{"id":1090,"date":"2024-10-13T08:49:00","date_gmt":"2024-10-13T15:49:00","guid":{"rendered":"https:\/\/dornsife.usc.edu\/scribe\/?p=1090"},"modified":"2026-04-24T08:51:01","modified_gmt":"2026-04-24T15:51:01","slug":"a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development","status":"publish","type":"post","link":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/","title":{"rendered":"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development"},"content":{"rendered":"\n\n\n\n\n \n \n\n\n\n\n\n\n\n
\n\n \n
\n \n \n
\n \n \n
\n\n \n

A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development<\/h1>\n\n\n<\/div>\n \n \n By<\/span>Avinash Chauhan<\/strong>\n \n October 13, 2024<\/span>\n <\/div>\n<\/div>\n\n\n <\/div><\/div>\n\n \n \n\n\n\n\n\n\n\n
\n\n \n
\n \n \n Share\n <\/span>\n \n \n <\/svg>\n <\/span>\n Copy Link<\/span>\n <\/a>\n \n \n <\/svg>\n <\/span>\n Facebook<\/span>\n <\/a>\n \n \n \n\n<\/svg>\n\n <\/span>\n X<\/span>\n <\/a>\n \n \n <\/svg>\n <\/span>\n LinkedIn<\/span>\n <\/a>\n \n \n \n \n <\/svg>\n <\/span>\n Bluesky<\/span>\n <\/a>\n \n \n <\/svg>\n <\/span>\n Email<\/span>\n <\/a>\n <\/span>\n <\/div>\n\n <\/div><\/div>\n \n\n\n\n \n \n\n\n\n\n\n\n\n
\n\n \n \n
\n\n \n
<\/header>\n
\n

The proliferation of nuclear weapons is a critical global security issue, posing significant environmental energy, and geopolitical challenges. Understanding and predicting nuclear proliferation trends are seminal for shaping effective non-proliferation policies and even simply preventing future conflict, particularly at the intersection of nuclear proliferation, environmental sustainability, and political reform. In this study, I aimed to understand trends in nuclear proliferation and then develop a comprehensive model to predict said proliferation of nuclear weapons among nations over the next two decades. Leveraging a diverse dataset of historical nuclear proliferation information, this model employs advanced machine learning techniques to forecast nuclear weapon acquisition by countries. This paper outlines the methodology, data sources, and analytical approaches used in constructing the model. By leveraging a diverse dataset and advanced machine learning techniques, this paper seeks to propose real-world solutions to mitigate the environmental and geopolitical challenges posed by nuclear weapons, thereby contributing to the broader efforts of promoting global disarmament, non-proliferation, and sustainability.<\/p>\n

I. INTRODUCTION
\nNuclear proliferation poses significant challenges to global security. The risks associated with the proliferation of nuclear weapons are multifaceted, involving geopolitical tensions, environmental detriment, and the potential for nuclear arms races. To address these challenges, it is imperative to understand and predict the factors influencing a nation\u2019s decision to pursue nuclear weapons. This paper presents a comprehensive analysis and predictive model of nuclear proliferation, focusing on the period from the inception of the atomic age to the present day. By examining historical data from 1945 to 2022, including nuclear technology development, international treaties, political stability, and regional conflicts, I hope to provide insights into the dynamics of nuclear proliferation. My study aims to answer key questions: (1) What are the historical trends in nuclear proliferation? (2) What is the most likely scenario for nuclear proliferation over the next few decades? Through this study, I seek to contribute to the formulation of effective non-proliferation policies and strategies.<\/p>\n

II. METHODS
\nA. Model Assumptions
\nThis predictive model is based on the assumption that the historical trends and patterns in nuclear weapon quantities offer valuable insights into future proliferation trends. This model posits that the historical stockpile data, when analyzed in conjunction with economic indicators such as GDP per capita and population share, can provide a reliable basis for learning and forecasting future changes in nuclear arsenals.<\/p>\n

B. Symbol Descriptions and Mathematical Models
\nTABLE I. SYMBOL DESCRIPTIONS<\/p>\n

\"\"<\/a><\/figure>\n

Definition 1: Random Forest Model for Nuclear Stockpile Prediction This Random Forest model (RF) is defined as a regression model that utilizes historical data (NWS_i) along with GDP_i and PS_i, all of which are included within X_hist to predict future nuclear stockpiles. The model learns from past trends in nuclear armament to understand how economic and demographic factors might influence future changes:<\/p>\n

