Environmental education as a means of combating growing environmental pollution: an optimized- explainable artificial intelligence (XAI) approach.

Mission: Educational

The development of medical imaging artificial intelligence (AI) systems for evaluating COVID‐19 patients has demonstrated potential for improving clinical decision making and assessing patient outcomes during the recent COVID‐19 pandemic. These have been applied to many medical imaging tasks, including disease diagnosis and patient prognosis, as well as augmented other clinical measurements to better inform treatment decisions. Because these systems are used in life‐or‐death decisions, clinical implementation relies on user trust in the AI output. This has caused many developers to utilize explainability techniques in an attempt to help a user understand when an AI algorithm is likely to succeed as well as which cases may be problematic for automatic assessment, thus increasing the potential for rapid clinical translation. AI application to COVID‐19 has been marred with controversy recently. This review discusses several aspects of explainable and interpretable AI as it pertains to the evaluation of COVID‐19 disease and it can restore trust in AI application to this disease. This includes the identification of common tasks that are relevant to explainable medical imaging AI, an overview of several modern approaches for producing explainable output as appropriate for a given imaging scenario, a discussion of how to evaluate explainable AI, and recommendations for best practices in explainable/interpretable AI implementation. This review will allow developers of AI systems for COVID‐19 to quickly understand the basics of several explainable AI techniques and assist in the selection of an approach that is both appropriate and effective for a given scenario.

While concern for the impact of humans on the environment dates back many centuries, modern environmentalism really began in the second half of the 20th century. We are now very aware of a number of “wicked problems” that are complex and impossible to solve. Such issues, which are interrelated at different levels, include climate change, biodiversity loss, water security, and poverty. These problems can be better understood with a knowledge of science, but they are not just “scientific” issues—they require knowledge from many other areas across the arts and humanities as well as the broad range of scientific disciplines. This article focuses on environmental and science education and, where relevant, suggests links to other cognate areas. One way of thinking about environmental and science education is as the place where environmental education and science education overlap. This is quite a fluid space, intellectually, partly because environmental education is itself conceptualized in many ways. It is important to point out that we are not simply concerned with environmental science, rather, this article identifies a growing need to reconceptualize the relationship between science education and environmental education.

Environmental education can trace many of its roots to science education, although the relationship between the two has been contested. With the growth of Education for Sustainable Development in the past decade or so the potential relationship between environmental education and science education has strengthened with a growing recognition that an understanding of ecological sustainability is essential if we are to achieve sustainable development. This foregrounding of the importance of an environmental science education has been happening at the same time as student interest in studying traditional science subjects is declining and concerns are being raised about the static nature of science education practices. However, environmental education and Education for Sustainable Development also remain marginalised in most schools and education systems. It thus seems timely to reconsider the nature of both environmental education and science education, and reconceptualise science education to their mutual benefit. The science education that emerges from this reconceptualisation will not be like that currently practiced as, within an ESD context and given the changing nature of youth, a reconceptualised science/environmental education will also need to explicitly address economic and social sustainability as well as ecological sustainability and the significance of “Education for all”.

The need for studies connecting the machine’s explainability with granularity is very important, especially for a detailed understanding of how data is fragmented and processed according to the domain of discourse. We develop a system called RYEL based on subject-matter experts about the legal case process, facts, pieces of evidence, and how to analyze the merits of a case. Through this system, we study the Explainable Artificial Intelligence (XAI) approach using Knowledge Graphs (KG) and enforcement unsupervised algorithms which results are expressed in an Explanatory Graphical Interface (EGI). The evidence and facts of a legal case are represented as knowledge graphs. Granular Computing (GrC) techniques are applied in the graph when processing nodes and edges using object types, properties, and relations. Through RYEL we propose new definitions for Explainable Artificial Intelligence (XAI) and Interpretable Artificial Intelligence (IAI) in a much better way and will help us to cover a technological spectrum that has not yet been covered and promises to be a new area of study which we call Interpretation-Assessment/Assessment-Interpretation (IA-AI) that consists not only in explaining machine inferences but the interpretation and assessment from a user according to a context. It is proposed a new focus-centered organization in which the XAI-IAI will be able to work and will allow us to explain in more detail the method implemented by RYEL. We believe our system has an explanatory and interpretive nature and could be used in other domains of discourse, some examples are: (1) the interpretation a doctor has about a disease and the assessment of using certain medicine, (2) the interpretation a psychologist has from a patient and the assessment for a psychological application treatment, (3) or how a mathematician interprets a real-world problem and makes an assessment about which mathematical formula to use. However, now we focus on the legal domain.KeywordsRYELExplanatory Graphical Interface (EGI)Interpretation-Assessment/Assessment-Interpretation (IA-AI)Explainable Artificial Intelligence (XAI)Granular Computing (GrC)Explainable legal knowledge representationCase-Based Reasoning (CBR)

