Research Proposal for Leveraging Research on Sustainable Data Methods Used in Lebanon to Forecast Disaster Management Efforts

Introduction

The ammonium nitrate explosion on the port of Beirut on August 4, 2020, led to a total of 218 deaths and 7,000 injuries, accompanied by the destruction of vital health infrastructure that caused many to be left untreated or treat themselves at home. According to Beirut Ammonium Nitrate Explosion: A Man-Made Disaster in Times of the COVID-19 Pandemic, “This event immediately overwhelmed the ability of Beirut hospitals, emergency medical services (EMS) agencies, first responder agencies, and other responding agencies to mount an effective response. Casualties flooded local hospitals with the less injured arriving first by private transportation or by walking to nearby hospitals and the more injured arriving later by EMS vehicles” (El Sayed, 2020). This meant that health officials in the area had no concrete plan of foreseeing this deadly event in which the current system of infrastructure was unable to support. Furthermore, many rescue teams were unable to work effectively since many of them were from outside the country, which meant that a bulk of the recovery process was spent on informing foreign aid networks of the incident rather than having a solid and strategic plan to help people within the blast’s radius. However, Lebanese data analysts have only recently discovered the use of GIS systems that account for areas in which most civilians do not inhabit, such as the warehouse that stored the explosive chemicals at the port. According to Statistics Lebanon Polling and Research in 2018, “We now have listings of all dwellings, buildings, apartments, and other nonresidential uses indicated on the cluster map.” Now that data methods like baseline cell cluster data and the topsy method have been researched and selected as the sustainable methods to be used in Lebanon as modeled in the Democratic Republic of the Congo and Japan respectively, the next step is to seek attention from institutions that must adapt to the advent of technology serving as a life-saving tool in the context of disaster management.

Since Statistics Lebanon recently announced that they have expanded their cluster maps to account for formerly known nonresidential zones in their GIS systems, the country has yet to see funding from institutions in the region to support these causes, especially for the devastating impacts from the ammonium nitrate explosion to the impoverished population in the so-called “nonresidential” zones of the country. Therefore, there has been no incentive for Statistics Lebanon to incorporate these sustainable methods used abroad, which can be attributed to the government’s lack of funding, weak networks with other countries from debt scandals, and overpriced educational opportunities for the youth involved to give purpose to the research company’s objectives with GIS systems.

Overall, the benefits that come from remedying these issues is that the vanishing side of the population that lives in “nonresidential” designated areas will receive roughly as much aid as needed in times of disaster. Furthermore, strengthening the foundation of geospatial research at the educational level will help draw more attention to the gap that is present in Lebanon’s ability to overcome disasters, which may eventually cause international donors to place more trust in their economic partner as the country invests in essential research for the long-term. This global recognition will be much needed since the country still depends on foreign influence to mitigate the effects of disasters and has yet to develop optimal capabilities to manage them on its own. However, this should only be temporary as the research proposal aims to heighten development in Lebanon to maximize the safety of its population.

Proposal

The steps that should be further taken to support the implementation of these sustainable data methods in Lebanon’s disaster-prone environments are as follows: offer affordable study abroad programs for students to customize the aforementioned data methods, integrate projects from a variety of researchers that can help guide Statistics Lebanon in the right direction by encouraging the institution to release data without imposing biases in methods, and garner support for the implementation of machine learning by hosting global conferences between countries that have been able to navigate disaster management effectively and encourage the youth to get involved. These steps must be followed in the listed order as any other order would be placing the country in a position of defense and would be seen as a struggle for compliance as opposed to a naturally occuring progression of the adoption of disaster management machine learning technologies. The goal is to foster this vision in order to convince policymakers that this is a pressing issue that affects many lives that are not accounted for by the flawed leadership in the country.

