Search Results (490)

The contemporary agricultural market is profoundly volatile, where agricultural prices are based on a complex supply chain, climatic irregularity or unscheduled market demand. Prices of crops need to be predicted in a reliable and timely manner for farmers, policy-makers and other stakeholders to take evidence-based decisions ultimately for the benefit towards sustainable agriculture and economic sustainability. Objective: The objective of this study is to develop and evaluate a comprehensive machine learning model for predicting agricultural prices incorporating logistic, economic and environmental considerations. It is the desire to make agriculture more profitable by building simple and accurate forecasting models. Methods: An assorted dataset was collected, which covers major factors to constitute the dataset of temperature, rainfall, fertiliser use, pest and disease attack level, cost of transportation, market demand-supply ratio and regional competitiveness. The data was subjected to pre-processing and feature extraction for quality control/quality assurance. Several machine learning models (Linear Regression, Support Vector Machines, AdaBoost, Random Forest, and XGBoost) were trained and evaluated using performance metrics such as R2 score, Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). Results: Out of the model approaches that were analysed, predictive performance was superior for XGBoost (with an R2 Score of 0.94, RMSE of 12.8 and MAE of 8.6). To generate accurate predictions, the ability to account for complex non-linear relationships between market and environmental information was necessary. Conclusions: The forecast model of the XGBoost-based prediction system is reliable, of low complexity and widely applicable to large-scale real-time forecasting of agricultural monitoring. The model substantially reduces the uncertainty of price forecasting, and does so by including multivariate environmental and economic aspects that permit more profitable management practices in a schedule for future sustainable agriculture. Full article

Environmental sustainability has emerged as a global imperative in the context of accelerating climate change, rapid industrialization, and increasing ecological stress. Ecological quality is necessary for countries to pursue because of its overall benefits to the entire ecosystem. Therefore, due to the significant role that the United Arab Emirates (UAE) plays in the global environment, this research examines the role of Green Innovation (GI), Financial Globalization (FG), Economic Growth (GDP), and Foreign Direct Investment (FDI) in influencing Environmental Quality (EQ) in the UAE from 1991–2022. The UAE is well known for these economic indices. Furthermore, this study employed the innovative Quantile Augmented Dickey–Fuller (QADF) test, Wavelet Quantile Regression (WQR), Wavelet Quantile Correlation (WQC), and Quantile-on-Quantile Granger Causality (QQGC). WQR is able to identify connections between series over a range of quantiles and periods. WQC evaluates the co-movement between variables at different quantile levels and across several scales. The QQGC captures the causal effect of the regressors on EQ. These methods are quite advanced compared to other traditional econometric methods. Based on the outcome of the WQR and WQC methods, evidence shows that GI contributes to EQ across all quantiles in the short, medium, and long term, while FG, GDP, and FDI reduces EQ across all quantiles in the short, medium, and long term. The QQGC results also affirm causality among the variables, implying that GI, FG, GDP, and FDI can predict EQ across all quantiles. This research recommends that the UAE should improve on its environmental policies both domestically and internationally by making them more stringent, and continue to promote clean energy investments. Full article

Ensuring the safe, efficient, and economically viable operation of irrigation and drainage infrastructures is essential for long-term system resilience. This field-based study presents a comparative evaluation of the semi-quantitative William T. Fine (WF) method and a simplified probability–consequence (SM) approach applied in the Lis Valley Irrigation and Drainage Association (Leiria, Portugal). Monthly on-site observations of routine maintenance and conservation activities were conducted between January 2023 and December 2024, covering eight main operation types and resulting in 87 distinct occupational risk scenarios (N = 87). The mean Hazard Risk Score (HRS) was 88.9 ± 51.1, corresponding predominantly to “Substantial” risk levels according to the William T. Fine classification (HRS = 70–200). Both methods consistently identified the highest-risk activities—tractor rollover, work at height, and boat-based removal of aquatic plants. Quantitative differences emerged for medium and chronic hazards; WF produced a wider dispersion of risk scores across tasks, while the SM aggregated most hazards into a limited number of intervention classes (74% classified as Intervention Level II and 26% as Level III). These differences reflect complementary methodological limitations; WF requires greater data input and expert judgment but offers finer prioritization, whereas SM enables rapid field application but tends to group ergonomic and low-intensity hazards when consequences are not immediately observable. Based on these findings, a combined assessment framework is proposed, integrating the discriminative capacity of WF with the operational simplicity of SM. Recommended mitigation measures include targeted personal protective equipment, task rotation, focused training, and technology-assisted monitoring to reduce worker exposure. The methodology is readily replicable for Water Users’ Associations with similar operational contexts and supports evidence-based decision-making for sustainable irrigation management. From a sustainability perspective, this integrated risk assessment framework supports safer working conditions, more efficient maintenance planning, and informed policy decisions for the long-term management of irrigation and drainage infrastructures. Full article