\"\"<\/a><\/figure>\n

Definition 2 (Feature Set Compilation)
\nThe feature set X_hist is compiled from historical records of nuclear stockpiles, GDP per capita, and population share. This comprehensive dataset allows the model to recognize patterns and correlations over time:<\/p>\n

\"\"<\/a><\/figure>\n

Definition 3 (Historical Data-Driven Predictive Function)
\nThe predictive function of the Random Forest model relies on historical data to forecast future stockpiles, where K represents the number of decision trees in the Random Forest. It uses a non-linear approach to understand how past stockpile trends, in combination with economic and demographic factors, predict future nuclear proliferation:<\/p>\n

\"\"<\/a><\/figure>\n

III. RESULTS
\nA. HISTORICAL ANALYSIS<\/p>\n

\"\"<\/a><\/figure>\n

Figure 1. Number of Nuclear Test by Selected Countries<\/p>\n

\"\"<\/a><\/figure>\n

Figure 2. Historical Data for Nuclear Stockpiles; (a) trends in nuclear stockpiles over the past half decade indicate a decrease in the total stockpiles; (b) nuclear weapons testing activity has declined significantly, in no small part by virtue of ef ective policy interventions at the global and national levels; (c) the \u201cstatus\u201d of countries in possession of nuclear weapons has increased.<\/p>\n

\"\"<\/a><\/figure>\n

Figure 3. Mapping significant historical events within the nuclear landscape to changes in the global weapons stockpile.<\/p>\n

B. PROSPECTIVE ANALYSIS<\/p>\n

\"\"<\/a><\/figure>\n

Figure 4. Diagnostic Plots (a) Residuals appear to fluctuate around zero (b) The histogram, combined with the Kernel Density Estimate (KDE), suggests the residuals are approximately normally distributed, but there might be some deviation from normality. (c) Normal Q-Q plot points largely follow the line, indicating normal distribution. (d) Most autocorrelations are within the confidence interval.<\/p>\n

\"\"<\/a><\/figure>\n
\"\"<\/a><\/figure>\n

Figure 5 Forecasted Nuclear Stockpile Plots (a) There looks to be a slight decline in the stockpile on a global level; (b) the United States is forecasted to stagnate in its stockpile growth; (c) China looks to increase their total stockpile, though at relatively low scale; (d) Russia projected to stagnate.<\/p>\n

IV. DISCUSSION
\nPerhaps the most moving insight from the historical data analysis is the sheer extent to which both nuclear weapons testing and the total nuclear stockpile have diminished post hoc the Cold War. Figure 1 depicts the sharp decline in nuclear tests, which suggests that international norms against testing are gaining traction. This can be reinforced by Figure 3, which demonstrates the correlative effects of policy and widespread interventions on this general decline. And yet, Figure 2c shows an increase in the \u201cstatus\u201d of countries in possession of nuclear weapons. This trend indicates the need for adaptive strategies to address new proliferation challenges, focusing on both diplomatic engagement and non-proliferation enforcement mechanisms. While stockpiles have trended down for the past few decades, this should not be conflated with a lack of proliferation. This can be partially understood by a method of strategic arms reductions via Figure 2a. Namely, the overall decrease in nuclear stockpiles signals progress in arms reduction from countries that have historically held the most arms (i.e. the United States and Russia).
\nThus, while traditional nuclear powers are reducing their arsenals, the number of states interested in nuclear capabilities is on the rise: this strategy of vertical arms reduction occurs independently of horizontal nuclear proliferation. While this vertical reduction trend should be encouraged through continued dialogue and negotiation of bilateral and multilateral arms reduction treaties, such as the extension of New START, such reduction occurs on a fundamentally different dimension than proliferation. Horizontally adjacent policy must focus on addressing the motivations of these newly proliferating states, potentially through security assurances and regional security frameworks. Remaining cognizant of this potential conflation is seminal for effectively shaping future nuclear arms policy on both the horizontal and vertical axes. Tangentially, this shift in nuclear status and the decline in stockpiles also underscore the importance of a strong nuclear security culture (propagated on a global level) to prevent theft, sabotage, and unauthorized use of arms, particularly in regions with increasing nuclear interest.<\/p>\n

