Total effect of heat on mortality considering heat-mediated air pollution and interaction effect under demographic, mitigation, and adaptation scenarios.

Research on operational trajectory control methods and performance testing of multi-degree-of-freedom robotic arms for fruit tree pruning

• Multi-year ML framework improves yield prediction under high climatic variability. • Integrating agronomic and environmental data outperforms single-factor models. • Random Forest and XGBoost capture nonlinear yield responses across bean cultivars. • Heat stress and reproductive traits emerge as key yield-driving predictors. • Framework supports climate-smart, cultivar-specific decision making for growers. Accurate yield prediction remains a major challenge for legume production in environmentally variable regions such as the USA Delmarva Peninsula, where sandy soils and fluctuating climatic conditions intensify crop sensitivity to heat and moisture stresses. To address this challenge, this study developed a multi-year machine learning framework to predict grain yield for four bean species, mung bean, pigeon pea, kidney bean, and cowpea, represented by a total of 11 cultivars evaluated across eight growing seasons. The framework integrated four categories of predictors: Genotype (G) (cultivars), agronomic (A) traits (plant height, pods and seeds metrics, plant biomass, and yield), management (M) practices (trial structure and replications), and environmental (E) factors (temperature, heat stress index: HSI, growing degree days: GDD, and precipitation). Two nonlinear algorithms, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost), were evaluated under single-input, two-input, three-input, and full multi-component configurations to assess the relative predictive contributions of G, A, M, and E. Mean annual grain yield varied substantially across seasons, ranging from 93.5 kg/ha in 2014 to 6,279.9 kg/ha in 2023, reflecting pronounced interannual climatic variability and environmental heterogeneity in the Delmarva region. Both models achieved their highest predictive accuracy in years with more consistent E patterns and narrower yield distributions (coefficient of determination: R² = 0.98–0.87 in 2017–2019), whereas predictive performance declined in seasons characterized by greater climatic variability and more dispersed yield values. Among single-input models, A traits showed the strongest predictive ability ( R² ≈ 0.53), followed by E variables ( R² ≤ 0.49), while G-only and M-only inputs contributed minimally. Across multi-input configurations, the E+A combination delivered the highest overall two-input performance (RF R² = 0.69; XGBoost R² = 0.71), and the three-input models that combined A and E with G or M also showed strong predictive ability ( R² ≈ 0.70–0.73), while the full G+E+A+M model achieved the strongest combined-year accuracy (RF R² = 0.73; XGBoost R² = 0.76). These results demonstrate that integrating agronomic structure with environmental variability substantially improves multi-year yield prediction, and support cultivar-specific recommendations and climate-informed management strategies for Delmarva and other coastal agroecosystems.

In the absence of biomarkers, the true biological footprint of migraine remains incompletely understood. It could perhaps be best characterized using machine learning models of multimodal data. The aim of this study was to (1) develop diagnostic models of migraine using multimodal data and (2) identify data-driven migraine phenotypes. This was a cross-sectional machine learning analysis of demographics, self-reported clinical and headache data, and genome-wide genotype data from the Trøndelag Health Study (data collected 1995-1997 and 2006-2008). All participants who were genotyped and completed the headache questionnaire were included. First, predictive machine learning models were developed using genotype data and general clinical data (excluding headache data) to diagnose individuals with migraine vs headache-free controls. Models were optimized on a training set and evaluated on a held-out test set, scored with the area under the receiver operating characteristic curve (AUC). Second, unsupervised models were trained on the headache data and the most predictive features from the diagnostic models to identify subgroups. The subgroups were compared using genome-wide association analyses, conventional polygenic risk scores (PRSs), and machine learning-based genetic risk scores. A total of 43,197 individuals were included in the diagnostic models, and 12,185 individuals were included in the data-driven phenotyping (mean [SD] age 49.1 [16.7] years; 51.7% women). The top-performing diagnostic model was a light gradient boosting machine, with a test set AUC of 0.80 (95% CI 0.78-0.81). Two main clusters were identified, one with 1,425 individuals, 94% of whom met diagnostic criteria for migraine, and another with 10,760 individuals, whereof 71% had nonmigraine headaches. The former was subclustered into 4 relatively distinct groups: one with only men, one with prominent neck pain, one with more musculoskeletal pain, anxiety and depression, and one with "classic" migraine. The groups were better discriminated by machine learning-based genetic risk scores compared with PRSs. Migraine can accurately be diagnosed from nonheadache data, suggesting that it is biologically describable by combinations of clinical, genetic, and environmental data. Data-driven phenotyping with such data identifies migraine subgroups with distinct phenotypic and genotypic signals, possibly not captured by current diagnostic criteria-but with potential implications for management.

