Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wondesen Teshome Bekele has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SMT-HCSD: stochastic multi-target hard-constrained spatial deep learning framework and architecture for perfect prognosis CMIP6 daily temperature downscaling

    by Wondesen Teshome Bekele, Marco D’ORia

    High-resolution projections of daily temperature extremes are essential for climate-resilient development and informed regional adaptation planning. However, conventional statistical downscaling methods often overlook inherent stochasticity and physical consistency. To address these limitations, we introduce SMT‑HCSD (Stochastic Multi‑Target Hard‑Constrained Spatial Deep Learning), a perfect‑prognosis framework and architecture that simultaneously predicts minimum and maximum temperature, providing probabilistic, uncertainty‑aware, and physically consistent projections. SMT‑HCSD achieves this by training a single model on both targets and applying a hard constraint to ensure Tmin $$\:\le\:$$ Tmax. Validation against historical observations demonstrates that the framework and architecture accurately reproduce the seasonal cycle, spatial distribution, and extremes of daily temperature. We applied SMT‑HCSD to downscale three CMIP6 global models (MPI-ESM1-2-HR, NorESM2-MM, and MRI-ESM2-0) over the Emilia-Romagna region (Italy) under both low (SSP1-2.6) and high (SSP3-7.0) emission scenarios. By integrating probabilistic modelling, physical constraints, and multi-target learning, SMT-HCSD advances statistical downscaling and produces actionable, reliable high-resolution climate information. The results underscore both the urgency of global emissions reductions and the need for regionally tailored adaptation and resilience strategies in Emilia-Romagna. SMT‑HCSD thus provides a robust and transparent basis for proactive climate policy and risk management.

  • Open Access

    Machine learning algorithms for predicting low birth weight in Ethiopia

    by Wondesen Teshome Bekele

    Background: Birth weight is a significant determinant of the likelihood of survival of an infant. Babies born at low birth weight are 25 times more likely to die than at normal birth weight. Low birth weight (LBW) affects one out of every seven newborns, accounting for about 14.6 percent of the babies born worldwide. Moreover, the prevalence of LBW varies substantially by region, with 7.2 per cent in the developed regions and 13.7 per cent in Africa, respectively. Ethiopia has a large burden of LBW, around half of Africa. These newborns were more likely to die within the first month of birth or to have long-term implications. These are stunted growth, low IQ, overweight or obesity, developing heart disease, diabetes, and early death. Therefore, the ability to predict the LBW is the better preventive measure and indicator of infant health risks. Method: This study implemented predictive LBW models based on the data obtained from the Ethiopia Demographic and Health Survey 2016. This study was employed to compare and identify the best-suited classifier for predictive classification among Logistic Regression, Decision Tree, Naive Bayes, K-Nearest Neighbor, Random Forest (RF), Support Vector Machine, Gradient Boosting, and Extreme Gradient Boosting. Results: Data preprocessing is conducted, including data cleaning. The Normal and LBW are the binary target category in this study. The study reveals that RF was the best classifier and predicts LBW with 91.60 percent accuracy, 91.60 percent Recall, 96.80 percent ROC-AUC, 91.60 percent F1 Score, 1.05 percent Hamming loss, and 81.86 percent Jaccard score. Conclusion: The RF predicted the occurrence of LBW more accurately and effectively than other classifiers in Ethiopia Demographic Health Survey. Gender of the child, marriage to birth interval, mother’s occupation and mother’s age were Ethiopia’s top four critical predictors of low birth weight in Ethiopia.


  • Open Access

    Predictors of Community-Based Health Insurance in Ethiopia via Multilevel Mixed-Effects Modelling: Evidence from the 2019 Ethiopia Mini Demography and Health Survey