In the discussion of global nuclear disarmament trends, Figure 3 is particularly novel in that it represents the decline in nuclear weapons stockpile from its late 20th-century peak. In effect, it provides an empirical basis to consider the influence of transnational peace movements and unilateral disarmament initiatives. For instance, authors such as Matthew Evangelista highlight that actions such as the shift to \u2018nonoffensive defense\u2019 and the new policy toward Eastern Europe were \u201cconsistently promoted by transnational activists\u201d and embraced by the USSR, substantially altering the geopolitical landscape and contributing to the end of the Cold War (The Transnational Movement to End the Cold War). This points to the tangible effect of transnational disarmament initiatives upon the nuclear stockpiles, with the data corroborating this upshot that such activism played a significant role in shaping global nuclear policies. Even the mass antinuclear activities, such as the Nevada-Semipalatinsk movement, underline the public\u2019s capability to influence policy decisively. Evangelista noted the movement\u2019s \u201cpotent mix of ecological nationalism and transnational peace activism\u201d brought tens of thousands of protesters into the streets, which \u201ceventually shut down the main Soviet nuclear test range in Kazakhstan\u201d. Basically, such substantial grassroots mobilization functionally elicited policy shifts that aligned with the popular will for disarmament. These insights from Evangelista\u2019s analysis, in conjunction with Figure 3, suggest that the reductions in nuclear arsenals were not simply the product of diplomatic negotiations but were significantly driven by a transnational advocacy for disarmament; in other words, the key historical events that I highlighted should not be reductively understood as independently elicited the shifts in stockpile volume. Furthermore, these factors collectively look to play a significant role in shaping the future distribution of nuclear stockpiles. Moreover, the forecasted plots generated through the computational model show the historical and forecasted nuclear weapons stockpiles at a global and national level. For instance, the United States shows a significant decrease in actual stockpiles, with the forecast suggesting a continued plateau. China\u2019s actual stockpile appears to have grown steadily, albeit at a slower rate than Russia or the US, and is forecasted to continue increasing. Russia\u2019s stockpile shows a large decrease from a previous peak, with a forecast that suggests stabilization or slight decline (Figure 5). Similarly, the global stockpile forecast indicates a non-linear decrease that appears to be a bit more accelerated than the past decade (Figure 4).
\nPerhaps a researcher with an interest in proliferation risk such as Scott Sagan may look at these proliferation plots with concern. The upward forecast for China might be seen as potentially destabilizing, particularly if it indicates a trend of other states following suit. Sagan would likely argue that these forecasts underscore the need for more robust non-proliferation efforts. He could also use the global forecast to argue that the potential for nuclear accidents or misuse grows as the number of nuclear weapons, even in spite of declining global stockpiles, remains substantial. In contrast, those with an interest in stability theory, such as Kenneth Waltz, may be of the view that the decline in global stockpiles, especially in the US and Russia, is indicative of a stabilizing balance of power. A Waltzian would posit that this balance would reduce the likelihood of nuclear war through deterrence. They might also see China\u2019s increasing stockpile not as a threat, but as a move toward a balance of power in Asia, which could deter conflicts in the region. Waltz may compel us to focus on the lack of relative scale; China\u2019s ever-increasing stockpile occurs at a scale hundreds of times inferior to that of the United States or Russia.<\/p>\n

This leads us to the environmental imperative: while progress in some areas is encouraging, the environmental costs of nuclear proliferation require urgent attention. To fully capitalize on this momentum, policymakers must integrate a commitment to sustainability into their disarmament strategies, and I believe their proposed policy solutions should offer avenues towards ensuring the longevity of disarmament gains while mitigating the environmental consequences of nuclear proliferation. Prioritizing green technologies within the existing nuclear sector acknowledges that complete and rapid abandonment of nuclear power may be unrealistic, as incentivizing innovation can lead to safer and more sustainable practices that reduce potential ecological harms. International cooperation rooted in environmental protection offers several advantages: joint research initiatives, collaborative waste management, and shared accountability reduce the environmental burden on any single nation. Moreover, such collaboration may enhance trust amongst states, strengthening the foundation for lasting disarmament agreements. Importantly, the push for renewable energy aligns nuclear disarmament with one of the most pressing global challenges of our time: climate change. Investing in clean energy simultaneously addresses energy security needs and combats the root causes of global instability that can incentivize some nations to pursue nuclear capabilities. Disarmament efforts cannot be separated from the broader sustainability agenda. A constructivist lens adds another layer to the analysis: the decline in nuclear testing and reductions in stockpile sizes post-Cold War can be partially attributed to the changing social norms and perceptions surrounding nuclear weapons. Policy efforts should continue to reinforce these evolving norms through education, diplomacy, and international condemnation of any proliferation activities. And in conjunction, it\u2019s important to note that while transitioning to a sustainable energy landscape, environmental justice must be prioritized. The move away from nuclear energy must not leave behind workers and communities dependent on the nuclear industry. Proactive programs focused on economic diversification and community development initiatives will be necessary to ameliorate any sort of socioeconomic impacts of this change. In the same vein, ensuring fairness during this shift will guarantee that the benefits of disarmament and environmental responsibility are shared equitably, building broader support for these vital long-term goals.<\/p>\n