A deep learning approach for predicting steel rebar corrosion in concrete bridge columns from two-year noisy GPR B-scan images

Climate and land-use interactions shape the future of an endangered butterfly in a warming world

Objectives. To describe a data-mapping blueprint for identifying US locations at high risk for childhood lead exposure and to apply this approach to inform targeted public health interventions. Methods. We developed a stepwise, flexible blueprint integrating environmental and housing data, blood lead level data, and geospatial mapping to identify potential lead exposure hotspots, characterize contributing sources, and guide intervention prioritization. We applied the blueprint in multiple federal and state case studies through interagency collaboration. Results. Application of the blueprint identified high-risk locations for childhood lead exposure and informed targeted actions across diverse contexts. In data-rich settings, integration of blood lead level and environmental data enabled identification of exposure hotspots and prioritization of outreach, enforcement, and remediation. In data-limited settings, lead exposure indices and environmental indicators supported targeted surveillance and resource allocation. Across applications, the blueprint facilitated coordination among agencies, improved lead-based paint and infrastructure intervention targeting, and supported expansion of screening and prevention efforts. Conclusions. A coordinated, data-driven mapping approach can improve identification of lead exposure hotspots and support prioritization of impactful interventions. Public Health Implications. Broader implementation of the blueprint, along with enhanced data integration and interagency collaboration, may strengthen efforts to reduce childhood lead exposures and improve public health outcomes. (Am J Public Health. 2026;116(7):1030-1037. https://doi.org/10.2105/AJPH.2026.308440).

In recent decades, citizen science has emerged as a key approach to engage the public in research, enhancing scientific productivity and democratizing science. However, the effective use of citizen-generated environmental data for climate change analysis and decision-making remains limited due to the heterogeneity of data sources, formats, and platforms, which hinders interoperability and reuse within existing environmental data infrastructures. This paper presents the Environmental Impact Hub (EIH), developed within the EU Horizon 2020 I-CHANGE project, as an interoperable data infrastructure designed to integrate heterogeneous environmental observations from citizen science activities, low-cost sensors, institutional monitoring networks, and Earth observation systems. Guided by the principle ‘from citizens to citizens’, the EIH adopts a modular architecture based on a Data and Information Broker, a Citizen Observatory Archive, and an interactive Dashboard, enabling data discovery, access, and reuse through open standards and APIs. The infrastructure was tested across eight Living Labs in Europe and beyond, demonstrating its capability to ingest, harmonize, and expose heterogeneous datasets, and to support interoperability with major initiatives such as Copernicus, GEO/EuroGEO, and the Green Deal Data Space. The EIH exemplifies a scalable, FAIR-aligned approach to integrating citizen-generated data into Digital Earth ecosystems, supporting climate-related environmental applications and data-driven services.

Background/Objectives: To evaluate whether day-of-procedure ambient ozone exposure is associated with pneumothorax after CT-guided lung biopsy. Methods: This retrospective single-centre study included 160 CT-guided lung biopsies performed between January 2018 and February 2026. Environmental data from the day of biopsy were assigned from the nearest national monitoring station. The primary outcome was any pneumothorax on post-biopsy CT; the secondary outcome was drainage-requiring pneumothorax. Multivariable logistic regression included ozone exposure, emphysema, and access route through dependent lung area (ARDA). Ozone was analysed as a continuous variable per 10 μg/m3 and, exploratorily, using a ROC-derived threshold of ≥75.8 μg/m3. Restricted cubic splines assessed nonlinearity. Sensitivity models adjusted for needle size, biopsy system, operator identity, and season. Drainage-requiring pneumothorax was analysed using Firth logistic regression. Results: Pneumothorax occurred after 86 of 160 biopsies (53.8%), and 13 biopsies (8.1%) required drainage. Ozone was not associated with pneumothorax when modelled linearly (OR, 1.09 per 10 μg/m3; 95% CI, 0.97–1.23; p = 0.167). In exploratory threshold modelling, ozone ≥ 75.8 μg/m3 was associated with pneumothorax (OR, 2.76; 95% CI, 1.39–5.61; p = 0.004). Emphysema increased pneumothorax odds (OR, 2.16; 95% CI, 1.03–4.68; p = 0.047), whereas ARDA was protective (OR, 0.23; 95% CI, 0.11–0.45; p < 0.001). Spline analysis supported nonlinearity (p = 0.001). For drainage-requiring pneumothorax, only emphysema was significant. Conclusions: Ambient ozone showed an exploratory nonlinear association with pneumothorax after CT-guided lung biopsy, with a threshold signal around 70–80 μg/m3. ARDA was protective, whereas emphysema was associated with drainage-requiring pneumothorax.