The UK’s net-zero by 2050 commitment necessitates urgent housing sector decarbonisation, as residential buildings contribute approximately 17% of national emissions. Post-1950 construction prioritised speed over efficiency, creating energy-deficient housing stock that challenges climate objectives. Current retrofit policies focus primarily on technological solutions—insulation and heating upgrades—while neglecting broader sustainability considerations. This research advocates systematically integrating Circular Economy (CE) principles into residential retrofit practices. CE approaches emphasise material circularity, waste minimisation, adaptive design, and a lifecycle assessment, delivering superior environmental and economic outcomes compared to conventional methods. The investigation employs mixed-methods research combining a systematic literature analysis, policy review, stakeholder engagement, and a retrofit implementation evaluation across diverse UK contexts. Key barriers identified include regulatory constraints, workforce capability gaps, and supply chain fragmentation, alongside critical transition enablers. An evidence-based decision-making framework emerges from this analysis, aligning retrofit interventions with CE principles. This framework guides policymakers, industry professionals, and researchers in the development of strategies that simultaneously improve energy-efficiency, maximise material reuse, reduce embodied emissions, and enhance environmental and economic sustainability. The findings advance a holistic, systems-oriented approach, positioning housing as a pivotal catalyst in the UK’s transition toward a circular, low-carbon built environment, moving beyond isolated technological fixes toward a comprehensive sustainability transformation. Full article

One major factor influencing the development of eco-friendly policies and the implementation of climate change mitigation strategies is the accurate projection of CO₂ emissions. Traditional statistical models face significant limitations in capturing complex nonlinear interactions within high-dimensional emissions data. Advanced deep learning architectures offer new opportunities to overcome these computational challenges due to their strong pattern-recognition capabilities. This paper evaluates four distinct deep learning architectures for CO₂ emissions forecasting: Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), Hybrid Convolutional–LSTM (CNN–LSTM) systems, and Dense Neural Networks (DNNs). A comprehensive comparison is conducted using consistent training protocols, hyperparameters, and performance metrics across five prediction horizons (1, 3, 6, 12, and 24 steps ahead) to reveal architecture-specific degradation patterns. Furthermore, analyzing emissions by category provides insight into the suitability of each architecture for varying levels of pattern complexity. LSTM-based models demonstrate particular strength in modeling long-term temporal dependencies, making them well-suited for integration into long-range environmental policy planning frameworks. Overall, this study provides empirical evidence supporting the use of neural networks in climate modeling and proposes criteria for selecting optimal architectures based on forecasting horizon and computational constraints. Full article

Electromobility provides an effective solution for developing countries to reduce dependence on fossil fuels, enhance energy security, and increase environmental sustainability. The current study evaluates the feasibility of implementing electric vehicles (EVs) powered by renewable energy in developing countries. Based on qualitative methods, including expert interviews, it discusses existing transportation systems, the benefits of EVs, and significant constraints such as poor infrastructure, high initial investment, and ineffective policy structures. Evidence further suggests that EV adoption is likely to bring considerable benefits, particularly in cities with high population densities, adequate infrastructure, and supportive regulations that facilitate rapid adoption. Countries like India and Kenya have reduced their fuel import bills and created new jobs. At the same time, cities such as Bogota and Nairobi have seen improved air quality through the adoption of electric public transit. However, the transition requires investments in charging infrastructures and improvements in power grids. Central to this is government backing, whether through subsidy or partnership. Programs like India’s Faster Adoption and Manufacturing of Hybrid and Electric Vehicles (FAME) initiative and China’s subsidy program are prime examples of such support. The study draws on expert interviews to provide context-specific insights that are often absent in global EV discussions, while acknowledging the limitations of a small, regionally concentrated sample. These qualitative findings complement international data and offer grounded implications for electromobility planning in developing contexts. It concludes that while challenges remain, tailored interventions and multi-party public–private partnerships can make the economic and environmental promise of electromobility in emerging markets a reality. Full article

