Nur Alvira Pascawati
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Nur Alvira Pascawati has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Tri Baskoro Tunggul Satoto
Department of Parasitology, Faculty of Medicine, Public Health, and Nursing, Universitas Gadjah Mada, Yogyakarta, Indonesia.
2 shared publications Dea Putri Ramadanti
Universitas Respati Yogyakarta
1 shared publicationElisabeth Deta Lusiyati
Universitas Respati Yogyakarta
1 shared publicationJati Untari
Universitas Respati Yogyakarta
1 shared publicationMarko Ferdian Salim
Department of Health Information and Services, Vocational College, Universitas Gadjah Mada, Yogyakarta, Indonesia
1 shared publicationRoger Frutos
Intertryp, UMR17, CIRAD, Montpellier, France
1 shared publication
Latest Publications
- Open Access
- 4 May 2026
- Published by Springer Nature in BMC Infectious Diseases
- Vol. 26
AI-based prediction of dengue incidence using climatic, environmental, and socio-demographic factors: an ensemble random forest approach with agile system development
Background: Dengue transmission in Indonesia is shaped by interacting climatic, environmental, and socio-demographic factors, yet most forecasting systems remain static and vulnerable to data shifts. There is a critical need for adaptive, data-driven early-warning frameworks that integrate multiple predictor domains while preventing methodological biases such as information leakage. This study aimed to develop a Random Forest (RF)–based predictive model embedded within an Agile System Development workflow to forecast monthly dengue case counts in Yogyakarta. Methods: Monthly dengue case counts from five districts (2017–2022) were modeled using multi-domain predictors. All preprocessing steps—including imputation, standardization, correlation screening, VIF diagnostics, and Negative Binomial GLM–based feature screening—were performed exclusively on the 2017–2021 training subset, with parameters applied unchanged to the 2022 test set. The GLM served solely as a leakage-free exploratory screening tool. A Random Forest model was trained using optimized hyperparameters (500 trees, max depth 10) and evaluated through temporal testing. Model reliability was assessed using calibration curves, prediction-interval metrics, and a one-month early-warning classification evaluated with sensitivity, specificity, PPV, and NPV. Results: The RF model achieved strong predictive performance (R² = 0.86; RMSE = 5.72), exceeding the GLM benchmark (R² = 0.64). Rainfall lag-1, temperature, and humidity emerged as dominant predictors, complemented by built-up area and population density. Calibration indicated good agreement across routine transmission ranges, with reduced reliability during outbreak peaks. The early-warning component demonstrated high sensitivity (0.82) and strong negative predictive value (0.86), supporting its use as a decision-support indicator of elevated transmission risk. Conclusion: The proposed Agile–AI framework demonstrates the potential to deliver accurate dengue risk predictions with interpretable uncertainty estimates within a flexible, multi-domain early-warning architecture. While external validation and further refinement are required, the framework offers a scalable foundation for adaptive dengue surveillance and targeted vector-control decision support in dynamic tropical settings.