Consistency of stream insect trait responses to instream pesticide exposure across five U.S. regions.

Feasibility of continuous sleep and environmental monitoring in residential substance use recovery: Associations with mental health outcomes.

Predicting type II diabetes mellitus in young and middle-aged adults: A machine learning approach using the Utah population database.

Sensitivity of ultrafine particle and black carbon simulations to model resolution and emission data in urban environment with a focus on Barcelona.

NEW INSIGHTS INTO THE COMPLEX GENETIC ARCHITECTURE OF AGE-RELATED HEARING LOSS.

Sustainable urban agriculture plays a very important role in the management of food security and environmental issues of rapidly expanding cities. Inefficient irrigation, poor choice of crops and a lack of real-time monitoring are major challenges that are affecting traditional rooftop gardening. To address these issues, this work suggests a smart Internet of Things-based, eco-friendly rooftop garden sensor and machine learning-based planting suggestion system that runs on electricity. The system incorporates a group of low-cost sensors to measure soil moisture, pH, temperature, humidity, and rainfall and an automated irrigation system where the harvested rainwater is used to manage water in an efficient and sustainable manner. The architecture is centered on a Random Forest machine learning module which analyzes the real-time environmental data and decides if it is possible to plant and suggests crops that best fit the current microclimate conditions of the location of the rooftop. The system is designed to work in three synchronous levels of sensing, processing and user interface, with a responsive GrowGreen web dashboard displaying real-time monitoring, irrigation notifications and recommended crops in a ranking order. The experimental findings prove that the Random Forest model attained as high as 92% prediction accuracy and irrigation efficiency of 95%, which proves the practical feasibility of the framework proposed. This platform contributes to retro-friendly rooftop farming by helping to streamline water usage, increase the potential of crops and promoting the growth of intelligent, resilient green cities due to the innovative incorporation of IoT and machine learning technologies.

Long-term exposure to ambient air pollution and risk of non-traumatic osteonecrosis of the femoral head: A nationwide cohort study.

ABSTRACT This article reconceptualizes environmental data activism as situated practices that mediate actions through data infrastructures and translation. Drawing on participant observation, interviews, and document analysis of two environmental NGOs (ENGOs) in Taiwan and their collaborations with civic-tech communities, we identify three key roles of ENGOs in environmental data activism: (1) extracting and infrastructuring datasets; (2) translating and re-embedding data into everyday practices through digital tools such as mobile apps and crowdsourcing games; (3) and mediating between different social actors in data activism. Hence, we theorize ENGOs as civic data intermediaries that turn open data into civic data infrastructures. We further identify contingent civic alliances in data activism. These are volunteer-driven collaborations that are generative yet precarious, producing episodic surges of both innovation and breakdown. This article argues that the value of data emerges not from purity of measurement but from socio-technical work that renders data publicly usable and criticizable. Conceptually, the research advances a practice-based theory of data justice as infrastructural work, showing how civic groups convert data from records into connected actions in everyday activism. From this perspective, the limits of justice are set as much by the labor of maintenance, temporal rhythms, and alliance fragility as by the epistemic accuracy of data.