To better understand the core problem with underfunded disaster management in Lebanon, immediate risk to the population must be observed to uncover why institutions in Lebanon have not prioritized areas near the warehouse explosion. For what I have researched in every study, there have been set parameters for each data method that had been crafted for a specific population. In the study of baseline cell cluster data in the Democratic Republic of the Congo, research revolved around the imminent threat to the population, Mount Nyiragongo and the several volcanoes that surround the region, which threaten the lives of the population surrounded by them. According to Eruption of Mount Nyiragongo: Estimating Population Displacement Using Mobile Operator Data by Vodacom RDC, “Mount Nyiragongo erupted on May 22, 2021. Although the time for emergency response had passed, the estimated scale of population movements suggested that recovery from this disaster and a return to normal may require significant efforts over the coming weeks and months.” On the other hand, the topsy method study in Japan after the earthquake and tsunami in 2011 focused on outreach to both domestic and international users, leading to a global effort that brought aid officials in touch with each other. As recorded in the study, “Characterizing the Japanese network before and after the earthquake shows clear increases in Twitter use” (Lu & Brelsford, 2014). Consequently, there is a need to have defined parameters when observing Lebanon as explosions may not be predictable by location. According to The Beirut Port Explosion: Understanding Its Impacts and How to Reduce Risks from Explosive Precursors, “The harm to the density and inherent vulnerability of the civilian population and its dependence on the web of critical interconnected services that are equally vulnerable to the damaging effects of the explosive blast” (Seddon & Shiotani, 2020). It is a necessity to have all parts of the country secured since many security breaches can be made from any point on a cluster map. The hypothesis, therefore, is that more research on incorporating nonresidential zones into standard and refined models will result in less deaths and injuries to the population and make aid allocation more efficient, subsequently leading to more domestic and international support for Lebanese disaster management operations due to the country gaining more trust from international donors.

Objectives, Obstacles, and Gains

The mission that my research aims to work towards is to incorporate these methods by fostering more support for the field of data science in Lebanon, both institutionally and academically. Gathering scholars from around the world through study abroad programs will promote the use of machine learning technology and innovations that are being created in other unique and geographically prone areas. Most importantly, there will be significant financial aid granted to students who struggle to make educational payments, as education in Lebanon is not funded by the government. It is important to note that these programs will only be offered to university students and computer scientists as they have been exposed to advanced computer science concepts, which can be oriented to focus on how algorithms can be applied to sustainable disaster management, such as identifying the cell cluster method of Statistics Lebanon and how it does not fully account for “nonresidential” zones. This approach would help direct students in a path that is focused on ameliorating the conditions of impoverished communities that do not live close to cities in Lebanon. However, this can be difficult for longevity as many colleges, such as American University of Beirut, offer majors in computer science, computer science engineering, and computer and communications engineering, leaving data science out of the picture (American University of Beirut). The students would be tasked with looking for biased algorithms in Lebanon and will eventually produce an algorithm, backed by research on underrepresented populations in Lebanon that could provide a solution to the gap that Statistics Lebanon has been neglecting in its data for years. According to Eruption of Mount Nyiragongo: Estimating Population Displacement Using Mobile Operator Data by Vodacom RDC, “The percent change is relative to the baseline measurement of the number of subscribers located in a cluster under a 24h period.” This would ideally be implemented in Lebanon since much of the data used from the explosion was from the population in the city. However, its use in nonresidential zones would help aid officials by directing them to all affected individuals with a daily update in migratory patterns.

Following the project among students studying abroad, the students who express an interest in working for Statistics Lebanon through internships or careers will share their ideas with the rest of the company in order to draw attention to the biases in cluster maps used to mitigate the effects of disasters. The newly improved map will contain data points in the formerly called “nonresidential” areas to account for life around disaster-prone regions. This means that off-the-grid places, such as areas around the warehouse explosion, will be part of the emergency routes that institutions usually overlook in the event of an emergency. Although this will result in a lot of progress for the company, it will need to fund these expenditures through a method that will also prove useful for managing aid. As used in Japan to observe the creation of online communities, the topsy method was devised to match users to nodes, suggesting that health officials were communicating with citizens online through an elaborate community of both native and global users. In order for Statistics Lebanon to receive its funding, it will also need to invest in this as it will spread awareness to international health organizations and donors that will be able to contribute to relief efforts with medical supplies and funds for research. Building these relationships over time will allow internationally-affiliated organizations such as the International Monetary Fund to gain trust in Lebanon and eventually lead to more funding for the nation’s refined disaster management methods.