This review focuses on the use of Interpretable Artificial Intelligence (IAI) and eXplainable Artificial Intelligence (XAI) models for data imputations and numerical or categorical hydroclimatic predictions from nonlinearly combined multidimensional predictors. The AI models considered in this paper involve Extreme Gradient Boosting, Light Gradient Boosting, Categorical Boosting, Extremely Randomized Trees, and Random Forest. These AI models can transform into XAI models when they are coupled with the explanatory methods such as the Shapley additive explanations and local interpretable model-agnostic explanations. The review highlights that the IAI models are capable of unveiling the rationale behind the predictions while XAI models are capable of discovering new knowledge and justifying AI-based results, which are critical for enhanced accountability of AI-driven predictions. The review also elaborates the importance of domain knowledge and interventional IAI modeling, potential advantages and disadvantages of hybrid IAI and non-IAI predictive modeling, unequivocal importance of balanced data in categorical decisions, and the choice and performance of IAI versus physics-based modeling. The review concludes with a proposed XAI framework to enhance the interpretability and explainability of AI models for hydroclimatic applications.

In 1988, New York City’s West Harlem community had a problem. The recently opened North River Sewage Treatment Plant, which stretches eight blocks along the Hudson River, was doing a poor job of processing about 170 million gallons of raw sewage daily. Residents were concerned about the foul smells coming from the plant, and parents complained that their children were suffering from respiratory problems. The community knew it needed help, but it also needed something else: information on the exposures it was facing, on the health effects of those exposures, and on the courses of action open to the people. When the community mobilized months later to form West Harlem Environmental Action Inc. (WE ACT), it had taken the first step toward cultivating just that sort of environmental literacy.

Educational systems should warrant learning needs of the population they serve offering a diversity of educational agents, strategies, and answers to the needs of those that seek knowledge (Caeiro, Martinho, Azeiteiro, & Carapeto, 2004). In Portugal the experience of teaching subjects related to environmental sciences via open distance learning started in 1995 at Universidade Aberta (a public university specially dedicated to the open distance learning of graduate and undergraduate courses). This experience began with general ecology, and in view of the interest showed by students (and in fact by a wider public) the university later offered other subjects such as environmental education and water pollution. Today we have a number of different subjects within the vast area of environmental sciences and are preparing an undergraduate programme in view of the recent Bolonha Agreement. The university also offers post-graduate programmes that bring together the environment and the citizen participation. The aim is to heighten the interests of our students in scientific subjects related to the environment as well as providing a practical perspective of what they can do as active citizens. The programmes are supported by necessary tools that enable students to critically analyse and discuss press articles about the environment, protocols that are designed to make industries “greener”, as well as government decisions.

XAI is critical for establishing trust and enabling the appropriate development of machine learning models. By offering transparency into how these models make judgements, XAI enables researchers and users to uncover potential biases, admit limits, and eventually enhance the fairness and dependability of AI systems. In this paper, we demonstrates two techniques, LIME and SHAP, used to improve the interpretability of machine learning models. Assessing Explainable AI (XAI) approaches is critical in searching for transparent and interpretable artificial intelligence (AI) models. Explainable AI (XAI) approaches are designed to provide insight into how complex models make decisions. This paper thoroughly analyzes two prominent XAI methods: Shapley Additive explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME). This study aims to understand the decision made by a machine learning model and how the model came to that decision. We discuss the approaches and framework of both LIME and SHAP and assess their behavior in predicting the model's outcome.

XAI is critical for establishing trust and enabling the appropriate development of machine learning models. By offering transparency into how these models make judgements, XAI enables researchers and users to uncover potential biases, admit limits, and eventually enhance the fairness and dependability of AI systems. In this paper, we demonstrates two techniques, LIME and SHAP, used to improve the interpretability of machine learning models. Assessing Explainable AI (XAI) approaches is critical in searching for transparent and interpretable artificial intelligence (AI) models. Explainable AI (XAI) approaches are designed to provide insight into how complex models make decisions. This paper thoroughly analyzes two prominent XAI methods: Shapley Additive explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME). This study aims to understand the decision made by a machine learning model and how the model came to that decision. We discuss the approaches and framework of both LIME and SHAP and assess their behavior in predicting the model's outcome.