In short, the historical data and future projections offer a nuanced picture of the global disarmament landscape. While progress has undoubtedly been made, the challenges of proliferation, security, and the environmental legacy of the nuclear age remain intrinsically linked. Effective policy solutions must embrace this complexity. Ultimately, by integrating disarmament, security, and environmental concerns, policymakers can effectively chart a course toward a safer world.<\/p>\n

V. CONCLUSION<\/p>\n

These forecasts underscore both the urgency of the challenge and the unique opportunity facing this generation. The decline in nuclear testing and reductions in some stockpiles offer a foundation for further progress, fueled by the momentum of transnational activism and shifting social norms. By embracing innovative policy solutions that integrate disarmament and non-proliferation, environmental protection, and equitable development, there\u2019s a feasible pathway to seize this moment and sustainably transform the global security landscape. The goal is not merely to manage the risks of nuclear weapons: the goal is to functionally create a world where they are obsolete.<\/p>\n<\/div>\n\n\n\n<\/div>\n\n\n <\/div><\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1036,"featured_media":1085,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[60,33],"tags":[],"class_list":["post-1090","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-avinash-chauhan","category-past-editor-blogs"],"acf":[],"yoast_head":"\nA Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development - Scribe\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/\" \/>\n<meta property=\"og:site_name\" content=\"Scribe\" \/>\n<meta property=\"article:published_time\" content=\"2024-10-13T15:49:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-24T15:51:01+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dornsife.usc.edu\/scribe\/wp-content\/uploads\/sites\/491\/2026\/04\/ashley_98-150x150-1.png\" \/>\n\t<meta property=\"og:image:width\" content=\"150\" \/>\n\t<meta property=\"og:image:height\" content=\"150\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Henry Mcquillan\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/\"},\"author\":{\"name\":\"Henry Mcquillan\",\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/#\\\/schema\\\/person\\\/85ae5955a9ba6bb5a1212b7144ce53d3\"},\"headline\":\"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development\",\"datePublished\":\"2024-10-13T15:49:00+00:00\",\"dateModified\":\"2026-04-24T15:51:01+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/\"},\"wordCount\":11,\"image\":{\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/wp-content\\\/uploads\\\/sites\\\/491\\\/2026\\\/04\\\/ashley_98-150x150-1.png\",\"articleSection\":[\"Avinash Chauhan\",\"Past Editor Blogs\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/\",\"url\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/\",\"name\":\"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development - Scribe\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/wp-content\\\/uploads\\\/sites\\\/491\\\/2026\\\/04\\\/ashley_98-150x150-1.png\",\"datePublished\":\"2024-10-13T15:49:00+00:00\",\"dateModified\":\"2026-04-24T15:51:01+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/#\\\/schema\\\/person\\\/85ae5955a9ba6bb5a1212b7144ce53d3\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/wp-content\\\/uploads\\\/sites\\\/491\\\/2026\\\/04\\\/ashley_98-150x150-1.png\",\"contentUrl\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/wp-content\\\/uploads\\\/sites\\\/491\\\/2026\\\/04\\\/ashley_98-150x150-1.png\",\"width\":150,\"height\":150},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/2024\\\/10\\\/13\\\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/#website\",\"url\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/\",\"name\":\"Scribe\",\"description\":\"USC Dornsife \",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/#\\\/schema\\\/person\\\/85ae5955a9ba6bb5a1212b7144ce53d3\",\"name\":\"Henry Mcquillan\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/96845f55fba7683656b8bbcb8a68b3c951a4e7abf7765d2478782dc73d20fd2b?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/96845f55fba7683656b8bbcb8a68b3c951a4e7abf7765d2478782dc73d20fd2b?