Ensuring consistent quality in friction stir welding (FSW) remains challenging because defect formation and mechanical performance arise from complex thermo-mechanical interactions. This study presents an interpretable convolutional neural network-bidirectional long short-term memory (CNN–BiLSTM) framework for patch-level surface-defect detection and weld-level tensile-strength classification in ultrasonic vibration-assisted FSW AA2060-T8E30 joints. Surface images from 54 welds were divided into six ordered patches to preserve contextual information along the welding direction. DenseNet121 and VGG16 were evaluated as standalone CNNs and hybrid CNN–BiLSTM models. DenseNet121–BiLSTM achieved the best defect-detection performance, with 98.15% fixed-test accuracy and 95.54% mean leave-one-weld-out accuracy, compared with 92.59% and 90.23% for VGG16–BiLSTM. The DenseNet121–BiLSTM model was then applied to three-class tensile-strength classification relative to base-material ultimate tensile strength, achieving 88.89% fixed-test accuracy and 77.78% ± 7.41% under repeated stratified grouped cross-validation. Gradient-weighted Class Activation Mapping (Grad-CAM) visualisations identified surface regions associated with the predictions, while a graphical user interface integrated image input, classification, confidence reporting, and interpretation. The results demonstrate the feasibility of using standard weld-surface images for both visible defect detection and preliminary tensile-strength categorisation to support post-weld decision-making.
Rapid and accurate building damage assessment after tornadoes is critical for emergency response and recovery, yet automated methods struggle with the visual complexity of tornado-induced wreckage, primarily due to severe domain shift and extreme class imbalance. We introduce ASTRA, a large-scale framework evaluating 79 open-source models (67 CNNs and 12 Transformers-based architectures) across 2,420 experiments on an expertly curated Quad-State Tornado Damage (QSTD) benchmark of 5,517 street-view images annotated under the IN-CORE engineering taxonomy. We find that achieving strong performance hinges on the interaction among architecture, optimization, and pre-training source, not on architecture alone. Attention-based models were acutely optimization-sensitive: although bottom-tier under the default configuration, they recovered by + 25 to + 38 Macro-F1-points once optimization was corrected, either by switching from Adam to SGD or, equivalently, lowering the learning rate. A controlled ablation attributes this swing primarily to the learning rate, with a smaller optimizer effect specific to Vision Transformers; CNNs showed no comparable reversal. Furthermore, we uncover a counterintuitive behavior in which scene-centric Places365 pre-training did not surpass object-centric ImageNet after optimization, despite its closer semantic proximity to building and streetscape scenes and its competitive zero-shot performance. In a strict zero-shot test on the held-out Tuscaloosa-Moore Tornado Damage dataset of 2,393 images, naive baselines failed to transfer, while QSTD-optimized models achieved substantially better performance. The champion model, ConvNeXt-Base, achieved a + 34.6 Macro-F1-point gain over its baseline, despite temporal, sensor, and geographic shifts. Consequently, ASTRA offers practical optimization guidelines and a rigorously validated, open-source foundation for automated tornado-damage assessment. Project Website: https://crumeike.github.io/astra-page.
Urban vegetation provides substantial health benefits in US cities, yet the protection that existing green cover delivers has not been quantified across a broad national sample. We conducted a census-tract-level health impact assessment across the 200 most populated US cities, estimating premature deaths, stroke cases, and dementia cases attributable to current greenness and the additional burden preventable through a 10% greenness increase. Using peak-greenness Normalized Difference Vegetation Index (NDVI) values derived from Sentinel-2 satellite imagery at 10 m resolution, population attributable fractions applied to county- and state-level baseline disease rates, and dose–response functions from published cohort studies and meta-analyses, we estimated that existing urban vegetation is associated with 133,698 fewer premature deaths annually (95% uncertainty interval [UI]: 97,056 to 214,462), 24,721 fewer stroke cases (95% UI: 11,700 to 31,784), and 16,349 fewer dementia cases (95% UI: 10,609 to 22,403). A 10% vegetation increase would be associated with an additional 18,100 fewer deaths, 3,288 fewer strokes, and 2,125 fewer dementia cases. Per-capita benefits vary 14-fold across cities, driven principally by vegetation level. Equity analysis using the CDC Social Vulnerability Index across 28,620 census tracts shows that the most socially vulnerable neighborhoods have 18% lower vegetation and receive 20% fewer mortality benefits per 100,000 adults than the least vulnerable. These estimates represent the statistical burden attributable to current vegetation exposure rather than individually identifiable prevented events, and they quantify what is at risk when existing urban green space is removed. We identify 4,185 doubly burdened tracts as priority targets for equitable greening investment.
Livestock systems represent a considerable environmental challenge. In response, various scientists, non-governmental organisations, and policy makers claim that Western populations in particular need to sharply reduce meat consumption. Given people’s attachment to meat, many of these actors favour hard policy interventions based on a range of systemic financial and legal reforms that would go beyond mere nudging and the formulation of recommendations, including the top-down imposition of meat taxes and bans, as well as herd size reductions, which would lead to sharply higher prices. However, arguments in support of such policies tend to oversimplify the issue, ignoring regional variations, mitigation potential, and broader ecological and nutritional contexts. The focus of this article is on dietary greenhouse gas (GHG) emissions as a main target for environmental policymaking, with all livestock production in the West contributing 2.6
Reasoning and reflection are essential professional thinking skills for health professionals, including occupational therapists. Clear definitions are needed to communicate a theory of professional thinking skills that includes both reasoning and reflection. Our aim was to understand how reasoning and reflection are defined, and therefore differentiated, in occupational therapy literature. We conducted a scoping review consistent with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews checklist. We searched CINAHL, PubMed, PsycINFO, Web of Science, Embase, and MEDLINE, no date restrictions, including peer-reviewed English-language literature related to occupational therapy education and practice that contained a definition of clinical reasoning, professional reasoning, critical thinking, reflective practice, reflection, or critical reflection. We extracted data using a framework for defining constructs. In total, 139 articles were included; 96 defined clinical reasoning, 15 defined professional reasoning, 12 defined critical thinking, 14 defined reflection, 16 defined reflective practice, and 10 defined critical reflection. Across these, adequate definitions were not consistent or consistently present. Most of our constructs of interest were identified as 'processes', and they appear to be considered overlapping processes. Our findings reemphasize the call for researchers to explicitly define professional thinking skills, including superordinate categories and detailed characteristics.