- 4 May 2026
- Published by Springer Nature in BMC Infectious Diseases
- Vol. 26
Open AccessAI-based prediction of dengue incidence using climatic, environmental, and socio-demographic factors: an ensemble random forest approach with agile system development
Background: Dengue transmission in Indonesia is shaped by interacting climatic, environmental, and socio-demographic factors, yet most forecasting systems remain static and vulnerable to data shifts. There is a critical need for adaptive, data-driven early-warning frameworks that integrate multiple predictor domains while preventing methodological biases such as information leakage. This study aimed to develop a Random Forest (RF)–based predictive model embedded within an Agile System Development workflow to forecast monthly dengue case counts in Yogyakarta. Methods: Monthly dengue case counts from five districts (2017–2022) were modeled using multi-domain predictors. All preprocessing steps—including imputation, standardization, correlation screening, VIF diagnostics, and Negative Binomial GLM–based feature screening—were performed exclusively on the 2017–2021 training subset, with parameters applied unchanged to the 2022 test set. The GLM served solely as a leakage-free exploratory screening tool. A Random Forest model was trained using optimized hyperparameters (500 trees, max depth 10) and evaluated through temporal testing. Model reliability was assessed using calibration curves, prediction-interval metrics, and a one-month early-warning classification evaluated with sensitivity, specificity, PPV, and NPV. Results: The RF model achieved strong predictive performance (R² = 0.86; RMSE = 5.72), exceeding the GLM benchmark (R² = 0.64). Rainfall lag-1, temperature, and humidity emerged as dominant predictors, complemented by built-up area and population density. Calibration indicated good agreement across routine transmission ranges, with reduced reliability during outbreak peaks. The early-warning component demonstrated high sensitivity (0.82) and strong negative predictive value (0.86), supporting its use as a decision-support indicator of elevated transmission risk. Conclusion: The proposed Agile–AI framework demonstrates the potential to deliver accurate dengue risk predictions with interpretable uncertainty estimates within a flexible, multi-domain early-warning architecture. While external validation and further refinement are required, the framework offers a scalable foundation for adaptive dengue surveillance and targeted vector-control decision support in dynamic tropical settings.
- Open Access
- 22 June 2023
- Published by Universitas Ahmad Dahlan in Disease Prevention and Public Health Journal
- Vol. 17 (2) , 149-161
University Readiness Analysis Towards Green Campus: A Case Study Using UI GreenMetric
Background: Global warming is a problem that attracts the world's attention because of its harmful effects on living things, including in Indonesia. One of the efforts made by the government is to invite universities to play an active role in reducing the impact of global warming through the green campus program. This study aims to analyze the university's readiness for a Green Campus through a case study at Universitas Respati Yogyakarta (UNRIYO). Method: This research uses a descriptive-quantitative method with case studies at Campus 2 UNRIYO. The population is the entire academic community, infrastructure, transportation, and guidelines that are by the Green Campus indicator. Instruments and data analysis using guidelines from UI GreenMetric with observational variables consisting of 6 indicators, namely Setting & Infrastructure (SI), Energy and Climate Change (EC), Waste (WS), Water (WR), Transportation (TR), and Education & Research (ED). Results: The results of the assessment show that UNRIYO on the SI indicator is at a score of 350 (readiness level 23.3%), EC score of 725 (34.5%), WS score of 450 (25% readiness level), TR score of 0, ED score of 425 (19.4% readiness level). Conclusion: These results indicate that UNRIYO is at a level that is less ready to implement Green Campus. The obstacles experienced are: 1) The supervisory function is still weak so the implementation of the green campus is not sustainable. 2) Incompatibility of infrastructure to realize smart building. 3) There is no sanction and appreciation for the practice of Green Campus. 4) Weak only policy support to create a sustainable environment. 5) Less massive Green Campus socialization, 8) Limited human resources in integrating scientific competence with tri dharma towards Green Campus.
- 22 June 2023
- Published by Universitas Ahmad Dahlan in Disease Prevention and Public Health Journal
- Vol. 17 (2) , 149-161
Open AccessUniversity Readiness Analysis Towards Green Campus: A Case Study Using UI GreenMetric
Background: Global warming is a problem that attracts the world's attention because of its harmful effects on living things, including in Indonesia. One of the efforts made by the government is to invite universities to play an active role in reducing the impact of global warming through the green campus program. This study aims to analyze the university's readiness for a Green Campus through a case study at Universitas Respati Yogyakarta (UNRIYO). Method: This research uses a descriptive-quantitative method with case studies at Campus 2 UNRIYO. The population is the entire academic community, infrastructure, transportation, and guidelines that are by the Green Campus indicator. Instruments and data analysis using guidelines from UI GreenMetric with observational variables consisting of 6 indicators, namely Setting & Infrastructure (SI), Energy and Climate Change (EC), Waste (WS), Water (WR), Transportation (TR), and Education & Research (ED). Results: The results of the assessment show that UNRIYO on the SI indicator is at a score of 350 (readiness level 23.3%), EC score of 725 (34.5%), WS score of 450 (25% readiness level), TR score of 0, ED score of 425 (19.4% readiness level). Conclusion: These results indicate that UNRIYO is at a level that is less ready to implement Green Campus. The obstacles experienced are: 1) The supervisory function is still weak so the implementation of the green campus is not sustainable. 2) Incompatibility of infrastructure to realize smart building. 3) There is no sanction and appreciation for the practice of Green Campus. 4) Weak only policy support to create a sustainable environment. 5) Less massive Green Campus socialization, 8) Limited human resources in integrating scientific competence with tri dharma towards Green Campus.
