Research Article
Prognosticate the Analogous Region in Bangladesh Utilizing an Unsupervised Machine Learning Technique
Md. Habibur Rahman*
,
Humayra Sadia
Issue:
Volume 11, Issue 3, June 2025
Pages:
46-62
Received:
28 March 2025
Accepted:
20 May 2025
Published:
13 June 2025
DOI:
10.11648/j.ijdsa.20251103.11
Downloads:
Views:
Abstract: Climate regionalization provides valuable insights into the climatic challenges faced by a country, enabling better preparedness for climate change impacts and the development of targeted strategies. In this study, the climate regionalization of Bangladesh was performed based on nine climatic factors from 34 weather stations using unsupervised machine learning techniques. The exploratory data analysis was performed to assess the characteristics of the parameters, revealing distributional patterns. Principal Component Analysis (PCA) was then applied to reduce the dimensionality of the data and extract significant climate patterns. Following this, the non-hierarchical k-means clustering algorithm was used to group the locations into homogeneous clusters. The optimal number of clusters was determined using three widely recognized methods: the average silhouette score, the gap statistic, and the elbow method, before applying the clustering. While both the Silhouette Method and Gap statistic suggested three clusters, the elbow method identified nine clusters, which provided a more detailed regionalization. The locations Barisal, Jessore, Khepupara, Khulna, Mongla, Potuakhali, Satkhira from the south-west region form a significant cluster with Faridpur. The second largest cluster includes Bogra, Dinajpur, Ishurdi, Rajshahi, Rangpur, and Saidpur from the North-West region of Bangladesh. The findings of this study demonstrate that clustering offers a systematic approach to understanding the spatial distribution of climatic characteristics, facilitating informed decision making, resource allocation, and the development of policies tailored to the specific needs of different geographic regions in Bangladesh.
Abstract: Climate regionalization provides valuable insights into the climatic challenges faced by a country, enabling better preparedness for climate change impacts and the development of targeted strategies. In this study, the climate regionalization of Bangladesh was performed based on nine climatic factors from 34 weather stations using unsupervised mach...
Show More
Research Article
Modeling the Climate-Conflict-Migration Interplay in Sudan by Integrating GAMS and Spatio-Temporal Neural Networks
Ndegwa Ruth Wambui*,
Mwalili Samuel,
Wamwea Charity
Issue:
Volume 11, Issue 3, June 2025
Pages:
63-75
Received:
22 April 2025
Accepted:
7 May 2025
Published:
16 June 2025
DOI:
10.11648/j.ijdsa.20251103.12
Downloads:
Views:
Abstract: The ongoing humanitarian crises in Sudan, which are being exacerbated by escalating climate change, persistent conflict, and migratory waves, highlight the critical need for predictive, data-driven models to guide efficient response plans. In order to investigate and predict the intricate links between climate variability, conflict intensity, and migration patterns in Sudan at the subnational level, this study combines Spatio-Temporal Neural Networks (STNNs) with Generalized Additive Models (GAMs). The hybrid modeling framework provides strong insights into displacement patterns and conflict dynamics by capturing both spatial-temporal dependencies and nonlinear effects. GAMs showed a high positive correlation between conflict severity and precipitation levels, as well as statistically significant nonlinear relationships between food prices and relocation. In the meantime, the STNNs performed better than traditional modeling techniques, with R2 values of 0.89 and 0.84 for conflict intensity and regional displacement prediction, respectively. These excellent performance measures show how well the model captures real-world dynamics and provide a useful tool for humanitarian predictions. Prototype app for visualizing migration and conflict forecasts are included in the study, but they are still in the early stages of development. Future studies aim to improve operational utility and decision-making support in the field through real-time application. The results highlight how crucial it is for humanitarian research to combine machine learning and statistical modeling. This study offers practical insights that can enhance early warning systems, policymaking, and disaster preparedness in climate-vulnerable areas like Sudan by identifying important drivers of displacement and violence.
Abstract: The ongoing humanitarian crises in Sudan, which are being exacerbated by escalating climate change, persistent conflict, and migratory waves, highlight the critical need for predictive, data-driven models to guide efficient response plans. In order to investigate and predict the intricate links between climate variability, conflict intensity, and m...
Show More