Biodiversity knowledge is fundamental to conservation planning and sustainable environmental decision-making; however, general-purpose Large Language Models (LLMs) frequently produce hallucinations when responding to biodiversity-related queries. To address this challenge, we propose BioChat, a domain-specific question-answering system that integrates a Retrieval-Augmented Generation (RAG) framework with a Re-Ranker–based retrieval and routing mechanism. The system is built upon a verified biodiversity dataset curated by the National Institute of Biological Resources (NIBR), comprising 25,593 species and approximately 970,000 structured data points. We systematically evaluate the effects of embedding selection, routing strategy, and generative model choice on factual accuracy and hallucination mitigation. Experimental results show that the proposed Re-Ranker-based routing strategy significantly improves system reliability, increasing factual accuracy from 47.9% to 71.3% and reducing hallucination rate from 34.0% to 24.4% compared with Naive RAG baseline. Among the evaluated LLMs, Qwen2-7B-Instruct achieves the highest factual accuracy, while Gemma-2-9B-Instruct demonstrates superior hallucination control. By delivering transparent, verifiable, and context-grounded biodiversity information, BioChat supports environmental education, citizen science, and evidence-based conservation policy development. This work demonstrates how trustworthy AI systems can serve as sustainability-enabling infrastructure, facilitating reliable access to biodiversity knowledge for long-term ecological conservation and informed public decision-making. Full article

Incivility and civility have been studied for more than a century across disciplines and in many areas ranging from workplaces to communication, the digital world, and everyday life. They are often used to the detriment of marginalized groups. Their negative use is seen to set the groundwork for other negative treatments, such as bullying and harassment, impacting the social climate in a negative way. Ostracism is seen to be linked to incivility. Disabled people disproportionally face negative treatments, such as bullying and harassment, and experience a negative social climate, as highlighted by the UN Convention on the Rights of People with Disabilities, suggesting that they also disproportionately experience incivility and ostracism. Climate surveys aim to expose toxic social climate in workplaces, schools, and communities caused by incivility, ostracism, bullying, and harassment. As such, how incivility, civility, ostracism, and the design of climate surveys are discussed in the literature is of importance to disabled people. We could find no review that analyzed the use of climate surveys beyond individual surveys and the concepts of incivility and ostracism in relation to disabled people. The objective of our study was to contribute to filling this gap by analyzing the academic literature present in SCOPUS, EBSCO HOST (70 databases), and Web of Science, performing keyword frequency and content analysis of abstracts and full texts. Our findings provide empirical evidence for a systemic neglect of disabled people in the topics covered: from 21,215 abstracts mentioning “civilit*” or “incivilit*”, only 14 were relevant, and of the 8358 abstracts mentioning ostracism, only 26 were relevant. Of the 3643 abstracts mentioning “climate surveys,” 12 sources covered disabled people by focusing on a given survey, but not one study performed an evaluation of the utility of climate surveys for disabled people in general. Racism is seen as a structural problem facilitating civility/incivility. Ableism, the negative judgments of a given set of abilities someone has, and disablism, the systemic discrimination based on such judgments, are structural problems experienced by disabled people, facilitating civility/incivility. However, ableism generated only 2 hits, and disablism/disableism had no hits. Most of our sources focused on workplace incivility, and authors were mostly from the USA. We found no linkage to social and policy discourses that aim to make the social environment better, such as equity, diversity, and inclusion, well-being, and science and technology governance. This is the first paper of its kind to look in depth at how the academic literature engages with the concepts of civility, incivility, and ostracism and with the instrument of social climate surveys in relation to disabled people. Our findings can be used by many different disciplines and fields to strengthen the theoretical and practical discussions on the topics in relation to disabled people and beyond. Full article

