Large Language Model (LLM) usage in recent years has become increasingly widespread in the Artificial Intelligence in Education (AIED) community. While LLMs offer unique avenues for learners and educators, using LLMs comes with computational and environmental costs. These costs are mostly hidden due to a lack of standardised procedures to measure and report these impacts. To address this gap, we first conducted a literature review of all papers published as part of the AIED 2025 conference proceedings, determining if and how computational or environmental costs of LLMs are reported. Most projects use LLMs, but few report computational resources used and almost none discuss environmental impacts of LLMs as an ethical concern. To address this lack of standardised reporting practices, we propose an open-source method for systematically measuring and reporting the computational expense of LLMs and environmental impact of running Machine Learning (ML) AIED systems. We provide software solutions to measure the carbon footprint for both local and cloud based hardware. We also provide an easy-to-use formula to calculate the computational expense of frontier LLMs even when the exact number
Artificial intelligence (AI) is often presented as a key tool for addressing societal challenges, such as climate change. At the same time, AI's environmental footprint is expanding increasingly. This report describes the systemic environmental risks of artificial intelligence, in particular, moving beyond direct impacts such as energy and water usage. Systemic environmental risks of AI are emergent, cross-sector harms to climate, biodiversity, freshwater, and broader socioecological systems that arise primarily from AI's integration into social, economic, and physical infrastructures, rather than its direct resource use, and that propagate through feedbacks, yielding nonlinear, inequitable, and potentially irreversible impacts. While these risks are emergent and quantification is uncertain, this report aims to provide an overview of systemic environmental risks. Drawing on a narrative literature review, we propose a three-level framework that operationalizes systemic risk analysis. The framework identifies the structural conditions that shape AI development, the risk amplification mechanisms that propagate environmental harm, and the impacts that manifest as observable ecological
The space-borne gravitational wave detectors such as TianQin offers a new window to test General Relativity by observing the early inspiral phase of stellar-mass binary black holes. A key concern arises if these stellar-mass binary black holes reside in gaseous environments such as active galactic nucleus accretion disks, where environmental effects imprint detectable modulations on the gravitational waveform. Using Bayesian inference on simulated signals containing both environmental and dipole deviation, we have assessed the extent to which the presence of environmental effects affects the detectability of dipole radiation. Our results demonstrate that even in the presence of strong environmental coupling, the dipole parameter can be recovered with high precision, and the evidence for dipole radiation remains distinguishable. Crucially, we find that the existence of environmental effects does not fundamentally impede the identification of dipole radiation, provided both effects are simultaneously modelled in the inference process. This study establishes that future tests of modified gravity with space-borne observatories can remain robust even for sources in astrophysical environ
This study investigates the interconnectivity of firms and Environmental Justice Organizations (EJOs) involved in socio-environmental conflicts worldwide, using data from the Environmental Justice Atlas (EJAtlas). By constructing a multilayer network that links firms, conflicts, and EJOs, the research applies social network analysis to evaluate the simultaneous involvement of these actors across multiple disputes. Both projected networks of firms and EJOs have been analysed by aggregating nodes by categories and countries to reveal structural differences. Findings reveal a stark contrast between the interconnectedness of firms and EJOs. Multinational corporations form a cohesive global network, enabling them to coordinate strategies and exert influence across regions. Conversely, EJOs are fragmented, often operating in isolated clusters with limited interconnection but forming a robust, decentralized and self-organized global network. Firms network present a strong dependence on pertaining conflict category while EJOs network does not depend on conflict category. This structural difference suggests a risk of systemic and structural coordination for firms towards exploitative expans
Purpose: We investigated the utilization of privacy-preserving, locally-deployed, open-source Large Language Models (LLMs) to extract diagnostic information from free-text cardiovascular magnetic resonance (CMR) reports. Materials and Methods: We evaluated nine open-source LLMs on their ability to identify diagnoses and classify patients into various cardiac diagnostic categories based on descriptive findings in 109 clinical CMR reports. Performance was quantified using standard classification metrics including accuracy, precision, recall, and F1 score. We also employed confusion matrices to examine patterns of misclassification across models. Results: Most open-source LLMs demonstrated exceptional performance in classifying reports into different diagnostic categories. Google's Gemma2 model achieved the highest average F1 score of 0.98, followed by Qwen2.5:32B and DeepseekR1-32B with F1 scores of 0.96 and 0.95, respectively. All other evaluated models attained average scores above 0.93, with Mistral and DeepseekR1-7B being the only exceptions. The top four LLMs outperformed our board-certified cardiologist (F1 score of 0.94) across all evaluation metrics in analyzing CMR reports.