Objective: This study analyzes the trend of implementing environmental education in science research. Method: This research was conducted using the bibliometric literature study method. The data collection of this study used a Scopus database and was analyzed by the Vosviewer application. Result: From this study known that there is a significant increase in environmental education science research. The highest number of publications carried out in 2021 was six articles. The results of the VOSviewer visualization found 3 clusters red, green, and blue. Red cluster show related keyword research about education, curriculum, learning science, and education program. Green cluster show related keyword research about environmental education and science education. Blue cluster show related keyword research about sustainable development, science and technology, environmental technology, environmental science, and environmental sustainability. From the cluster, there are known that some theme related can be used to combine and use to research environmental education in science. Novelty: Analysis of these research trends can be used as a reference and a means of developing self-abilities concerning being an environmental educator in schools. Implementing environmental education can make students better understand and explore their abilities in science.

<p indent="0mm">Mitochondria, as the main site of cellular aerobic respiration, are organelles that provide energy for cells. The mitochondrial genomes are independent of the nuclear genome, known as mitochondrial DNA (mtDNA). mtDNA encodes 37 genes, including 13 respiratory chain-related polypeptides, 22 tRNAs and 2 rRNA genes. Mitochondrial abnormalities can directly reduce cellular ATP synthesis and thus generate insufficient cellular energy. The regulation of mtDNA copy number and epigenetics is crucial for the basic functions of mitochondria. After entering the cells of organisms, environmental pollutants elevate reactive oxygen species (ROS), causing oxidative stress in the organism and resulting in abnormal metabolism and various diseases. Compared with nuclear DNA, mtDNA is more susceptible to oxidative stress because of its proximity to the site of oxidative phosphorylation (OXPHOS) and lack of histone protection and sufficient DNA damage repair capacity. Exposure to various environmental pollutants can induce excessive accumulation of ROS, which leads to changes in mtDNA copy number and epigenetic modifications of mtDNA. An increasing number of studies focus on abnormal mtDNA as a possible biomarker for the exposure and toxicity of environmental pollutants. In this article, we briefly introduce the physiological functions and regulatory mechanisms of mitochondria and mtDNA copy number. Environment pollutant exposures often cause mitochondrial damage, which may alter mtDNA copy number, leading to mitochondrial abnormalities and impairing cell function. Studies have found that mitochondrial dysfunction is related to the occurrence and development of various diseases (e.g., cancer, diabetes, cardiovascular disease, neurodegenerative diseases, etc.). Noteworthily, decreased mtDNA copy number in germ cells blocks embryonic development. Next, along with the associated proteins found in recent studies, possible epigenetic modifications present on mtDNA (e.g., 5-methylcytosine, 5-hydroxymethylcytosine and N6-methyladenine) are also summarized. A study identified mtDNMT1 in the mitochondrial matrix, which was suggested to be a methyltransferase for mtDNA 5mC. Since 5hmC modification on mtDNA was first reported in 2011, the results of studies on mtDNA 5hmC have been conflicting. However, some research groups found that Tet1 and Tet2 may be involved in the formation of mtDNA 5hmC. A higher level of 6mA modification than nuclear DNA was suggested to be detected in mtDNA, and the METTL4 protein is a potential mtDNA 6mA methyltransferase. Nonetheless, the study on mtDNA methylation is of intensive interest. We reviewed the effects of multiple common environmental pollutants (e.g., PM, black carbon, nicotine, heavy metal particles, etc.) on mitochondrial DNA from two aspects: (1) Environmental pollutants exposure causes mtDNA copy number changes, which may increase disease risk; (2) environmental pollutant exposure alters methylation levels of certain genes in mtDNA. In the first aspect, exposure to different pollutants, or even the same pollutant, resulted in different changes in mtDNA copy number. It suggests that the same environmental pollutants may also affect mtDNA copy number through different mechanisms and pathways. In the second aspect, changes in the methylation levels of D-loop and gene regions on mtDNA caused by pollutant exposure can affect mitochondrial physiological function by affecting mitochondrial DNA replication and mitochondrial-encoded protein expression. We prospect and discuss how to perform further study on the effect of environmental pollutants on mtDNA and its molecular mechanism. The following two aspects should be improved in future pollutants-mtDNA studies: (1) Develop more convenient methods for the extraction of mtDNA from less than million cells to a high purity. This will facilitate the detection and sequencing of mtDNA for diverse purposes; (2) to achieve accurate identification of mtDNA methylation sites in small number of cells and eliminate the interference of mtDNA heterogeneity, the mtDNA methylation sequencing method should be further innovated.