    by Wondesen Teshome Bekele

    Background: The World Health Organization has endorsed a community-based health insurance scheme (CBHIS) as a shared financing plan to improve access to health services and ensure universal coverage of the healthcare delivery system. Such a contributory scheme is the most likely option to provide health insurance coverage when governments cannot offer direct health care support. Despite improvements in access to current healthcare services, Ethiopia’s healthcare delivery remained low, owing to the country’s underdeveloped healthcare finance system. As a result, the present study assessed CBHIS coverage and its predictors in Ethiopia at the individual and community level. Methods: The availability of CBHIS was checked via a criterion: at least one of the cluster respondents had to be enrolled in CBHIS. This study was based on secondary data from the Ethiopia Mini Demography and Health Survey (EMDHS) 2019 and included 7724 respondents. The study population was described using percentage and frequency. Four multilevel mixed-effects logistic regression modelling stages were performed to control for variations due to heterogeneity across clusters, and determinant predictors of CBHIS enrollment were outplayed. Results: The prevalence of CBHIS enrollment in Ethiopia was 33.13%. Rural residents were 3.218 times (AOR = 3.218; 95% CI: 1.521, 6.809), male household heads were 1.574 times (AOR = 1.574, 95% CI: 1.105, 2.241), getting funds from the safety net program were times 2.062 (AOR = 2.062, 95% CI: 1.297, 3.279), attending the primary educational level was 1.686 times (AOR = 1.686, 95% CI: 1.007, 2.821), bank accounts were 1.373 times (AOR = 1.373, 95% CI: 1.052, 1.792), and wealth index was 1.356 times (AOR = 1.356, 95% CI: 1.001, 1.838) more likely associated with CBHIS coverage, whereas the regions, the other religions, and women aged 20– 24 had lower odds of CBHIS coverage. Conclusion: In Ethiopia, regional healthcare expenditure per capital, religious affiliation, women age range, residents, sex of household head, funds from the safety net program, formal educational level, and having bank accounts were associated with community-based health insurance scheme coverage.


  • Open Access

    The knowledge and practice towards COVID-19 pandemic prevention among residents of Ethiopia. An online cross-sectional study

    by Daniel Bekele, Tadesse Tolossa, Reta Tsegaye, Wondesen Teshome

    Background: The disease from the novel coronavirus (COVID-19) has been considered as an international concern and a pandemic starting from the declaration of the World Health Organization (WHO) as an outbreak disease. Objective: The objective of this study is to assess the prevention of knowledge and practices towards the COVID-19 pandemic among the residents of Ethiopia. Methods: An online cross-sectional study was conducted among a sample of Ethiopian residents via social platforms of the author’s network with popular social media such as Facebook, Telegram, and email. The snowball sampling was employed to recruit participants. In doing so, we collected the responses of 341 participants successfully from April 15 to 22, 2020. The collected data were analyzed by STATA version 14 software and descriptive statistics were employed to summarize the knowledge and practices of the community towards the COVID-19 pandemic. Results: The majority of respondents 80.5% were male. About 91.2% of the participants heard about the COVID-19 pandemic. Moreover, out of 341 participants 90.0%, 93.8% of them knew that the COVID-19 pandemic was prevented by maintaining social distance and frequent handwashing, respectively. This shows that the prevention knowledge of the participants towards the COVID-19 by maintaining social distance and frequent handwashing was high. However, out of 341 participants only 61%,84% of them practiced social distance and frequent handwashing toward COVID-19, respectively. Conclusions: The majority of the participants knew the ways to protect themselves from the novel coronavirus (COVID-19), but there was a great problem of changing this prevention knowledge to practices. This shows that there is an action gap between having prevention knowledge of the COVID-19 and implementing it into practices to tackle the spread of the COVID-19 among communities. Therefore, the concerned body should be focused on providing awareness and education for the community regarding the implementation of prevention knowledge to practices.


  • Open Access

    The knowledge and practice towards COVID-19 pandemic prevention among residents of Ethiopia: An Online Cross-Sectional Study

    by Daniel Bekele, Tadesse Tolossa, Reta Tsegaye, Wondesen Teshome

    Background: The Novel coronavirus disease-2019 (COVID-19) is now the international concerns and a pandemic, since the World Health Organization declared as the outbreaks. The objective of this study to assess the prevention knowledge and practices towards the COVID-19 among the residents of Ethiopia. Methods: An online cross-sectional study was conducted among the sample of Ethiopian residents via social platforms of the author’s network with the popular media such as Facebook, in Ethiopia from the April 15-22, 2020 and successfully recruited 341 responses. The snowball sampling was employed to recruit the participants. The data were analyzed using STATA version 14. Descriptive statistics were used to summarize the level of knowledge and practices. Results: The majority of the respondents (80.35%) were male. The overall prevention knowledge of the participants towards the novel coronavirus (COVID-19) was high. About 91.2% of the participant was heard about the novel coronavirus disease and Social Medias’ were the main source of the information. About 90% of the participants had a good prevention knowledge of maintaining social distance and frequent hand washing. The practices of the participants towards the COVID-19 prevention were very low. Out of 341 participants, only 61% and 84% of the participants were practicing social distance and frequent hand washing, respectively. Conclusions: Majority of the participants had knew the ways of protecting themselves from the novel coronavirus. But, there was deficiencies of changing these prevention knowledge to practice. This indicates that there was gap between knowledge and implementation of prevention strategies in the community. The concerned body should focus on providing education for the community regarding the implementation of the prevention knowledge to practice.