Microorganisms are ubiquitous in nature, and microbial activities are closely intertwined with the entire life cycle system and human life. Developing novel technologies for the detection, characterization and manipulation of microorganisms promotes their applications in clinical, environmental and industrial areas. Over the last two decades, terahertz (THz) technology has emerged as a new optical tool for microbiology. The great potential originates from the unique advantages of THz waves including the high sensitivity to water and inter-/intra-molecular motions, the non-invasive and label-free detecting scheme, and their low photon energy. THz waves have been utilized as a stimulus to alter microbial functions, or as a sensing approach for quantitative measurement and qualitative differentiation. This review specifically focuses on recent research progress of THz technology applied in the field of microbiology, including two major parts of THz biological effects and the microbial detection applications. In the end of this paper, we summarize the research progress and discuss the challenges currently faced by THz technology in microbiology, along with potential solutions. We also
Artificial Intelligence (AI) is changing the world, but its impacts on the environment and human well-being remain uncertain. We conducted a systematic literature review of 1,291 studies selected from 6,655 records, identifying the main impacts of AI and how they are assessed. The evidence reveals an uneven landscape: 72% of environmental studies focus narrowly on energy use and CO2 emissions, while only 11% consider systemic effects. Well-being research is largely conceptual and overlooks subjective dimensions. Strikingly, 83% of environmental studies portray AI's impacts as positive, while well-being analyses show a near-even split overall (44% positive; 46% negative). However, this split masks differences across well-being dimensions. While the impacts of AI on income and health are expected to be positive, its impacts on inequality, social cohesion, and employment are expected to be negative. Based on our findings, we suggest several areas for future research. Environmental assessments should incorporate water, material, and biodiversity impacts, and apply a full life-cycle perspective, while well-being research should prioritise empirical analyses. Evaluating AI's overall impa
Mathematical models are increasingly a part of microbiological research. Here, we share our perspective on how modeling advances the discipline by: (i) enforcing logical consistency, (ii) enabling quantitative prediction, (iii) extracting hidden parameters from data, and (iv) generating intuitive understanding. We map a spectrum of modeling frameworks, from whole-cell simulations to minimal logistic growth equations, and provide interactive examples for some common frameworks. Building on this overview, we outline pragmatic criteria for choosing an appropriate level of description to capture phenomena of interest. Finally, we present a case study in modeling of microbial ecosystems from our own work to illustrate how mechanistic modeling can yield generalizable intuition. This perspective aims to be an introductory roadmap for integrating mathematical modeling into experimental microbiology.
This paper presents a comprehensive dataset of LoRaWAN technology path loss measurements collected in an indoor office environment, focusing on quantifying the effects of environmental factors on signal propagation. Utilizing a network of six strategically placed LoRaWAN end devices (EDs) and a single indoor gateway (GW) at the University of Siegen, City of Siegen, Germany, we systematically measured signal strength indicators such as the Received Signal Strength Indicator (RSSI) and the Signal-to-Noise Ratio (SNR) under various environmental conditions, including temperature, relative humidity, carbon dioxide (CO$_2$) concentration, barometric pressure, and particulate matter levels (PM$_{2.5}$). Our empirical analysis confirms that transient phenomena such as reflections, scattering, interference, occupancy patterns (induced by environmental parameter variations), and furniture rearrangements can alter signal attenuation by as much as 10.58 dB, highlighting the dynamic nature of indoor propagation. As an example of how this dataset can be utilized, we tested and evaluated a refined Log-Distance Path Loss and Shadowing Model that integrates both structural obstructions (Multiple W
Machine learning inference occurs at a massive scale, yet its environmental impact remains poorly quantified, especially on low-resource hardware. We present ML-EcoLyzer, a cross-framework tool for measuring the carbon, energy, thermal, and water costs of inference across CPUs, consumer GPUs, and datacenter accelerators. The tool supports both classical and modern models, applying adaptive monitoring and hardware-aware evaluation. We introduce the Environmental Sustainability Score (ESS), which quantifies the number of effective parameters served per gram of CO$_2$ emitted. Our evaluation covers over 1,900 inference configurations, spanning diverse model architectures, task modalities (text, vision, audio, tabular), hardware types, and precision levels. These rigorous and reliable measurements demonstrate that quantization enhances ESS, huge accelerators can be inefficient for lightweight applications, and even small models may incur significant costs when implemented suboptimally. ML-EcoLyzer sets a standard for sustainability-conscious model selection and offers an extensive empirical evaluation of environmental costs during inference.
