Geohealth最新文献

{"title":"Can Electric Vehicles Reduce Summertime Air Pollution Exposure Inequalities in Metro Atlanta? A High-Resolution Analysis","authors":"Yakun Zhou,&nbsp;Xin He,&nbsp;T. Nash Skipper,&nbsp;Zongrun Li,&nbsp;Ziqi Gao,&nbsp;Armistead G. Russell,&nbsp;Jennifer Kaiser","doi":"10.1029/2025GH001654","DOIUrl":"10.1029/2025GH001654","url":null,"abstract":"<p>Electric vehicles (EVs) are widely expected to improve air quality by reducing on-road emissions, but their impacts on exposure inequalities remain uncertain. To assess whether EVs can reduce summertime air pollution exposure inequalities in the Atlanta metropolitan area, we conduct high-resolution (1 km) photochemical air quality simulations using the Community Multiscale Air Quality (CMAQ) model. A 30% EV adoption of heavy-duty and light-duty vehicles is simulated to evaluate changes in nitrogen dioxide (NO₂), maximum daily 8-hr average ozone (MDA8 O₃), and fine particulate matter (PM_2.5) during summer. EV adoption leads to average domain-wide concentration reductions of 0.22 ppb in NO₂, 0.94 ppb in MDA8 O₃, and 0.06 μg/m³ in PM_2.5, with localized increases in NO₂ and PM_2.5 near power plants from increased electricity demand. The primary driver of air quality improvement from EV adoption is the reduction in on-road vehicle emissions, which outweighs any increases in emissions from electric generating units. The largest exposure reductions are observed in communities with higher proportions of Asian, Hispanic, and Black populations, underscoring the potential for EV adoption to alleviate exposure burdens in the communities of color. However, exposure disparities persist even with EV adoption, despite overall reductions in exposure levels across all racial/ethnic groups. Coarse-resolution (12 km) simulations tend to underestimate exposure for minority groups by up to 25% for NO₂ and 10% for PM₂_.5 but still capture the overall patterns of exposure disparities.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13602988/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149041491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond Green Cover: Links Between Greenspace Morphology, Configuration, and Heat-Related Illness in Arizona","authors":"Huaqing Wang,&nbsp;Shujuan Li,&nbsp;Simin Gholami,&nbsp;Joseph Hoover,&nbsp;Mackenzie Waller,&nbsp;Kacey Ernst","doi":"10.1029/2026GH001978","DOIUrl":"https://doi.org/10.1029/2026GH001978","url":null,"abstract":"<p>Residential greenness has been associated with reduced heat-related illness, yet the specific role of greenspace morphology at the neighborhood scale remains insufficiently understood. This study quantified the relationship between heat-related illness and multiple dimensions of greenspace morphology using an 8-year (2016–2023) unbalanced panel data set comprising 19,021 block-group–year observations across 2,427 census block groups in Arizona, USA. One meter high-resolution National Agricultural Imagery Program aerial imagery was classified to calculate greenspace percentage, number of greenspaces, average size, shape complexity, connectedness, and distantness, at the block group level. We applied conditional spatial autoregressive models with a negative binomial distribution to estimate associations between each morphology metric and yearly heat-related illness counts, adjusting for sociodemographic and geographic covariates. Additional sensitivity analyses evaluated the robustness of findings to overall greenspace amount, local climatic conditions, and alternative exposure specifications. We found higher greenspace percentage, aggregation, shape complexity, connectedness, and density were consistently associated with lower heat-related illness risk. A one–standard deviation increases in shape complexity corresponded to a 12.4% decrease in expected heat-related illness counts (IRR = 0.876, 95% CI: 0.834–0.921). Similarly, increases in greenspace percentage (14.6% decrease; IRR = 0.855, 95% CI: 0.827–0.885), number of greenspace patches (3.7% decrease; IRR = 0.963, 95% CI: 0.937–0.990), average size (4.5% decrease; IRR = 0.955, 95% CI: 0.923–0.989), and connectedness (5.5% decrease; IRR = 0.945, 95% CI: 0.918–0.972) were all protective. In contrast, larger inter-greenspace distances were associated with increased heat-related illness risk (6.1% increase; IRR = 1.061, 95% CI: 1.033–1.091). These associations were generally robust to additional adjustment for local climatic conditions and overall greenspace area. Our findings highlight the critical importance of multiple dimensions of greenspace morphology in relation to heat-related health risks. These results suggest that heat-reduction planning with greening initiatives should consider not only the amount of greenspace but also its spatial configuration to maximize cooling and result in health benefits.