Scenario Projections Research Articles

Cost-Efficient Deployment Strategies: A Comparative Analysis of Feature Flagging Services and Blue/Green Deployments

Aims: This study provides a detailed comparison of two leading feature flagging services, LaunchDarkly and ConfigCat, and also examines the cost-efficiency and operational implications of using Blue/Green deployment strategies. It seeks to aid stakeholders in understanding the trade-offs and benefits of each approach to make informed decisions based on project-specific needs, budget constraints, and developmental objectives. Study Design: The study employs a comparative analysis framework, focusing on features, usability, scalability, architectural design, and the financial impacts of adopting feature flagging services versus Blue/Green deployment strategies. Place and Duration of Study: The analysis was conducted over a period of two years, encompassing a broad range of software development environments and project scenarios to ensure comprehensive coverage and relevance. Methodology: The methodology employed in this paper includes a detailed examination of LaunchDarkly and ConfigCat's service offerings, an evaluation of Blue/Green deployment strategies, and an analysis of cost-efficiency of each approach. The study synthesizes information from product documentation, user feedback, and performance metrics, alongside interviews with industry experts and case studies from diverse software development projects. Results: The results highlight the nuanced differences between feature flagging services in terms of scalability, ease of use, and the suitability for various project sizes. LaunchDarkly emerges as optimized for large-scale, complex projects due to its extensive feature set and scalability, while ConfigCat is favored for its simplicity and ease of use in smaller projects. The analysis also uncovers the cost benefits of feature flagging over Blue/Green deployments, emphasizing the savings on infrastructure and operational expenses while offering dynamic feature management capabilities. Conclusion: The study concludes that the choice between feature flagging services like LaunchDarkly and ConfigCat, and the utilization of Blue/Green deployment strategies, should be guided by specific project requirements, financial constraints, and desired operational efficiency. Feature flagging services provide a cost-effective, flexible solution for dynamic feature management, whereas Blue/Green deployments offer a straightforward, though potentially more resource-intensive, approach to minimizing deployment risks. This comparative analysis aims to assist stakeholders in selecting the most appropriate deployment strategy to meet their development goals efficiently.

Projected Changes in Mean and Extreme Precipitation over Northern Mexico

Abstract Northern Mexico is home to more than 32 million people and is of significant agricultural and economic importance for the country. The region includes three distinct hydroclimatic regions, all of which regularly experience severe dryness and flooding and are highly susceptible to future changes in precipitation. To date, little work has been done to characterize future trends in either mean or extreme precipitation over northern Mexico. To fill this gap, we investigate projected precipitation trends over the region in the NA-CORDEX ensemble of dynamically downscaled simulations. We first verify that these simulations accurately reproduce observed precipitation over northern Mexico, as derived from the Multi-Source Weighted-Ensemble Precipitation (MSWEP) product, demonstrating that the NA-CORDEX ensemble is appropriate for studying precipitation trends over the region. By the end of the century, simulations forced with a high-emissions scenario project that both mean and extreme precipitation will decrease to the west and increase to the east of the Sierra Madre highlands, decreasing the zonal gradient in precipitation. We also find that the North American monsoon, which is responsible for a substantial fraction of the precipitation over the region, is likely to start later and last approximately three weeks longer. The frequency of extreme precipitation events is expected to double throughout the region, exacerbating the flood risk for vulnerable communities in northern Mexico. Collectively, these results suggest that the extreme precipitation-related dangers that the region faces, such as flooding, will increase significantly by the end of the century, with implications for the agricultural sector, economy, and infrastructure. Significance Statement Northern Mexico regularly experiences severe flooding and its important agricultural sector can be heavily impacted by variations in precipitation. Using high-resolution climate model simulations that have been tested against observations, we find that these hydroclimate extremes are likely to be exacerbated in a warming climate; the dry (wet) season is projected to receive significantly less (more) precipitation (approximately ±10% by the end of the century). Simulations suggest that some of the changes in precipitation over the region can be related to the North American monsoon, with the monsoon starting later in the year and lasting several weeks longer. Our results also suggest that the frequency of extreme precipitation will increase, although this increase is smaller than that projected for other regions, with the strongest storms becoming 20% more frequent per degree of warming. These results suggest that this region may experience significant changes to its hydroclimate through the end of the century that will require significant resilience planning.