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/96845f55fba7683656b8bbcb8a68b3c951a4e7abf7765d2478782dc73d20fd2b?s=96&d=mm&r=g\",\"caption\":\"Henry Mcquillan\"},\"url\":\"https:\\\/\\\/dornsife.usc.edu\\\/scribe\\\/author\\\/hmcquill\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/","og_locale":"en_US","og_type":"article","og_title":"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development - Scribe","og_url":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/","og_site_name":"Scribe","article_published_time":"2024-10-13T15:49:00+00:00","article_modified_time":"2026-04-24T15:51:01+00:00","og_image":[{"width":150,"height":150,"url":"https:\/\/dornsife.usc.edu\/scribe\/wp-content\/uploads\/sites\/491\/2026\/04\/ashley_98-150x150-1.png","type":"image\/png"}],"author":"Henry Mcquillan","twitter_card":"summary_large_image","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/#article","isPartOf":{"@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/"},"author":{"name":"Henry Mcquillan","@id":"https:\/\/dornsife.usc.edu\/scribe\/#\/schema\/person\/85ae5955a9ba6bb5a1212b7144ce53d3"},"headline":"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development","datePublished":"2024-10-13T15:49:00+00:00","dateModified":"2026-04-24T15:51:01+00:00","mainEntityOfPage":{"@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/"},"wordCount":11,"image":{"@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/#primaryimage"},"thumbnailUrl":"https:\/\/dornsife.usc.edu\/scribe\/wp-content\/uploads\/sites\/491\/2026\/04\/ashley_98-150x150-1.png","articleSection":["Avinash Chauhan","Past Editor Blogs"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/","url":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/","name":"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development - Scribe","isPartOf":{"@id":"https:\/\/dornsife.usc.edu\/scribe\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/#primaryimage"},"image":{"@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/#primaryimage"},"thumbnailUrl":"https:\/\/dornsife.usc.edu\/scribe\/wp-content\/uploads\/sites\/491\/2026\/04\/ashley_98-150x150-1.png","datePublished":"2024-10-13T15:49:00+00:00","dateModified":"2026-04-24T15:51:01+00:00","author":{"@id":"https:\/\/dornsife.usc.edu\/scribe\/#\/schema\/person\/85ae5955a9ba6bb5a1212b7144ce53d3"},"breadcrumb":{"@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/#primaryimage","url":"https:\/\/dornsife.usc.edu\/scribe\/wp-content\/uploads\/sites\/491\/2026\/04\/ashley_98-150x150-1.png","contentUrl":"https:\/\/dornsife.usc.edu\/scribe\/wp-content\/uploads\/sites\/491\/2026\/04\/ashley_98-150x150-1.png","width":150,"height":150},{"@type":"BreadcrumbList","@id":"https:\/\/dornsife.usc.edu\/scribe\/2024\/10\/13\/a-machine-learning-based-forecasting-approach-for-nuclear-proliferation-and-policy-development\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dornsife.usc.edu\/scribe\/"},{"@type":"ListItem","position":2,"name":"A Machine Learning-Based Forecasting Approach for Nuclear Proliferation and Policy Development"}]},{"@type":"WebSite","@id":"https:\/\/dornsife.usc.edu\/scribe\/#website","url":"https:\/\/dornsife.usc.edu\/scribe\/","name":"Scribe","description":"USC Dornsife ","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dornsife.usc.edu\/scribe\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/dornsife.usc.edu\/scribe\/#\/schema\/person\/85ae5955a9ba6bb5a1212b7144ce53d3","name":"Henry Mcquillan","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/96845f55fba7683656b8bbcb8a68b3c951a4e7abf7765d2478782dc73d20fd2b?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/96845f55fba7683656b8bbcb8a68b3c951a4e7abf7765d2478782dc73d20fd2b?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/96845f55fba7683656b8bbcb8a68b3c951a4e7abf7765d2478782dc73d20fd2b?s=96&d=mm&r=g","caption":"Henry Mcquillan"},"url":"https:\/\/dornsife.usc.edu\/scribe\/author\/hmcquill\/"}]}},"_links":{"self":[{"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/posts\/1090","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/users\/1036"}],"replies":[{"embeddable":true,"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/comments?post=1090"}],"version-history":[{"count":2,"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/posts\/1090\/revisions"}],"predecessor-version":[{"id":1092,"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/posts\/1090\/revisions\/1092"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/media\/1085"}],"wp:attachment":[{"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/media?parent=1090"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/categories?post=1090"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dornsife.usc.edu\/scribe\/wp-json\/wp\/v2\/tags?post=1090"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}