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2026GH001978","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148994297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Climate Informed Dengue Prediction and Future Risk Under a Changing Monsoon Climate in Kerala, India","authors":"Yacob Sophia,&nbsp;Mathew Koll Roxy,&nbsp;Surendranath Bindu Vaisakh,&nbsp;Pallipurathu Raghunathan Nair Sreelakshmi,&nbsp;Thekkumkara Surendran Anish,&nbsp;Pillaveetil Sathyadas Indu","doi":"10.1029/2026GH001893","DOIUrl":"10.1029/2026GH001893","url":null,"abstract":"<p>Dengue fever has emerged as a major public health threat in India, with its burden projected to rise under climate change. This study investigates the influence of climate variability on dengue incidence in Kerala, a dengue hotspot in southern India, using 14 years of climate and dengue data (2006–2019). Temperature, monsoon rainfall and its active-break phases, relative humidity (RH), and the El Niño–Southern Oscillation are identified as key climatic predictors of dengue transmission in the region. Dengue seasonality in Kerala closely follows its rainfall cycle, with cases rising in May and peaking during the southwest monsoon (June–September), reaching a maximum in June–July. To capture the nonlinear and combined relationships between climatic predictors and dengue incidence, several machine learning (ML) models were trained and evaluated, with the XGBoost regression model showing the best predictive performance (<i>R</i>² = 0.72, Normalized Root Mean Square Error = 0.53). Locally, warmer temperatures (30.5–32.5°C) and moderate humidity (66%–79%) during the pre-monsoon season, together with moderately high rainfall (180–450 mm/month) during the monsoon season, favor high dengue incidence. Remotely, El Niño–like conditions increase dengue incidence by shifting large-scale circulation toward warmer and drier pre-monsoon conditions over Kerala, while La Niña–like conditions have the opposite effect, providing about 3 months of potential predictability. Future simulations from Coupled Model Intercomparison Project Phase 6 models project an increase in dengue incidence by 16%–20% in the near future (2021–2040) and 46%–113% in the far future (2081–2100) under low-to-high emission pathways. These findings highlight the need for climate-informed dengue early warning and future risk planning in Kerala.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580351/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148992129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contrasting Effects of Phosphate on Arsenic Mobility and Human Exposure in Agricultural Soils","authors":"Petr Drahota,&nbsp;Alena Černíková,&nbsp;Vojtěch Ettler,&nbsp;Johana Kešnerová,&nbsp;Martin Lichovník,&nbsp;Martin Mihaljevič","doi":"10.1029/2026GH002031","DOIUrl":"10.1029/2026GH002031","url":null,"abstract":"<p>Arsenic in agricultural soils may pose human health risks due to elevated concentrations and increased soil ingestion associated with dust generation. However, the actual exposure depends on the fraction of As that becomes bioaccessible under gastrointestinal conditions. This study evaluates As mobility, bioaccessibility, and associated health risks in 57 agricultural topsoils from seven regions affected by geogenic enrichment and historical mining. Arsenic partitioning was characterized using operationally defined extractions and mineralogical analyses, and bioaccessibility was determined by an in vitro gastric assay. The total As concentrations range from 25 to 2007 mg kg⁻¹, exceeding national agricultural soil thresholds (40 mg kg⁻¹) in ∼80% of samples. Nevertheless, relative As bioaccessibility ranges from 2% to 38%, with most soils exhibiting values below 10%. Arsenic is predominantly associated with Fe (oxyhydr)oxides, while discrete As-bearing minerals are rare. Surface-bound As, defined by phosphate extraction, strongly controls both mobility and bioaccessibility. Long-term phosphate enrichment due to repeated fertilization exerts contrasting effects on As behavior. Readily soluble P enhances both As mobility and bioaccessibility, whereas higher Olsen-extractable P is associated with lower As bioaccessibility, suggesting progressive occupation of reactive sorption sites. A risk assessment based on a conservative rural ingestion scenario indicates that most soils did not exceed non-carcinogenic thresholds when bioaccessible As was considered. These findings demonstrate that bioaccessible As and associated exposure risk are controlled primarily by reactive surface-bound As fractions rather than by total soil As concentrations, whereas phosphate exerts contrasting secondary effects depending on its geochemical availability and partitioning.