With the growth of global maritime transportation, energy optimization has become crucial for reducing costs and ensuring operational efficiency. Shaft power is the mechanical power transmitted from the engine to the shaft and directly impacts fuel consumption, making its accurate prediction a paramount step in optimizing vessel performance. Power consumption is highly correlated with ship parameters such as speed and shaft rotation per minute, as well as weather and sea conditions. Frequent access to this operational data can improve prediction accuracy. However, obtaining high-quality sensor data is often infeasible and costly, making alternative sources such as noon reports a viable option. In this paper, we propose a transfer learning-based approach for predicting vessels shaft power, where a model is initially trained on high-frequency data from a vessel and then fine-tuned with low-frequency daily noon reports from other vessels. We tested our approach on sister vessels (identical dimensions and configurations), a similar vessel (slightly larger with a different engine), and a different vessel (distinct dimensions and configurations). The experiments showed that the mean abso
This paper introduces AIJIM, the Artificial Intelligence Journalism Integration Model -- a novel framework for integrating real-time AI into environmental journalism. AIJIM combines Vision Transformer-based hazard detection, crowdsourced validation with 252 validators, and automated reporting within a scalable, modular architecture. A dual-layer explainability approach ensures ethical transparency through fast CAM-based visual overlays and optional LIME-based box-level interpretations. Validated in a 2024 pilot on the island of Mallorca using the NamicGreen platform, AIJIM achieved 85.4\% detection accuracy and 89.7\% agreement with expert annotations, while reducing reporting latency by 40\%. Unlike conventional approaches such as Data-Driven Journalism or AI Fact-Checking, AIJIM provides a transferable model for participatory, community-driven environmental reporting, advancing journalism, artificial intelligence, and sustainability in alignment with the UN Sustainable Development Goals and the EU AI Act.
With the booming of the unconventional oil and gas industry, its inevitable damage to the environment and human health has attracted public attention. We applied text mining on a total 6057 the type of Environmental Health and Safety compliance reports from 2008 to 2018 lunched by the Department of Environmental Protection in Pennsylvania, USA, to discover the intern mechanism of environmental violations.
The study of microorganisms, or microbiology, has demonstrated significant development since its inception and is currently a key field of biological sciences that has a huge impact on modern society and scientific research. Over the centuries, this discipline has undergone significant changes, shaping our understanding of infectious diseases and food safety. Starting from the simplest observations of microscopic organisms such as bacteria, viruses, fungi and protozoa, and ending with modern molecular and genomic research methods. This article describes a brief historical path of microbiology development. The heuristic, morphological, physiological, immunological, and molecular genetic stages are the main periods into which the development of this science is traditionally divided, despite the lack of full-fledged and precise boundaries between them.