Inventory, Dynamic Evolution, and Scenario Projections of Agricultural Carbon Emissions in Shandong Province, China

The reduction in agricultural carbon emissions (ACEs) in Shandong Province is essential to China’s carbon peak and carbon neutrality objectives. In this regard, we constructed an ACE inventory for Shandong Province at a resolution of 1 km × 1 km, integrating the emission factor method with geographic information system (GIS) technology. Building upon this, we explored the dynamic evolution patterns of ACEs using kernel density estimation and conditional probability density estimation. Additionally, long short-term memory networks were trained to predict ACEs under various scenarios. The results showed that: (1) ACEs in Shandong Province exhibited two stages of change, i.e., “rise and decline”. Notably, 64.39% of emissions originated from the planting industry. The distribution of emissions was closely correlated with regional agricultural production modes. Specifically, CO2 emissions were predominantly distributed in crop cultivation areas, while CH4 and N2O emissions were primarily distributed in livestock breeding areas. The uncertainty of the emission inventory ranged from −12.04% to 10.74%, mainly caused by emission factors. (2) The ACE intensity of various cities in Shandong Province is decreasing, indicating a decoupling between ACEs and agricultural economic growth. Furthermore, the emission disparities among different cities are diminishing, although significant spatial non-equilibrium still persists. (3) From 2022 to 2030, the ACEs in Shandong Province will show a continuous downward trend. By 2030, the projected values under the baseline scenario, low-carbon scenario I, and low-carbon scenario II will be 6301.74 × 104 tons, 5980.67 × 104 tons, and 5850.56 × 104 tons. The low-carbon scenario reveals greater potential for ACE reduction while achieving efficient rural economic development and urbanization simultaneously. This study not only advances the methodology of the ACE inventory but also provides quantitative references and scientific bases for promoting low-carbon, efficient, and sustainable regional agriculture.

Assessment of plausible changes in Climatic Impact-Drivers relevant for the viticulture sector: A storyline approach with a climate service perspective

Under the pressing warming of climate, interpretable and useful-for-adaptation information has become a need in society and has promoted rapid methodological advances in climate science. One such advance is the development of the dynamical-storyline approach, with which the spread in multi-model scenario projections can be represented as a set of physically plausible scenarios (storylines) defined by (a) a global warming level and (b) changes in large-scale dynamical conditions that arise from climate forcing. Moreover, if changes in regional climate are assessed in such a way that they can clearly inform societal systems or management of natural ecosystems, they can potentially aid decision-making in a practical manner. Such is the aim of the climatic impact-driver (CID) framework, proposed in the Sixth Assessment Report (AR6) from the Intergovernmental Panel on Climate Change. Here, we combine the dynamical-storyline approach with the CID framework and apply them to climate services. We focus on CIDs associated with the viticulture sector and the region of the South American Andes, where currently both Argentina and Chile produce wine. We explain the benefits of this approach from a communication and adaptation perspective. In particular, we found that the CIDs related to seasonally aggregated temperatures are mainly dependent on the global warming level although in some regions, but they can also be sensitive to changes in dynamical conditions. Meanwhile, CIDs related to extreme temperature values and precipitation depend strongly on the dynamical response. We show how adaptation to climate-related compound risks can be informed by a storyline approach, given that they can address compound uncertainty in multiple locations, variables and seasons.