In the centralized scheduling mode of automated container terminals, Automated Guided Vehicles (AGVs) often experience decision-making delays caused by system information-processing bottlenecks, which significantly affect path-planning efficiency and are particularly evident in sudden-traffic scenarios. To address this issue, this paper incorporates the artificial potential field (APF) into the cost function of Model Predictive Control (MPC) and develops a dual-trigger mechanism for lane-change and lane-return MPC obstacle-avoidance framework (Event-Triggered Model Predictive Control, EMPC). This framework integrates an obstacle-triggered local optimization mechanism and a lane-change trigger, enabling AGV to perform autonomous and dynamically responsive local obstacle avoidance, thereby improving local path-planning efficiency. Furthermore, a Proximal Policy Optimization (PPO)-based strategy is introduced to adaptively adjust the obstacle-weighting parameters within the EMPC cost function, enhancing both obstacle-avoidance and lane-keeping performance. Under multi-lane overtaking conditions, a lane-change trigger—implemented as a dual-phase “lane-change–return” mechanism—is employed, in which lateral optimization is activated only during critical phases, reducing online computational load by at least 28% compared with conventional MPC strategies. The experimental results demonstrate that the proposed PPO–EMPC architecture exhibits high robustness, real-time performance, and scalability under dynamic and partially observable environments, providing a practical and generalizable decision-making paradigm for cooperative AGV operations in automated container terminals. Full article

In this study, we present Hierarchical Local Interpretable Model-agnostic Explanations (H-LIME), an innovative extension of the LIME technique that provides interpretable machine learning insights across multiple levels of data hierarchy. While traditional local explanation methods focus on instance-level attributions, they often overlook systemic patterns embedded within educational structures. To address this limitation, H-LIME aggregates local explanations across hierarchical layers, Institution Type, Location, and Educational Level, thereby linking individual predictions to broader, policy-relevant trends. We evaluate H-LIME on a student adaptability dataset using a Random Forest model chosen for its superior explanation stability (approximately 4.5 times more stable than Decision Trees). The framework uncovers consistent global predictors of adaptability, such as education level and class duration, while revealing subgroup-specific factors, including network type and financial condition, whose influence varies across hierarchical contexts. This work demonstrates the effectiveness of H-LIME at uncovering multi-level patterns in educational data and its potential for supporting targeted interventions, strategic planning, and evidence-based decision-making. Beyond education, the hierarchical approach offers a scalable solution for enhancing interpretability in domains where structured data relationships are essential. Full article

Public open spaces play a vital role in supporting social connection and leisure among residents, enhancing quality of life while contributing to both economic growth and environmental health. The rapid global urbanization underscores the critical link between urban environments and human health, which demands focusing on sustainable, health-conscious urban planning. Accordingly, Public and green spaces are vital in this context, as recognized by global agendas like the Sustainable Development Goals (SDG) 11.7. This research aims to objectively evaluate the availability of public open spaces (POS) in Alexandria, Egypt. This study will utilize Geographic Information System (GIS) to formulate a methodology that incorporates spatial data analysis for quantifying public open spaces and assessing the proportion of the population with convenient access to these areas, evaluating their coverage, service area isochrones, spatial distribution, and proximity to residential areas. The study will benchmark its findings against global standards to expose critical spatial inequalities within cities of the Global South. The primary aim is to present evidence-based recommendations for sustainable urban public space design, tackling availability and accessibility issues to improve the well-being of Alexandria’s expanding urban population. This research offers a scientific foundation to inform policy and decision-making focused on creating more equitable, healthier, and resilient urban environments. Full article