This auto-ethnographic article explores how land-based education might challenge Western environmental science education (ESE) in an Indigenous community. This learning experience was developed from two perspectives: first, land-based educational stories from Dene First Nation community Elders, knowledge holders, teachers, and students; and second, the author’s critical self‐reflections focusing on how land-based education could offer unlearning, rethinking, relearning, and reclaiming ESE. This auto-ethnography provides particular insights into who we are as environmental educators, the challenges in Western ESE, why land-based education matters, why and how a significant move should be made from Western ESE to land-based ESE, and how land-based education offers a bridge between Western and Indigenous education.

Eastern Africa stands at a critical crossroad where environmental degradation, biodiversity loss, and pollution are intensifying climate vulnerability and deepening interconnected challenges such as food and nutrition insecurity, poverty, conflict, and public health risks. In this context, environmental science education is not merely an academic pursuit, but rather, it’s a strategic foundation for sustainable development across the region. This study presents a regional landscape analysis of environmental science training using a mixed-method evaluation of 42 academic programmes across 30 universities in Kenya, Uganda, Tanzania, Rwanda, and Ethiopia, complemented by insights from interviews with 30 faculty leaders. The findings reveal a sector struggling for relevance and impact, yet constrained by structural and resource limitations. Teaching capacity remains stretched with 57% of institutions operating as student: staff ratios between 20:1 and 40:1 which is well above global benchmarks – hence limiting meaningful mentorship, experiential learning, and research productivity. Infrastructure gaps are equally significant where fewer than 40% of programmes report adequate laboratory facilities, less than one-third have sufficient field equipment or reliable transport, and the post-pandemic transition to digital learning continues to be undermined by weak technological systems. Curriculum relevance also emerges as a pressing concern. While environmental challenges are increasingly localized, 70% of programmes rely on outdated learning materials. Indigenous and community knowledge systems are incorporated in only 35% of the curricula, and formal industry-linked internships exists in just 28% of programmes essentially leaving many graduated insufficiently prepared for practices oriented environmental problem solving. Although 62% of the programmes benefits from PhD qualified faculty, persistent brain drain threatens institutional continuity and leadership. Encouragingly, nearly 40% of institutions are currently undertaking curriculum reforms and strengthening inter-university collaboration. The study underscores that advancing sustainable development in Eastern Africa will require more than incremental improvements. It calls for systematic transformation through pedagogical innovations, strategic investment in learning infrastructure, and stronger partnership between universities, industry, and policy actors to align environmental science education with the regions urgent socio-ecological realities.

Advancements in brain tumor prognosis, especially for glioma, demand a transparent and comprehensive diagnostic framework that not only ensures high accuracy but also fosters interpretability for clinical decision-making. To meet this need, an interpretable artificial intelligence (AI) approach is proposed, combining machine learning (ML) and deep learning (DL) models enriched by explainable artificial intelligence (XAI) techniques. The approach focuses on enhancing prediction accuracy while ensuring the process remains understandable and traceable by medical professionals. Patient-centric data such as clinical histories and genetic profiles are integrated to enable more personalized diagnostics. A multi-stage methodology is adopted, employing multiple feature selection techniques including Vital Feature Selection (FS), Mutual Information FS, Principal Component Analysis (PCA) FS, and Pearson Correlation Coefficient FS. These techniques help in reducing dimensionality and improving model generalization without losing critical predictive markers. A combination of classical ML algorithms and advanced ensemble methods such as the Voting Classifier is utilized to maximize glioma grading accuracy. The Voting Classifier exhibits perfect performance, achieving 100% accuracy using essential features and mutual information-based selection. In contrast, deep learning models, particularly Convolutional Neural Networks (CNNs), achieve commendable results with 91% accuracy when PCA-based features are applied and 90% with Pearson coefficient-based features. The fusion of these techniques under the umbrella of interpretable AI ensures not only high performance but also enables medical experts to understand the decision pathways involved in classification outcomes. This transparency bridges the gap between black-box AI systems and real-world clinical applicability. Overall, the integration of diverse feature selection strategies, patient-specific data, robust machine learning models, and explainable frameworks presents a significant leap toward precise, trustworthy, and interpretable brain tumor prognosis.