Advancements in artificial intelligence (AI) have transformed many scientific fields, with microbiology and microbiome research now experiencing significant breakthroughs through machine learning applications. This review provides a comprehensive overview of AI-driven approaches tailored for microbiology and microbiome studies, emphasizing both technical advancements and biological insights. We begin with an introduction to foundational AI techniques, including primary machine learning paradigms and various deep learning architectures, and offer guidance on choosing between traditional machine learning and sophisticated deep learning methods based on specific research goals. The primary section on application scenarios spans diverse research areas, from taxonomic profiling, functional annotation \& prediction, microbe-X interactions, microbial ecology, metabolic modeling, precision nutrition, clinical microbiology, to prevention \& therapeutics. Finally, we discuss challenges in this field and highlight some recent breakthroughs. Together, this review underscores AI's transformative role in microbiology and microbiome research, paving the way for innovative methodologies an
The Earth possesses many environmental extremes that mimic conditions on extraterrestrial worlds. The stratosphere at 30-40 km altitude closely resembles the surface of Mars in terms of pressure, temperature, and radiation levels (UV, proton, and Galactic cosmic rays). While microbial life in the troposphere is well documented, the true upper limit of Earth's biosphere remains unclear. The stratosphere offers a promising environment to explore microbial survival in such extreme conditions. Despite its significance to astrobiology, this region remains largely unexplored due to difficulties in access and avoiding contamination. To address this, we have developed SAMPLE (Stratospheric Altitude Microbiology Probe for Life Existence), a balloon-borne payload designed to collect dust samples from the stratosphere and return them in conditions suitable for lab analysis. The entire system is novel and designed in-house, with weight- and stress-optimized components. The main payload includes three pre-sterilized sampling trays and a controller that determines altitude and governs tray operation. One tray will remain closed during flight (airborne control) and another on the ground (cleanroo
Measuring the effectiveness of corporate environmental reports, it being highly qualitative and less regulated, is often considered as a daunting task. The task becomes more complex if comparisons are to be performed. This study is undertaken to overcome the physical verification problems by implementing data mining technique. It further explores on the effectiveness by performing exploratory analysis and structural equation model to bring out the significant linkages between the selected 10 variables. Samples of five hundred and thirty nine reports across various countries are used from an international directory to perform the statistical analysis like: One way ANOVA (Analysis of Variance), MDA (Multivariate Discriminant Analysis) and SEM (Structural Equation Modeling). The results indicate the significant differences among the various types of industries in their environmental reporting, and the exploratory factors like stakeholder, organization strategy and industrial oriented factors, proved significant. The major accomplishment is that the findings correlate with the conceptual frame work of GRI.
Microbiology culture reports contain critical information for important clinical and public health applications. However, microbiology reports often have complex, semi-structured, free-text data that present a barrier for secondary use. Here we present the development and validation of an open-source package designed to ingest free-text microbiology reports, determine whether the culture is positive, and return a list of SNOMED-CT mapped bacteria. Our rule-based natural language processing algorithm was developed using microbiology reports from two different electronic health record systems in a large healthcare organization, and then externally validated on the reports of two other institutions with manually-extracted results as a benchmark. Our algorithm achieved F-1 scores >0.95 on all classification tasks across both validation sets. Our concept extraction Python package, MicrobEx, is designed to be reused and adapted to individual institutions as an upstream process for other clinical applications, such as machine learning studies, clinical decision support, and disease surveillance systems.
Small Language Models (SLMs) offer computational efficiency and accessibility, yet a systematic evaluation of their performance and environmental impact remains lacking. We introduce SLM-Bench, the first benchmark specifically designed to assess SLMs across multiple dimensions, including accuracy, computational efficiency, and sustainability metrics. SLM-Bench evaluates 15 SLMs on 9 NLP tasks using 23 datasets spanning 14 domains. The evaluation is conducted on 4 hardware configurations, providing a rigorous comparison of their effectiveness. Unlike prior benchmarks, SLM-Bench quantifies 11 metrics across correctness, computation, and consumption, enabling a holistic assessment of efficiency trade-offs. Our evaluation considers controlled hardware conditions, ensuring fair comparisons across models. We develop an open-source benchmarking pipeline with standardized evaluation protocols to facilitate reproducibility and further research. Our findings highlight the diverse trade-offs among SLMs, where some models excel in accuracy while others achieve superior energy efficiency. SLM-Bench sets a new standard for SLM evaluation, bridging the gap between resource efficiency and real-wor
The carbon footprint of algorithms must be measured and transparently reported so computer scientists can take an honest and active role in environmental sustainability. In this paper, we take analyses usually applied at the industrial level and make them accessible for individual computer science researchers with an easy-to-use Python package. Localizing to the energy mixture of the electrical power grid, we make the conversion from energy usage to CO2 emissions, in addition to contextualizing these results with more human-understandable benchmarks such as automobile miles driven. We also include comparisons with energy mixtures employed in electrical grids around the world. We propose including these automatically-generated Energy Usage Reports as part of standard algorithmic accountability practices, and demonstrate the use of these reports as part of model-choice in a machine learning context.