Search Results (1,127)

This paper reviews contemporary developments in systems analysis applied to water resources and agricultural management, highlighting the growing influence of artificial intelligence (AI) and machine learning (ML). The literature in this field encompasses a wide range of approaches, methods, and applications, including hydrological simulation models, decision-support systems, and participatory governance frameworks. In recent years, increasing attention has been devoted to systematically reviewing and categorizing these approaches, particularly in light of rapid advances in AI- and ML-based technologies. The present study focuses on the contributions and impacts of AI and ML on systems analysis methodologies compared with the state of the field approximately a decade ago. By revisiting and classifying key groups of approaches, methods, and software tools, the paper provides an updated overview of the current status of systems analysis in water resources and irrigation management. This overview also serves as a reference framework for assessing future methodological and technological developments. Adopting a systems-thinking perspective, the review spans multiple spatial and management scales, from plot-level irrigation practices to river-basin water allocation. The paper aims to support a more holistic understanding and improved design and evaluation of water–agriculture systems, while also strengthening policy support for sustainable resource management. Finally, it highlights the need for continued interdisciplinary integration, enhanced stakeholder participation, and the development of operational tools capable of translating complex systems insights into actionable water management strategies in the emerging context shaped by AI and ML. Full article

This study illuminates fundamental questions in behavioral science through advanced machine learning methodologies applied to large-scale public opinion data. Drawing on Kahneman and Tversky’s dual-process theory and Sunstein’s nudge architecture, we employ hierarchical unsupervised clustering and supervised predictive models to detect cognitive biases—loss aversion, availability heuristic, and partisan motivated reasoning—embedded within a nationally representative survey of 5022 American respondents. Our primary methodological contribution is a hierarchical two-stage clustering framework that uncovers latent opinion structures without imposing a priori partisan categories, permitting discovery of cross-cutting cleavages invisible to conventional survey analysis. Three principal findings emerge: (1) loss aversion is empirically confirmed in prospective economic perception, with pessimists outnumbering optimists at a 1.14:1 ratio even among respondents rating current conditions positively; (2) partisan motivated reasoning produces a 13.15 percentage-point perception gap among individuals with identical financial circumstances; and (3) multi-platform digital engagement is associated with reduced partisan bias, providing evidence that challenges simple echo chamber assumptions. Crime safety perception emerges as the strongest predictor of economic bias, surpassing party affiliation, and substantiating availability heuristic dominance in political cognition. These findings carry implications for democratic accountability, platform governance, and the ethics of AI-augmented behavioral analysis in an era of affective polarization. Full article

The rapid integration of artificial intelligence (AI) into educational systems is transforming how student performance is analysed and how educational policies are informed by large-scale data. Within this context, machine learning techniques are increasingly used to identify patterns associated with academic success and educational inequality. However, the use of predictive algorithms in education also raises important questions regarding transparency, fairness, and potential algorithmic bias. This study examines the predictive performance and fairness implications of machine learning models used to identify academically resilient students using data from the Programme for International Student Assessment (PISA) 2022. The analysis is based on a dataset containing more than 600,000 student observations across multiple national education systems. Academic resilience is operationalised following the OECD framework, identifying students who belong to the lowest quartile of the socioeconomic status index (ESCS) within their country while simultaneously achieving mathematics performance in the top quartile (PV1MATH). A predictive framework incorporating six supervised learning algorithms—Logistic Regression, Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost—was implemented. The modelling pipeline includes data preprocessing, missing value imputation, class imbalance correction using SMOTE, and model evaluation through multiple classification metrics, including accuracy, F1-score, and the area under the ROC curve (AUC). In addition, fairness diagnostics are conducted to examine potential disparities in prediction outcomes across gender groups, while feature importance analysis and SHAP-based explanations are used to interpret the contribution of key predictors. The results indicate that ensemble-based models achieve the highest predictive performance, particularly those based on gradient boosting techniques. At the same time, the analysis reveals that socioeconomic status, migration background, and school repetition constitute the most influential predictors of academic resilience. Although gender displays relatively low predictive importance, measurable differences in positive prediction rates across gender groups suggest the presence of potential algorithmic disparities. These findings highlight the importance of integrating fairness evaluation, transparency, and interpretability into educational data science workflows. The study contributes to ongoing discussions on the responsible use of artificial intelligence in education by emphasising the need for governance frameworks capable of ensuring that algorithmic systems support equity-oriented educational policies. Full article