- Open Access
- 13 March 2023
- Published by Research Synergy Foundation in Rsf Conference Proceeding Series: Medical and Health Science
- Vol. 2 (1) , 102-113
Portable Device for Aedes Sp Larva Suction with Mechanical Electric Methods: Innovation in Control of DHF Disease
Controlling Aedes Sp larvae is an essential component in the Integrated Mosquito Management (IMM) program because when mosquitoes are removed before they become adults, there will be no transmission of vector-borne diseases, especially DHF. However, physical, chemical, and biological control is still not optimal because it is considered resistant, less sensitive, effective, and efficient, especially in scarce clean water. The research aims to make and test the effectiveness of the innovative portable Aedes Sp larvae sucker using the electric-mechanical method. This type of research is an actual experiment in the laboratory test stage and quasi-experimental in the field test. This innovation is a pump with a suction power of 1400 litres/hour and 1800 litres/hour equipped with an AC electric motor connected to an inverter circuit. On the laboratory scale, it was tested on 1,500 instars III and IV Aedes aegypti larvae, and on a field scale, it was tested on 45 containers in Endemic Village, Klaten Regency. Data analysis used the Pearson Correlation, independent sample, and Cochran tests. Laboratory test results showed that the time to catch all Aedes Sp larvae in containers with a volume of 80 litres and 90 litres using a power of 1400 litres/hour took 60 seconds and 138 seconds, while with a power of 1800 litres/hour, it took 33 seconds and 110 seconds. The speed of the number of Aedes Sp larvae caught is affected by the volume of water >=20 litres with a water level of > 8 cm. This tool was tested in the community at 43 houses and 45 positive larvae containers. The result show that with a power of 1800 litres/second, the time needed to suck the larvae in a bathtub-type container with a volume of 80-85 litres is 122.14 seconds, while a container with a volume of 86-90 litres is 208.67 seconds. A crock-type container with a volume of 80-85 litres takes 87.80 seconds, while a volume of 86-90 litres takes 98 seconds. This tool can reduce the presence of larvae at home from 61.43% to 3.77% and the density of larvae in containers from 38.14% to 5.56%. This means that this tool is declared effective, efficient, and sensitive in reducing the density of Aedes Sp larvae compared to physical methods.
