organisations, and sharing of resources are key to implementing WHO's road map and innovative digital approaches based on AI such as those proposed here. We declare no competing interests. RRdC is supported by Fondation Louis-Jeantet and AMD is supported by the Fondation privée des Hôpitaux Universitaires de Genève (Grant number QS04-20 ).

The Gulf of Aqaba is a long, narrow body of water on the eastern side of the Sinai Peninsula. The western shore is Egyptian, the eastern shore is Saudi Arabian, and the head of the Gulf is Israeli and Jordanian territory. The islands of Tiran and Sanafir front the entrance and have been under Egyptian occupation since 1950. Saudi Arabia, however, maintains the claim that the two islands are Saudi Arabian territory. The length of the Gulf is about 96 miles; the breadth at the entrance to the Gulf is 5¾ miles; at its widest the Gulf measures 14½ miles. The entrance to the Gulf is through the Strait of Tiran (about 3 miles wide), between Tiran Island and the Egyptian coast. There are two passages in the Strait; Enterprise Passage and Grafton Passage, 1,300 and 950 yards wide, respectively. Enterprise Passage, which lies close to the Sinai Peninsula coast, is the principal navigation channel into the Gulf, and the only channel that can be navigated safely by vessels of substantial size. On the coastline, Egypt and Saudi Arabia each have over 100 miles of territory; also Jordanian territory encompasses about 3½ miles and the territory of Israel about 6 miles.

Satellite-observed night-time light data has been widely applied to estimate natural disaster loss, which is important for evaluating progress of SDG 11 and 13, but large uncertainty of the time series data hindered the evaluation in high accuracy. This study aims to estimate power outage, a proxy of economic loss, after natural disasters using VIIRS daily night-time light data with improved quality, which is able to capture abrupt change of the light. Firstly, an angular normalization algorithm was developed to generate a stable time series of night-time light data with less fluctuation, and it was validated with different metrics. The algorithm was then applied to analyze power outage after 2017 Maria Hurricane in Puerto Rico, and it was found that the Pearson correlation coefficient between the improved night-time light data and power supply is 0.929 in Puerto Rico, suggesting that the data is accurate to reflect the power supply. For the eight regions in Puerto Rico, they totally lost 78.01% of the power supply after the hurricane, while Caguas, Guayama and Humacao are the regions suffering from the hurricane most severely, losing 94.29%, 92.85% and 88.38% of power supply, respectively, and their recovery speeds are also relatively slow compared to other regions. In addition, we discuss the possibility of using the night-time light indicator for estimating GDP loss of service and industry due to disaster-derived power outage.