Landslides rank among the most frequent and devastating natural hazards globally, causing significant loss of life and property. As a result, landslide susceptibility assessment has become a central focus in geohazard research, which is devoted to preventing and alleviating the frequent occurrence of landslides. Numerous analytical models have been applied to evaluate landslide susceptibility, including Frequency Ratio (FR), Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and various hybrid and neural network-based approaches. This review synthesizes current progress in integrating Nature-based Solutions (NBS) with modeling and policy frameworks, highlighting their potential to provide cost-effective, sustainable, and adaptive alternatives to conventional landslide mitigation strategies. Based on a systematic review of 127 peer-reviewed publications published between 2023 and 2025, selected from Web of Science, ScienceDirect, MDPI, Springer, and Google Scholar using predefined keywords and screening criteria, this study reveals that the most frequently used conditioning factors in landslide susceptibility modeling are slope (96 times), aspect (77 times), elevation (77 times), and lithology (77 times). Among modeling approaches, Random Forest (RF), Support Vector Machine (SVM), hybrid models, and neural network models consistently demonstrate high predictive performance. Despite the expanding body of literature on NBS, only 2.3% of all NBS-related studies specifically address landslide mitigation. The existing literature primarily concentrates on assessing the biophysical effectiveness of interventions such as vegetation cover, root reinforcement, and forest-based stabilization using a range of predictive modeling techniques. However, significant gaps remain in the integration of economic valuation frameworks, particularly cost–benefit analysis (CBA), to quantify the monetary value of NBS interventions in landslide risk reduction. This highlights a critical area for future research to support evidence-based decision-making and sustainable risk governance. Full article

Urban logistics serves as a cornerstone for efficient freight transport and sustainable city development, particularly in contexts challenged by congestion and environmental pressures. This research examines the restructuring of the urban logistics system in Sfax, Tunisia—an expanding industrial and economic center increasingly burdened by traffic congestion. Through a comprehensive analytical framework, the study identifies the primary determinants influencing freight transport operations and develops a phased policy roadmap to enhance logistical efficiency. Neural Network Modeling is employed to evaluate the effects of multiple transport-related variables on logistics performance, while Graph Theory is utilized to represent spatial and functional interconnections, facilitating the visualization of freight flows and supporting evidence-based decision-making. The results emphasize the crucial role of managing truck circulation within Sfax’s urban core. Accordingly, a three-phase reorganization plan is proposed to optimize freight mobility, alleviate congestion, and advance sustainable urban growth. The methodological approach and policy insights offer practical guidance applicable to other metropolitan areas facing similar logistical challenges. Full article

Financial institutions increasingly rely on data-driven decision systems; however, many operational models remain purely predictive, failing to account for confounding biases inherent in observational data. In credit settings characterized by selective treatment assignment, this limitation can lead to erroneous policy assessments and the accumulation of “methodological debt”. To address this issue, we propose an “Estimate → Predict & Evaluate” framework that integrates Double Machine Learning (DML) with practical MLOps strategies. The framework first employs DML to mitigate selection bias and estimate unbiased Conditional Average Treatment Effects (CATEs), which are then distilled into a lightweight Target Model for real-time decision-making. This architecture further supports Off-Policy Evaluation (OPE), creating a “Causal Sandbox” for simulating alternative policies without risky experimentation. We validated the framework using two real-world datasets: a low-confounding marketing dataset and a high-confounding credit risk dataset. While uplift-based segmentation successfully identified responsive customers in the marketing context, our DML-based approach proved indispensable in high-risk credit environments. It explicitly identified “Sleeping Dogs”—customers for whom intervention paradoxically increased delinquency risk—whereas conventional heuristic models failed to detect these adverse dynamics. The distilled model demonstrated superior stability and provided consistent inputs for OPE. These findings suggest that the proposed framework offers a systematic pathway for integrating causal inference into financial decision-making, supporting transparent, evidence-based, and sustainable policy design. Full article

Improving alignment between timber sawmilling and prefabrication, defined as the coordination of information, materials, and decision-making across the supply chain, is critical for sustainable construction. This study examined integration through semi-structured interviews with 15 industry practitioners. Using framework analysis supported by NVivo, eight interlinked themes were identified: supply chain fragmentation and market cycles; data-driven forecasting; inventory and moisture management; digital integration; smart planning and production; quality assurance and workforce capability; circular economy and residue utilisation; and systemic enablers and constraints. The findings show that technical capabilities such as optimisation, grading, and QR-based traceability are often undermined by organisational and policy barriers, including distributor-mediated purchasing, limited interoperability, outdated standards, and uneven skills pathways. Integration was considered more feasible for mass timber prefabrication, where batch planning, tighter quality assurance, and vertical integration align with mill operations, compared with frame-and-truss networks that rely on just-in-time project workflows. The study provides empirical evidence of practitioner perspectives and identifies priorities for action that translate into sustainability gains through improved material efficiency, waste reduction, higher-value residue pathways, and supportive policy settings. Full article