Urban growth scenario projection using heuristic cellular automata in arid areas considering the drought impact

Urban growth scenario projection using heuristic cellular automata in arid areas considering the drought impact

Improving project management skills by integrating a boardgame into educational paths

The increasing demand for practical project management skills makes crucial the adoption of innovative educational approaches. This study presents an experiment carefully designed to assess the effectiveness of an innovative project management educational boardgame named PMBoG. Two samples from a class of university students, enrolled in a bachelor's degree management course, participated in the experiment. One sample joined PMBoG sessions playing with and against other colleagues, the other sample did not participate in the sessions. After game sessions, both groups took a project management test to evaluate their capacity to make decisions or countermeasures based on classical project management issues. The test also included a questionnaire about game evaluations and peer feedback. Preliminary analysis using multiple statistical tests (t-test, ANOVA, Tuckey and Effect Size) indicates that participants in the experimental group demonstrated statistically significant higher performance compared to those who did not participate in the game sessions. The results suggest that the adoption of PMBoG positively impacts on increase of students' project management competencies. The study underscores the importance of incorporating experience-based and student-centered education tools in project management education, enhancing students' readiness for real-world project scenarios.

Variation in genomic vulnerability to climate change across temperate populations of eelgrass (Zostera marina)

AbstractA global decline in seagrass populations has led to renewed calls for their conservation as important providers of biogenic and foraging habitat, shoreline stabilization and carbon storage. Eelgrass (Zostera marina) occupies the largest geographic range among seagrass species spanning a commensurately broad spectrum of environmental conditions. In Canada, eelgrass is managed as a single phylogroup despite occurring across three oceans and a range of ocean temperatures and salinity gradients. Previous research has focused on applying relatively few markers to reveal population structure of eelgrass, whereas a whole‐genome approach is warranted to investigate cryptic structure among populations inhabiting different ocean basins and localized environmental conditions. We used a pooled whole‐genome re‐sequencing approach to characterize population structure, gene flow and environmental associations of 23 eelgrass populations ranging from the Northeast United States to Atlantic, subarctic and Pacific Canada. We identified over 500,000 SNPs, which when mapped to a chromosome‐level genome assembly revealed six broad clades of eelgrass across the study area, with pairwise FST ranging from 0 among neighbouring populations to 0.54 between Pacific and Atlantic coasts. Genetic diversity was highest in the Pacific and lowest in the subarctic, consistent with colonization of the Arctic and Atlantic oceans from the Pacific less than 300 kya. Using redundancy analyses and two climate change projection scenarios, we found that subarctic populations are predicted to be potentially more vulnerable to climate change through genomic offset predictions. Conservation planning in Canada should thus ensure that representative populations from each identified clade are included within a national network so that latent genetic diversity is protected, and gene flow is maintained. Northern populations, in particular, may require additional mitigation measures given their potential susceptibility to a rapidly changing climate.

Influence of New Parameterization Schemes on Arctic Sea Ice Simulation

Two coupled climate models that participated in the CMIP6 project (Coupled Model Intercomparison Project Phase 6), the Earth System Model of Chinese Academy of Sciences version 2 (CAS-ESM2-0), and the Nanjing University of Information Science and Technology Earth System Model version 3 (NESM3) were assessed in terms of the impact of four new sea ice parameterization schemes. These four new schemes are related to air–ice heat flux, radiation penetration and absorption, melt ponds, and ice–ocean flux, respectively. To evaluate the effectiveness of these schemes, key sea ice variables with and without these new schemes, such as sea ice concentration (SIC) and sea ice thickness (SIT), were compared against observation and reanalysis products from 1980 to 2014. The simulations followed the design of historical experiments within the CMIP6 framework. The results revealed that both models demonstrated improvements in simulating Arctic SIC and SIT when the new parameterization schemes were implemented. The model bias of SIC in some marginal sea ice zones of the Arctic was reduced, especially during March. The SIT was increased and the transpolar gradient of SIT was reproduced. The changes in spatial patterns of SIC and SIT after adding new schemes bear similarities between the two coupled models. This suggests that the new schemes have the potential for broad application in climate models for simulation and future climate scenario projection, especially for those with underestimated SIT.