The final step to this plan for leveraging research on sustainable methods in Lebanon to be used in nonresidential zones is to host global conferences with organizations that seek to share their innovations with each other. This will put into motion the proposed model by collaborating with other aspiring data scientists that seek to learn how they can improve their disaster management methods. In terms of Lebanon, there will need to be simulations in place before the model is put into use, which will require international collaboration as health organizations Lebanon is partnered with will need to know how these methods can make their work a lot more transparent.

Funding

The proposal will require the researchers from the studies of baseline cell cluster data and the topsy method to collaborate with each other for the duration of the study abroad programs. The head researchers of the baseline cell cluster data study from Flowminder will split the students into two groups based on their interests in revising the methods used by Statistics Lebanon, with one group being tasked with incorporating nonresidential zones into the algorithm while the other focuses on developing an algorithm that gets updated in a 24-hour interval in order to accurately track migratory patterns in these locations. Furthermore, head researchers that studied the topsy method, Xin Lu & Christa Brelsford, will also be requested to work with. The students focused on international outreach will be divided into three groups: isolating the digital Arabic-speaking population, non-native Arabic-speaking population, and global users on social media to effectively measure the response from users mentioning each other online with a percentage relative to before and after the occurrence of a disaster to locate aid organizations reaching out to Lebanon. After the customization of these sustainable data methods is completed, the scholars and possibly former employees will present their findings to Statistics Lebanon upon entry to the organization. However, there will be a need for funds in order to develop the required technologies in the Statistics Lebanon laboratory, which is where the researchers of the topsy method will play a role in collecting foreign aid from other countries, making it less costly to compensate workers and develop technology. Subsequently, Statistics Lebanon will host annual global conferences to meet with potential foreign donors by having face-to-face interactions that will allow researchers in Lebanon to gain trust and international recognition for their revitalized work.

<image src= “ Screen Shot 2021-12-13 at 3 33 15 PM

In summary, developing an algorithm based on baseline cell cluster data to incorporate nonresidential zones in Lebanon will benefit Statistics Lebanon and the country in the long-run by saving lives that have been neglected for years while also having a stable source of funding from other countries through the topsy method. The hope of the study is to convince officials in higher positions of the country that inequalities in health infrastructure must be remedied to meet the needs of the population in the event of a disaster.

Works Cited

“American University of Beirut.” Majors and Programs, https://www.aub.edu.lb/academics/pages/majors_programs.aspx. Accessed 11 Dec. 2021.

El Sayed, Mazen J. “Beirut Ammonium Nitrate Explosion: A Man-Made Disaster in Times of the Covid-19 Pandemic.” Disaster Medicine and Public Health Preparedness, Cambridge University Press, 18 Nov. 2020, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7985624/. Accessed Dec. 11 2021.

Flowminder, and Vodacom RDC. “Publication: Eruption of Mount Nyiragongo: Estimating Population Displacement Using Mobile Operator Data.” Publication: Eruption of Mount Nyiragongo: Estimating Population Displacement Using Mobile Operator Data, 6 July 2021, https://www.flowminder.org/resources/publications/eruption-of-mount-nyiragongo-estimating-population-displacement-using-mobile-operator-data-call-detail-records. Accessed 11 Dec. 2021.

Lu, Xin, and Christa Brelsford. “Network Structure and Community Evolution on Twitter: Human Behavior Change in Response to the 2011 Japanese Earthquake and Tsunami.” Nature News, Nature Publishing Group, 27 Oct. 2014, https://www.nature.com/articles/srep06773. Accessed 11 Dec. 2021.

Seddon , Bob, and Himayu Shiotani . “The Beirut Port Explosion: Understanding Its Impacts and How to Reduce Risks from Explosive Precursors.” HeinOnline, https://heinonline.org/HOL/Page?handle=hein.unl%2Fbpeui0001&id=1&collection=unl&index=. Accessed 11 Dec. 2021.

Statistics Lebanon, “Beyond Data: Statistics Lebanon.” Beyond Data

Statistics Lebanon Polling and Research , Stat, https://www.statisticslebanonltd.com/node/149. Accessed 11 Dec. 2021.