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13575764/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148978414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-Income, Minority-Serving Public Schools in Southern California Have Disproportionately High Surface Temperatures","authors":"Joaquin Murillo,&nbsp;Gabriella R. Dauber,&nbsp;Joshua B. Fisher,&nbsp;Gregory R. Goldsmith","doi":"10.1029/2026GH001927","DOIUrl":"10.1029/2026GH001927","url":null,"abstract":"<p>Extensive evidence demonstrates that people from minority backgrounds often face unequal exposure to extreme heat and have less access to green space that can provide cooling relief. What is less clear is whether these inequities extend to students on school playgrounds, where high temperatures can affect physical health, social and emotional well-being, and learning. We paired high resolution, satellite remote sensing surface temperature data for all 615 of the public schools in Orange County, California (serving ca. 450,000 students) with data on neighborhood household income, race/ethnicity of school enrollment, distance from the coast, and Normalized Difference Vegetation Index as a measure of landscape greenness. Based on &gt;47,000 observations from the hottest late summer days, we observed mean school surface temperatures in excess of 40°C, with temperatures at some schools reaching nearly 50°C on some days. Higher school ground surface temperatures were significantly correlated with low household income (<i>ρ</i> = −0.36) and racially/ethnically diverse student populations (<i>ρ</i> = 0.37). These same schools also exhibited less variation in temperature across their grounds, which may indicate fewer spaces for students to seek relief. Greener school landscapes were weakly correlated with lower school ground surface temperatures and this was independent of socioeconomics. Our findings provide robust evidence of links between school surface temperatures and school demographics, and they highlight the growing potential of satellite remote sensing to assess heat exposure within and across schools.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13576633/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148978422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Who Can Avoid the Heat? Inter-Individual Differences in 24-hr Heat Exposure Reveal Disparities in Heat Adaptation and Stress","authors":"G. Guzman-Echavarria,&nbsp;A. Middel,&nbsp;N. Ravanelli,&nbsp;J. B. Rosales Chavez,&nbsp;A. R. Caldwell,&nbsp;C. Metzler,&nbsp;K. Rentz,&nbsp;M. Munoz,&nbsp;M. Guardaro,&nbsp;J. K. Vanos","doi":"10.1029/2026GH001914","DOIUrl":"https://doi.org/10.1029/2026GH001914","url":null,"abstract":"<p>Differences in adaptive capacity and sensitivity shape behavioral and physiological responses to overheated environments, which are associated with unequal personal heat exposure (PHE). Although growing evidence documents heterogeneity in PHE across regions and populations, studies rarely examine how adaptive factors influence sub-daily exposure patterns and resulting heat stress relative to regional heat. This study assesses intra- and inter-individual variation in 24-hr PHE and heat loads using regional weather as a non-behavioral baseline. We studied 34 adults aged 45–74 from diverse socioeconomic, occupational, and housing backgrounds in the Phoenix Metropolitan Area. Using the HeatSuite™ system and Kestrel Drop D2 sensors, we monitored 10-min indoor and on-body ambient conditions over 21-day periods during summer 2024, reconstructing PHE based on participants' locations. We used Generalized Additive Models to explain inter-individual differences and Linear Mixed Models to examine associations with vulnerability features. Heat stress was assessed using a physiology-based human heat balance model. Results reveal