Reversal of Projected European Summer Precipitation Decline in a Stabilizing Climate

AbstractPrecipitation projections in transient climate change scenarios have been extensively studied over multiple climate model generations. Although these simulations have also been used to make projections at specific Global Warming Levels (GWLs), dedicated simulations are more appropriate to study changes in a stabilizing climate. Here, we analyze precipitation projections in six multi‐century experiments with fixed atmospheric concentrations of greenhouse gases, conducted with the UK Earth System Model and which span a range of GWLs between 1.5 and 5°C of warming. Regions are identified where the sign of precipitation trends in high‐emission transient projections is reversed in the stabilization experiments. For example, stabilization reverses a summertime precipitation decline across Europe. This precipitation recovery occurs concurrently with changes in the pattern of Atlantic sea surface temperature trends due to a slow recovery of the Atlantic Meridional Overturning Circulation in the stabilization experiments, along with changes in humidity and atmospheric circulation.

Expected Changes in Heating and Cooling Degree Days over Greece in the near Future Based on Climate Scenarios Projections

The change in heating and cooling needs of Greece in the near future due to the climate change is assessed in the present study. Global and regional climate models and two different representative concentration pathways (RCPs) are used to simulate the expected change in temperature. A widely used methodology of computation of heating degree days (HDDs) and cooling degree days (CDDs) is employed with a base temperature of 18 °C. In agreement with the expected temperature rise in the near future, an HDD decrease and CDD increase under both RCPs is also expected. The changes under RCP8.5 are stronger compared to those under RCP4.5. Differences related to topography are noted. The HDD decrease is stronger than CDD increase but the relative increase in CDDs is higher than the relative increase in HDDs. The highest absolute decreases in HDDs are expected for February and March while the highest absolute increases in CDDs are expected during the three summer months.

Data-driven mechanistic framework with stratified immunity and effective transmissibility for COVID-19 scenario projections

Scenario-based modeling frameworks have been widely used to support policy-making at state and federal levels in the United States during the COVID-19 response. While custom-built models can be used to support one-off studies, sustained updates to projections under changing pandemic conditions requires a robust, integrated, and adaptive framework. In this paper, we describe one such framework, UVA-adaptive, that was built to support the CDC-aligned Scenario Modeling Hub (SMH) across multiple rounds, as well as weekly/biweekly projections to Virginia Department of Health (VDH) and US Department of Defense during the COVID-19 response. Building upon an existing metapopulation framework, PatchSim, UVA-adaptive uses a calibration mechanism relying on adjustable effective transmissibility as a basis for scenario definition while also incorporating real-time datasets on case incidence, seroprevalence, variant characteristics, and vaccine uptake. Through the pandemic, our framework evolved by incorporating available data sources and was extended to capture complexities of multiple strains and heterogeneous immunity of the population. Here we present the version of the model that was used for the recent projections for SMH and VDH, describe the calibration and projection framework, and demonstrate that the calibrated transmissibility correlates with the evolution of the pathogen as well as associated societal dynamics.

An empirical study of just-in-time-defect prediction using various machine learning techniques