To evaluate the environmental impact associated with CT scanners equipped with deep-learning-based image reconstruction (DLIR) compared with scanners equipped with hybrid-iterative reconstruction (HIR), focusing on electricity consumption, carbon dioxide equivalent (CO₂e) emissions, and iodinated contrast media (ICM) utilization in a high-volume tertiary referral center. In this retrospective single-center study, environmental data were collected over an 18-month period from four CT scanners: two using HIR (Group 1) and two using DLIR (Group 2), including body CT examinations. DLIR-based protocols were implemented with reduced tube voltage (80-100 kV vs 120 kV) and optimized ICM doses. Electricity consumption, CO₂e emissions, and ICM utilization were quantified and compared between groups. Environmental outcomes were analyzed at the scanner level and normalized per examination. A total of 42,300 examinations were analyzed (23,096 in Group 1; 19,204 in Group 2). Electricity consumption was 123,000 kWh for Group 1 and 66,927 kWh for Group 2, corresponding to 30.75 and 16.73 tons of CO₂e emissions, respectively. At the scanner level, this represented a reduction of 28,037 kWh and 7.01 tons of CO₂e per scanner (4.67 tons/year). DLIR-based protocols were associated with an ICM saving of 434 L over 18 months, corresponding to 4.47 tons of avoided CO₂e emissions and 60,730 L of water preserved. Combined CO₂e emissions from electricity and ICM were 49.62 tons in Group 1 and 29.10 tons in Group 2. DLIR-based optimized protocols were associated with improved environmental metrics, supporting their potential contribution to more sustainable radiology practices in high-volume settings. Deep learning-based image reconstruction enables routine body CT protocols with lower tube voltage and reduced ICM dose, supporting a clinically feasible transition toward more sustainable CT practice in high-volume imaging workflows. DLIR was associated with the implementation of lower tube voltage and reduced ICM dose, supporting more sustainable CT imaging based on protocol adaptations. In a high-volume tertiary referral center, deep learning-based image reconstruction was associated with a substantial reduction in electricity consumption and overall CO₂-equivalent emissions compared with hybrid iterative reconstruction. Optimization of contrast media dosing with deep learning-based image reconstruction contributed meaningfully to environmental benefits.

This study investigated the impact of heat on the risk of hospital admission due to a range of health conditions in England. We used records of over 4 million hospital admissions in the summer months between 2008 and 2019, to construct daily time series of admissions in 32 837 census areas. Coupled with high-resolution environmental data, we conducted a case time-series analysis using distributed-lag non-linear models to measure the lagged relationship between summertime temperature and risk of admission for a broad set of health conditions. We derived the relative risks of admission at the 99th compared with the 50th temperature percentile to understand the effect of extreme heat in each locality. The adult population of England (aged 18 years and older). Unplanned National Health Service (NHS) in-patient hospital admissions for cardiovascular, respiratory, genitourinary, metabolic and infectious diseases, along with their subcategories. These conditions contributed more than 3.7 million admissions, of which over 1.5 million (42%) were for those aged 75 years and over. More than 80% of admissions were for respiratory, cardiovascular or genitourinary illness, which collectively contributed 3.1 million hospital admissions. There was clear evidence of an increased risk of hospital admission for many conditions, including acute renal failure (1.37, 95% CI 1.32 to 1.42), metabolic disorders (1.28, 95% CI 1.24 to 1.32), infectious and parasitic diseases (1.06, 95% CI 1.04 to 1.08), pneumonia (1.07, 95% CI 1.05 to 1.09) and chronic obstructive pulmonary disease (1.08, 95% CI 1.05 to 1.10). The evidence was less clear for asthma and diabetes, while there were negative associations for many cardiovascular conditions. There was a clear age gradient in heat-related admissions, with older people facing the greatest risk of admission. These findings highlight the widespread effect of extreme heat across a range of health conditions, in addition to mortality, and have implications for public health planning in our changing climate.

ABSTRACT Large outdoor iron artifacts are vulnerable to environmental factors, and their conservation presents an enormous challenge. The Pujindu site is renowned for its large iron artifacts. The ‘Qixing Column’ iron columnar artifacts exhibit gradient corrosion from top to bottom, which may compromise their stability. In this study, the corrosion characteristics of iron columns and the soluble chlorine content in their environmental samples were analyzed using scanning electron microscopy-energy dispersive spectroscopy, Raman spectroscopy, X-ray diffraction, and ion chromatography. Elemental chlorine caused structural differences in the corrosion layer at various locations on the iron column. Furthermore, from the top to bottom of the iron column, the soluble chlorine content increased, leading to a deterioration in the stability of the corrosion layer. Groundwater was identified as the primary source of chloride contamination in the iron artifacts at the site through the analysis of environmental data. This investigation elucidates the gradient corrosion characteristics of large iron objects by chloride ions, underscores the critical role of groundwater in the deterioration of outdoor iron artifacts, and provides valuable insights for the development of targeted conservation strategies.