significant inter-individual differences in individually experienced temperatures (IET) and humidities (IEH), with three sub-daily patterns emerging: highest overall exposures, strong diurnal amplitude, and day-long stable exposures. Median IET and IEH were 25.9°C and 1.4 kPa, with maxima reaching 47.5°C and 5.1 kPa. On average, participants experienced temperatures 10.4°C below regional conditions, with low evaporative cooling requirements to attain heat balance for sedentary activities. However, participants with income &lt;$40k/year experienced higher peak daily temperatures. These findings demonstrate how high-resolution personal monitoring reveals when and why heat interventions may be most effective, informing policy with locally-grounded evidence.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2026GH001914","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148943320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association of Environmental Factors and Aging Levels Under Different Urbanization Levels in China","authors":"Zehua Zheng,&nbsp;Yiting Liu,&nbsp;Jiawei Zang,&nbsp;Huaiyue Xu,&nbsp;Kailai Lu,&nbsp;Jie Ban,&nbsp;Qing Wang","doi":"10.1029/2025GH001642","DOIUrl":"https://doi.org/10.1029/2025GH001642","url":null,"abstract":"<p>In China, the processes of population aging and urbanization are persistently accelerating. To gain insights into the association of environmental factors and aging levels under different urbanization levels, this study examined how these factors correlate with aging levels across varying degrees of urbanization in China. County-level data encompassing aging levels and 22 pertinent factors were collated for the years 2010 and 2020. Aging levels were quantified by the proportions of elderly population aged 65+ and 85+ within the total population. The counties were categorized into three urbanization levels: high, medium, and low. Fixed effect models and random forest models were established to scrutinize the impacts and significance of independent variables on aging levels under different urbanization levels. Notably, the aging levels across all urbanization levels rose by a factor of 1.5–2.1 from 2010 to 2020. The results of the two models indicate that there are urbanization gradient differences in the impact factors: in low-urbanization areas, resident savings and PM_2.5 are the important variables; in medium-urbanization counties, resident savings and air pollution such as CO, SO₂, PM_2.5, and O₃ are the important variables; in high-urbanization counties, climate factors such as average temperature in January and July are the important variables. Moreover, air pollutants show age-specific associations, and medical resources only have a significant supporting impact on LA85+. The study reveals the transformation rule of the aging driving mechanism in the urbanization process from “economic foundation support” to “life quality adaptation,” providing a scientific basis for formulating differentiated health aging policies.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2025GH001642","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148943298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Calling for a GeoHealth Decadal Survey: Accelerating Solution-Oriented Research and Applications to Address Environmental and Health Problems","authors":"D. Q. Tong,&nbsp;M. E. Gorris,&nbsp;A. M. Abadi,&nbsp;S. Anenberg,&nbsp;K. Ardon-Dryer,&nbsp;J. R. Bratburd,&nbsp;K. Cromar,&nbsp;Y. Hang,&nbsp;R. D. Harp,&nbsp;A. Hoffman-Hall,&nbsp;C. J. Horwell,&nbsp;G. H. Kerr,&nbsp;Y. Ma,&nbsp;S. J. Ryan,&nbsp;J. D. Stowell,&nbsp;M. Usmani,&nbsp;M. C. Wimberly,&nbsp;B. F. Zaitchik,&nbsp;K. Chen","doi":"10.1029/2026GH002024","DOIUrl":"https://doi.org/10.1029/2026GH002024","url":null,"abstract":"<p>GeoHealth is a rapidly growing, transdisciplinary field that integrates Earth and health sciences to understand the complex interactions between these domains. In 2017, the GeoHealth section of the American Geophysical Union and affiliated journal were established and both have grown rapidly since. Despite this growth, the field faces current and foreseeable challenges in translating scientific insights into action, including fragmented data infrastructure, funding gaps, and an evolving policy landscape. This commentary piece advocates for a GeoHealth Decadal Survey, a consensus-driven report to identify priority research questions, guide workforce development, build community consensus, and inform strategic investments over the next decade.