The goal of defect specificity is to pinpoint defective program components (such as faulty files, problematic procedures, or troublesome lines of code) based on defect symptoms, such as event logs or program spectrum. However, the problem is revealed and adverse effects are introduced when one experiences the defect indications. Consequently, one difficult task is to determine whether one can find buggy program before the signs of the defect manifests itself. Just-in-time defect prediction (JIT-DP) is a particular category of Software Defect Prediction (SDP) that includes this type of early detection of flawed changes to a software programs. This paper presents a novel five-phase JIT-DP framework that classifies the newly committed change as either a buggy change or a clean change relying on the project's historical data regarding the executed changes. The distinctive aspect of the model is that it uses the Chunk Balancing Algorithm (CBA) as a novel way of handling the Class Imbalance Problem (CIP) rather than utilizing conventional data re-sampling techniques. The experimental study uses 10 open-source projects with an average of 23,989 modifications to train the JIT-DP model. The research study examines the JIT-DP model's prediction abilities from both Within Project (WP) and Cross Project (CP) scenarios. The findings show that for within project setup, Logistic Regression (LR) outperforms among all other classifiers with the highest accuracy, TPR, and FPR as 0.85, 0.847, and 0.207, respectively. The model provides comparable prediction findings with an average accuracy of 0.90 for all seven testing samples when it was trained using commit logs from related six Java projects under CP context. However, taking into account the larger training pool of commit records in the former scenario, the model in the CP context (3.740 s) lags behind in terms of training and classification time periods when compared to the results of WI (0.984 s).

Hydro-sediment responses to management options under current and future climate change scenarios in Maybar watershed, South Wollo Zone, Ethiopia

Climate change coupled with inappropriate land use management is a serious environmental challenge in the highland part of Ethiopia. The aim of this study was to investigate hydro-sediment responses to management options under current and future climate change scenarios in Maybar watershed, Northern Ethiopia. We employed soil and water assessment tool (ArcSWAT 2012.10_7.24) for hydrologic modeling and CORDEX-climate data under RCP 4.5 and RCP 8.5 emission scenarios for climate projections. Soil map was prepared by digitizing soil characterization map of the watershed generated by Weigel in 1986. DEM data with 2 m spatial resolution was obtained from water and land resource center and land use classification was done through digitization of google earth images. Better agreement between calibrated SWAT simulation and observed variables was achieved. Delta change bias correction method was employed to improve the climate simulation in reproducing the observed climate variables. We found a considerable increase in annual precipitation by 18.71 % and 22.33 % for RCP 4.5 and RCP 8.5, respectively compared with the current climate conditions. Climate change induced hydro-sediment results were observed to be consistent with predicted precipitation. Under the current climatic conditions, average sediment yield at the sub-basin scale varies from negligible (under terrace complementation) to approximately more than 50 t ha−1 yr−1 with a basin average of 32 t ha−1 yr−1 (under no-terrace conditions). The implementation of management alternatives gets the dry season's hydrological behavior of the catchment improved and climate change induced sediment yield reduction. Generally, the information could possibly support decision makers and planners to implement best-fitted management options and thereby reduce current and expected aggressive sediment loss situations.

The Scenario Approach of the Country Investment Policy in the Conditions of Globalization

Considering the particularities of economic development, countries should cooperate and participate in joint projects within regional and international groupings. The paper aims to develop a scenario approach to the investment policy of countries in the context of globalization. Defines how important the investment component of a country's economic development is and justifies why countries are heterogeneous regarding investment attractiveness. To fulfil the main goal the author applies the capital asset pricing model, which is a basic concept in the field of finance. In addition to the main goal, the text of the article systematizes the stages of development of the organizational project scenario, justifies the role of foreign investments in economic development, and analyses world trends regarding changes in the attractiveness of investments. The paper estimates how attractive national economies are for foreign investments as well.

Effects of Climate Change on the Distribution of Prosthechea mariae (Orchidaceae) and within Protected Areas in Mexico.

The impact of climate change on the distribution of native species in the Neotropics remains uncertain for most species. Prosthechea mariae is an endemic epiphytic orchid in Mexico, categorized as threatened. The objective of this study was to assess the effect of climate change on the natural distribution of P. mariae and the capacity of protected areas (PAs) to safeguard optimal environmental conditions for the species in the future. Historical records were obtained from herbaria collections and through field surveys. We utilized climate variables from WorldClim for the baseline scenario and for the 2050 period, using the general circulation models CCSM4 and CNRM-CM5 (RCP 4.5). Three sets of climate data were created for the distribution models, and multiple models were evaluated using the kuenm package. We found that the species is restricted to the eastern region of the country. The projections of future scenarios predict not only a substantial reduction in habitat but also an increase in habitat fragmentation. Ten PAs were found within the current distribution area of the species; in the future, the species could lose between 36% and 48% of its available habitat within these PAs. The results allowed for the identification of locations where climate change will have the most severe effects, and proposals for long-term conservation are addressed.

