Geospatial-based surveillance of malaria risk in dar es salaam using a hybrid 3DCNN + LSTM and CA model.

A spatiotemporal U-Net++ deep learning framework for dengue risk mapping in Colombia

A spatio-temporal deep learning framework based on the U-Net++ architecture is proposed to generate high-resolution dengue risk maps in Colombia and highlights the potential of integrating heterogeneous climatic, environmental, and socioeconomic data within a spatiotemporal deep learning framework to characterize dengue risk patterns and support high-resolution surveillance.

Spatio-Temporal Modeling of Malaria Occurrence Probability Using Multi-Sensor Remote Sensing and Machine Learning

Background: Reliable mapping of malaria occurrence requires validation across environmentally distinct years and care­ful separation of model-derived probability from transmission intensity. This study developed a multi-sensor remote sensing and machine-learning framework for mapping annual malaria case occurrence in southeastern Iran. Methods: Annual median composites of Soil Water Index (SWI), Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST) were generated from Sentinel-1, Sentinel-2 and Landsat 8/9 at 30m resolution. After quality control, 82, 168, 775 and 483 malaria case locations were retained for the Solar Hijri years 1400–1403 (2021–2025). Five spatially balanced pseudo-absence realizations were generated annually at a 1:1 ratio with a 300m exclu­sion buffer. Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) were evaluated through complete four-fold leave-one-year-out validation with nested tuning. Performance, bootstrap confidence intervals, uncertainty, Getis–Ord Gi* clusters and SHAP (SHapley Additive exPlanations) were assessed. Results: Across 20 outer evaluations, RF achieved ROC-AUC 0.685±0.045, PR-AUC 0.693±0.040, balanced accuracy 0.624±0.026 and Brier score 0.230±0.015. XGBoost achieved ROC-AUC 0.687±0.044, PR-AUC 0.691±0.043, bal­anced accuracy 0.625±0.033 and Brier score 0.231±0.015. Year-specific ROC-AUC ranged from 0.624 to 0.726. LST was the dominant predictor (48.27%), followed by NDVI (37.04%) and SWI (14.69%). Only 3.46–6.10% of pixels ex­ceeded probability 0.70. Mean uncertainty was low (0.030–0.032) but spatially heterogeneous. Conclusion: Both algorithms showed moderate, comparable performance with year-dependent variation. Maps provide relative probabilities for prioritizing field surveillance, not transmission estimates.

Flood risk modeling for Kisumu County, Kenya: integrating multi-source geospatial data and machine learning

Flooding poses an escalating threat to Kisumu County, Kenya, driven by climate change and rapid urbanization. This study develops an integrated framework combining remote sensing, GIS, and machine learning for flood risk mapping and forecasting using multi‐source geospatial data (Sentinel‐1 SAR, Landsat 8, SRTM DEM, SMAP soil moisture) and meteorological data (2014‐2025). Four machine learning models random forest (RF), artificial neural network (ANN), deep neural network (DNN), and convolutional neural network (CNN) were developed and validated. The ANN achieved the highest accuracy (R 2 = 0.910, RMSE = 0.038). Excluding RF (R 2 = 0.520) from the ensemble improved performance to R 2 = 0.916 (RMSE = 0.035), a 22% error reduction. Flood risk mapping classified Kisumu County into five categories, revealing that 40.9% (857.8 km 2 ) faces moderate to very high risk, with critical hotspots along the Lake Victoria shoreline and in Kisumu City and Ahero. Slope (20%), NDBI (15%), soil moisture (15%), and stream proximity (15%) were identified as dominant flood drivers. Uncertainty quantification revealed low model variance (R 2 σ = 0.006) and demonstrated that aleatoric uncertainty (62%) dominates epistemic uncertainty (38%). This framework provides a replicable, data‐driven methodology for flood risk assessment in data‐scarce regions globally.

A data-driven framework for flood hazard mapping using integrated geospatial and multi-model machine learning approaches in a tropical mountainous region: insights from Aceh Jaya, Aceh Province, Indonesia

Modelling climatic and temporal dynamics of dengue transmission in Bangladesh using deep learning models

A high-resolution forecasting framework that integrates daily dengue case data with meteorological drivers to improve predictions in Bangladesh and provides an efficient, reproducible, and scalable approach that can strengthen dengue preparedness in public health systems with limited resources is developed.

Mapping Malaria Risk in Jayapura Using a Random Forest Approach

Background: Malaria remains a major health issue in Jayapura, where climatic and landscape variability creates uneven transmission risks. Early identification of vulnerable areas is essential for supporting targeted control strategies.Objective: This study aims to develop a Random Forest model integrating remote-sensing environmental variables to identify malaria-prone areas in Jayapura District and Jayapura City.Methods: Environmental predictors including rainfall, land surface temperature, slope, NDVI, humidity, land use, and population density were linked to confirmed malaria cases. Data were split into 70% training and 30% testing datasets. Model performance was evaluated using accuracy, sensitivity, macro-sensitivity, and macro-specificity, and the outputs were used to generate a spatial malaria risk map.Results: The Random Forest model achieved an overall accuracy of 0.667, sensitivity of 0.833, macro-sensitivity of 0.800, and macro-specificity of 0.867, indicating good capability in identifying areas with higher malaria vulnerability. Feature importance analysis showed that rainfall, land surface temperature, and slope were the most influential predictors of malaria risk. High-risk areas were concentrated in coastal and urban zones, while peri-urban agricultural areas showed moderate risk and high-elevation regions exhibited lower vulnerability.Conclusion: Integrating remote-sensing environmental data with epidemiological information allows the Random Forest model to capture key malaria-risk patterns in Jayapura. The resulting spatial risk map can support targeted vector control strategies, improved surveillance, and more efficient allocation of public health resources toward Indonesia’s Malaria Elimination 2030 goals.