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2026GH002024","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148943297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Climate Warming on All-Causes Mortality in China: The Role of Non-Optimal Temperature Exposure and Multi-Scenario Projections to 2050","authors":"Yujun He,&nbsp;Conglin Song,&nbsp;Dejun Chen,&nbsp;Yuan He,&nbsp;Xiaojun Li,&nbsp;Xuequan Wang,&nbsp;Zhaoyang Liu,&nbsp;Tao-Hsin Tung","doi":"10.1029/2026GH001897","DOIUrl":"https://doi.org/10.1029/2026GH001897","url":null,"abstract":"<p>Global warming intensifies non-optimal temperature exposure (consisting of high and low temperature), which poses severe threats to human health. As the world's most populous country located in temperate and subtropical zones, China is highly vulnerable to temperature-related mortality, with distinct yearly and population disparities in health risks. To investigate the impact of non-optimal temperature exposure on China's all-causes mortality during 1990–2023 and project future trends (2024–2050) under different climate change scenarios. Integrated CN05.1 gridded observational data, CMIP6 climate data (SSP2-4.5 and SSP5-8.5 scenarios), SimmEX extreme temperature indices data, and GBD 2023 disease burden data. We applied Spearman's correlation analysis, Joinpoint regression, Age-Period-Cohort analysis, and restricted cubic spline models for trend quantification and future projections. Non-optimal temperature-related deaths increased, while age-standardized mortality rate declined significantly. Low-temperature exposure remained the primary risk, but high-temperature-related health impacts intensified notably. The elderly (≥80 years) and individuals with cardio-cerebrovascular or respiratory diseases were the most susceptible. Climate warming showed significant correlations with most cause-specific mortalities. Future projections revealed divergent disease risk trends under the two emission scenarios, with some diseases facing elevated risks. Non-optimal temperature exposure exerts heterogeneous impacts on China's all-causes mortality, with high-temperature risks becoming increasingly prominent amid global warming. Targeted prevention and control strategies tailored to age, disease types, and emission scenarios are crucial to mitigate temperature-related health burdens.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2026GH001897","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148943015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Explainable Machine Learning Framework for Predicting West Nile Virus and Uncovering Key Transmission Drivers","authors":"Dimitrios Sainidis,&nbsp;Konstantinos Tsaprailis,&nbsp;Charalampos Kontoes","doi":"10.1029/2025GH001747","DOIUrl":"https://doi.org/10.1029/2025GH001747","url":null,"abstract":"<p>This study introduces Disease Vector Intelligence (DVI), an explainable Machine Learning (ML) framework developed within the EYWA (EarlY WArning system for mosquito-borne diseases) ecosystem. DVI integrates big Earth Observation (EO), socioeconomic, and estimated mosquito abundance data to predict the presence or absence of West Nile Virus (WNV) cases, expressed as a risk score at a high spatiotemporal resolution. The SHAP (SHapley Additive exPlanations) method is employed for a local-level feature importance analysis to uncover key drivers with a high impact on the prediction. The framework consists of two ML models: one intended to be used as an Early Warning System (EWS) predicting at a regional scale, and the other identifying areas susceptible to WNV transmission at a 2 × 2 km² grid scale, independent of human-defined administrative boundaries. Both models were trained on 11 years of historical WNV case data and validated in Greece. SHAP analysis on both models revealed temperature as a crucial driver of WNV transmission. The fine spatial resolution of the second model uncovered micro-scale key drivers, such as elevation and land cover type, that the lower resolution model missed. DVI models could be used complementarily by health authorities to aid their decision-making process and to provide critical insights into important drivers that influence the transmission of WNV.</p>","PeriodicalId":48618,"journal":{"name":"Geohealth","volume":"10 9","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2025GH001747","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}