Enhancing seasonal influenza projections: A mechanistic metapopulation model for long-term scenario planning

In temperate regions, annual preparation by public health officials for seasonal influenza requires early-season long-term projections. These projections are different from short-term (e.g., 1–4 weeks ahead) forecasts that are typically updated weekly. Whereas short-term forecasts estimate what “will” likely happen in the near term, the goal of scenario projections is to guide long-term decision-making using “what if” scenarios. We developed a mechanistic metapopulation model and used it to provide long-term influenza projections to the Flu Scenario Modeling Hub. The scenarios differed in their assumptions about influenza vaccine effectiveness and prior immunity. The parameters of the model were inferred from early season hospitalization data and then simulated forward in time until June 3, 2023. We submitted two rounds of projections (mid-November and early December), with the second round being a repeat of the first with three more weeks of data (and consequently different model parameters). In this study, we describe the model, its calibration, and projections targets. The scenario projection outcomes for two rounds are compared with each other at state and national level reported daily hospitalizations. We show that although Rounds 2 and 3 were identical in definition, the addition of three weeks of data produced an improvement to model fits. These changes resulted in earlier projections for peak incidence, lower projections for peak magnitude and relatively small changes to cumulative projections. In both rounds, all four scenarios presented conceivable outcomes, with some scenarios agreeing well with observations. We discuss how to interpret this agreement, emphasizing that this does not imply that one scenario or another provides the ground truth. Our model's performance suggests that its underlying assumptions provided plausible bounds for what could happen during an influenza season following two seasons of low circulation. We suggest that such projections would provide actionable estimates for public health officials.

A multiscale modeling framework for Scenario Modeling: Characterizing the heterogeneity of the COVID-19 epidemic in the US

The Scenario Modeling Hub (SMH) initiative provides projections of potential epidemic scenarios in the United States (US) by using a multi-model approach. Our contribution to the SMH is generated by a multiscale model that combines the global epidemic metapopulation modeling approach (GLEAM) with a local epidemic and mobility model of the US (LEAM-US), first introduced here. The LEAM-US model consists of 3142 subpopulations each representing a single county across the 50 US states and the District of Columbia, enabling us to project state and national trajectories of COVID-19 cases, hospitalizations, and deaths under different epidemic scenarios. The model is age-structured, and multi-strain. It integrates data on vaccine administration, human mobility, and non-pharmaceutical interventions. The model contributed to all 17 rounds of the SMH, and allows for the mechanistic characterization of the spatio-temporal heterogeneities observed during the COVID-19 pandemic. Here we describe the mathematical and computational structure of our model, and present the results concerning the emergence of the SARS-CoV-2 Alpha variant (lineage designation B.1.1.7) as a case study. Our findings show considerable spatial and temporal heterogeneity in the introduction and diffusion of the Alpha variant, both at the level of individual states and combined statistical areas, as it competes against the ancestral lineage. We discuss the key factors driving the time required for the Alpha variant to rise to dominance within a population, and quantify the impact that the emergence of the Alpha variant had on the effective reproduction number at the state level. Overall, we show that our multiscale modeling approach is able to capture the complexity and heterogeneity of the COVID-19 pandemic response in the US.