- 13 March 2023
- Published by Research Synergy Foundation in Rsf Conference Proceeding Series: Medical and Health Science
- Vol. 2 (1) , 102-113
Open AccessPortable Device for Aedes Sp Larva Suction with Mechanical Electric Methods: Innovation in Control of DHF Disease
Controlling Aedes Sp larvae is an essential component in the Integrated Mosquito Management (IMM) program because when mosquitoes are removed before they become adults, there will be no transmission of vector-borne diseases, especially DHF. However, physical, chemical, and biological control is still not optimal because it is considered resistant, less sensitive, effective, and efficient, especially in scarce clean water. The research aims to make and test the effectiveness of the innovative portable Aedes Sp larvae sucker using the electric-mechanical method. This type of research is an actual experiment in the laboratory test stage and quasi-experimental in the field test. This innovation is a pump with a suction power of 1400 litres/hour and 1800 litres/hour equipped with an AC electric motor connected to an inverter circuit. On the laboratory scale, it was tested on 1,500 instars III and IV Aedes aegypti larvae, and on a field scale, it was tested on 45 containers in Endemic Village, Klaten Regency. Data analysis used the Pearson Correlation, independent sample, and Cochran tests. Laboratory test results showed that the time to catch all Aedes Sp larvae in containers with a volume of 80 litres and 90 litres using a power of 1400 litres/hour took 60 seconds and 138 seconds, while with a power of 1800 litres/hour, it took 33 seconds and 110 seconds. The speed of the number of Aedes Sp larvae caught is affected by the volume of water >=20 litres with a water level of > 8 cm. This tool was tested in the community at 43 houses and 45 positive larvae containers. The result show that with a power of 1800 litres/second, the time needed to suck the larvae in a bathtub-type container with a volume of 80-85 litres is 122.14 seconds, while a container with a volume of 86-90 litres is 208.67 seconds. A crock-type container with a volume of 80-85 litres takes 87.80 seconds, while a volume of 86-90 litres takes 98 seconds. This tool can reduce the presence of larvae at home from 61.43% to 3.77% and the density of larvae in containers from 38.14% to 5.56%. This means that this tool is declared effective, efficient, and sensitive in reducing the density of Aedes Sp larvae compared to physical methods.
- Open Access
- 9 February 2022
- Published by IntechOpen
Epidemiology of Chikungunya in Indonesia
Chikungunya is a zoonotic disease which is caused by the Chikungunya virus (CHIKV) and transmitted by infected Aedes spp mosquito. In Indonesia, CHIKV is a re-emerging disease, which means that it is a disease that has gone for a long time, but then it spreads again and causes outbreaks frequently. CHIKV presence in Indonesia was first reported in 1979 in Bengkulu City causing substantial acute and chronic morbidity. After disappearing for 16 years, the CHIKV outbreak spreaded again in 24 regions throughout Indonesia from 2001 to 2003. In 2009 and 2010, CHIKV outbreaks hit western and central regions of Indonesia and increased from 3,000 cases per year to 83,000 and 52,000 cases per year. The burden of this disease is unclear due to insufficient monitoring and diagnosis. The spread and transmission of CHIKV in Indonesia is very high, due to travel, competent vectors, and the vulnerability of the population. In addition, the evolution of viruses, globalization and climate change has accelerated the spread of this virus. Effective antiviral treatment and vaccines do not yet exist, so early detection and appropriate management can help reducing the burden of this disease. Monitoring and risk assessment to reduce human-vector contact are also needed to reduce the impact of chikungunya.
- 9 February 2022
- Published by IntechOpen
Open AccessEpidemiology of Chikungunya in Indonesia
Chikungunya is a zoonotic disease which is caused by the Chikungunya virus (CHIKV) and transmitted by infected Aedes spp mosquito. In Indonesia, CHIKV is a re-emerging disease, which means that it is a disease that has gone for a long time, but then it spreads again and causes outbreaks frequently. CHIKV presence in Indonesia was first reported in 1979 in Bengkulu City causing substantial acute and chronic morbidity. After disappearing for 16 years, the CHIKV outbreak spreaded again in 24 regions throughout Indonesia from 2001 to 2003. In 2009 and 2010, CHIKV outbreaks hit western and central regions of Indonesia and increased from 3,000 cases per year to 83,000 and 52,000 cases per year. The burden of this disease is unclear due to insufficient monitoring and diagnosis. The spread and transmission of CHIKV in Indonesia is very high, due to travel, competent vectors, and the vulnerability of the population. In addition, the evolution of viruses, globalization and climate change has accelerated the spread of this virus. Effective antiviral treatment and vaccines do not yet exist, so early detection and appropriate management can help reducing the burden of this disease. Monitoring and risk assessment to reduce human-vector contact are also needed to reduce the impact of chikungunya.