FlepiMoP: The evolution of a flexible infectious disease modeling pipeline during the COVID-19 pandemic

The COVID-19 pandemic led to an unprecedented demand for projections of disease burden and healthcare utilization under scenarios ranging from unmitigated spread to strict social distancing policies. In response, members of the Johns Hopkins Infectious Disease Dynamics Group developed flepiMoP (formerly called the COVID Scenario Modeling Pipeline), a comprehensive open-source software pipeline designed for creating and simulating compartmental models of infectious disease transmission and inferring parameters through these models. The framework has been used extensively to produce short-term forecasts and longer-term scenario projections of COVID-19 at the state and county level in the US, for COVID-19 in other countries at various geographic scales, and more recently for seasonal influenza. In this paper, we highlight how the flepiMoP has evolved throughout the COVID-19 pandemic to address changing epidemiological dynamics, new interventions, and shifts in policy-relevant model outputs. As the framework has reached a mature state, we provide a detailed overview of flepiMoP’s key features and remaining limitations, thereby distributing flepiMoP and its documentation as a flexible and powerful tool for researchers and public health professionals to rapidly build and deploy large-scale complex infectious disease models for any pathogen and demographic setup.

Amplified Extreme Floods and Shifting Flood Mechanisms in the Delaware River Basin in Future Climates

AbstractHistorical records in the Delaware River Basin reveal complex and spatially diverse flood generating mechanisms influenced by the region's mountains‐to‐plains gradients. This study focuses on predicting future flood hazards and understanding the underlying drivers of changes across the region. Using a process‐based hydrological model, we analyzed the hydrometeorological condition of each historical and future flood event. For each event, at the subbasin scale, we identified the dominant flood generating mechanism, including snowmelt, rain‐on‐snow, short‐duration rain, and long‐duration rain. The rain‐induced floods are further categorized based on the soil's Antecedent Moisture Condition (AMC) before the event, whether dry, normal, or wet. Our historical analysis suggests that rain‐on‐snow is the primary flood mechanism of the Upper Basin. Although most frequent, the magnitude of rain‐on‐snow floods is often less severe than short rain floods. In contrast, historical floods in the Lower Basin are primarily caused by short rain under normal AMC. Given the uncertainties in climate projections, we used an ensemble of future climate scenarios for flood projections. Despite variations in regional climate projections, coherent perspectives emerge: the region will shift toward a warmer, wetter climate, with a projected intensification of extreme floods. The Upper Basin is projected to experience a marked decrease in rain‐on‐snow floods, but a substantial increase in short rain floods with wet AMC. The largest increase in flood magnitude will be driven by short rains with wet AMC in the Upper Basin and by short rains with normal AMC in the Lower Basin.

Enhancing clay content estimation through hybrid CatBoost-GP with model class selection

Excessive soil swelling, triggered by variations in moisture content, is recognized as one of the most severe geo-hazards. Swelling Potential (SP) is closely correlated with Clay Content (CC), Plasticity Index (PI), and Activity (A = PI/CC), which are crucial input features for SP prediction models. Traditional methods for determining CC, such as the hydrometer and pipette methods, are labor-intensive and time-consuming. Employing easily accessible soil properties to predict CC directly not only enhances the modeling efficiency of SP prediction models but also mitigates the impact of laboratory test errors on model performance. This study leveraged two databases encompassing a broad spectrum of soil classifications and developed three ensemble learning models (RF, XGBoost, and CatBoost) to predict CC efficiently. Sequential model-based optimization algorithms (SMBO) were employed to effectively identify the optimal hyperparameters for these models. To further refine the model, the Shapley additive explanation (SHAP) method was utilized to ascertain the most influential soil properties. The findings revealed that the CatBoost model, optimized via GP, achieved the highest level of predictive accuracy. Three easily measurable soil properties — the percentage of soil particles passing through 0.075 mm and 0.425 mm sieves, along with the plasticity index — were identified as key predictors for CC. The estimated CC values were instrumental in constructing various empirical and machine learning models to predict SP, all of which exhibited exceptional performance. This research advances the modeling efficiency of SP prediction models, making it particularly relevant for rapid-response scenarios in transportation infrastructure projects.