Extreme class imbalance is a persistent obstacle for machine learning-driven intrusion detection, as rare but high-impact cyberattacks occur far less frequently than benign traffic in training data. In many real-world cybersecurity datasets, this imbalance becomes extreme, with certain attack types containing a handful of samples, effectively placing the problem in a few-shot learning regime. This paper presents a controlled benchmarking study of Generative Adversarial Network (GAN) objectives for synthesizing minority-class cyberattack data. Using the UWF-ZeekData22 network traffic dataset, each MITRE ATT&CK tactic is framed as a separate binary detection task, and tactic-specific GANs are trained solely on minority samples to generate synthetic attack records. Four widely used GAN variants—Vanilla GAN, Conditional GAN (cGAN), Wasserstein GAN (WGAN), and Wasserstein GAN with Gradient Penalty (WGAN-GP)—are compared under unified training steps and fixed augmentation conditions. The utility of generated data is assessed by evaluating downstream detection performance using five traditional classifiers: Logistic Regression, Support Vector Machine, k-Nearest Neighbors, Decision Tree, and Random Forest. The results indicate that GAN augmentation generally strengthens minority-class detection across tactics and models, reducing false negatives and improving recall consistency, while not systematically harming majority-class performance. However, the effectiveness of each GAN objective varies significantly with data sparsity. Specifically, simpler adversarial objectives often outperform more complex architectures by preserving discriminative feature structure, while heavily regularized models may overly smooth minority-class distributions and reduce separability. Wasserstein-based objectives provide improved training stability, but additional regularization does not consistently translate to better detection performance. Overall, the results demonstrate that in extreme-imbalance settings, GAN effectiveness is governed more by data sparsity and structure preservation than by architectural complexity. These findings establish class-specific generative augmentation as a practical strategy for intrusion detection and provide empirical guidance for selecting appropriate GAN objectives for tabular cybersecurity data under highly imbalanced conditions. Full article

Accurate wind power forecasting is essential for efficient wind farm operation and reliable grid dispatch. This study proposes a site-adaptive forecasting framework that integrates machine learning, Tree-structured Parzen Estimator (TPE)-based Bayesian hyperparameter optimization, and SHapley Additive exPlanations (SHAP) for interpretability. Using real-world meteorological and power generation data from two wind farms, we first perform joint-distribution feature analysis to characterize statistical relationships between key inputs and power output, supporting model development and interpretation. TPE optimization is then applied to six benchmark models (CatBoost, Extra Trees, GBM, LightGBM, TabNet, and XGBoost). The optimized Extra Trees model achieves the best performance at Site 1 (R² = 0.965, RMSE = 3.872 kW, MAE = 2.333 kW), whereas the optimized XGBoost model performs best at Site 2 (R² = 0.921, RMSE = 3.049 kW, MAE = 1.382 kW), demonstrating the effectiveness of TPE tuning and the strong predictive capability of tree-ensemble learners. SHAP analysis further reveals heterogeneous drivers across sites: Site 1 benefits from synergistic wind-speed contributions across multiple heights, while Site 2 is primarily governed by hub-height wind speed. Overall, the proposed framework achieves both high accuracy and robust interpretability for multi-site wind power forecasting. Full article

Artificial intelligence (AI) is increasingly transforming talent acquisition and workforce analytics, raising both efficiency opportunities and ethical concerns. This study aims to map the intellectual structure and evolution of AI-enabled recruitment research with a focus on ethical and data-driven approaches. A bibliometric analysis was conducted on 1893 Scopus-indexed journal articles published between 2014 and 2025 using VOSviewer. The results reveal rapid growth in the field, dominant thematic clusters spanning machine learning applications, HR analytics, and ethical governance, and strong international collaboration led by the United States, China, and the United Kingdom. Findings also highlight the increasing prominence of fairness, transparency, and explainability within AI recruitment research. The study concludes by identifying research gaps and proposing future directions for integrating ethical AI frameworks with workforce analytics to support responsible talent acquisition. Full article

Within the context of regional energy governance, land use has emerged as a critical regulatory interface for managing energy demand. Clarifying the land-use–energy nexus is a technical prerequisite for evidence-based and spatially explicit energy planning. This study develops a digital modeling framework that integrates machine learning (Random Forest, achieving R² = 0.95/0.91 for training/testing) and spatial simulation (Patch-generating Land Use Simulation model, with 82.5% accuracy for industrial land) to quantify land-use-driven energy dynamics in Shaanxi Province, China (2005–2030). Key findings reveal: (1) socioeconomic factors dominate land-use expansion, with service industries (14.8–22.4%) and infrastructure (13.5–18.9%) acting as primary drivers, leading to a projected 94.2% growth in urban built-up areas and a tripling of total energy consumption; (2) structural transitions indicate a declining industrial energy share (from 68% to 54%) and reduced coal dependency (from 78% to 62%), though with significant regional disparities; (3) spatial analysis identifies critical energy path-dependency risks in Xi’an City and Yulin City, which are projected to account for 70% of provincial consumption by 2030. These results demonstrate that land-use structure constitutes a direct physical interface linking regional development with energy demand trajectories. The findings underscore the necessity of transitioning from generalized energy policies toward data-driven, land-use-based energy constraints, providing a digital evidentiary base for more precise and stable regional energy governance. Full article

Corporate “greenwash” constrains high-quality economic development in China, and its identification and governance constitute a critical step in building a green market and advancing ecological civilization. However, existing studies have primarily focused on the green governance effects of green finance policies, while paying limited attention to whether such policies may induce corporate “greenwash”. Using panel data on A-share listed firms in China from 2011 to 2023, this study exploits the Green Finance Reform and Innovation Pilot Zones as a quasi-natural experiment and employs a Double Machine Learning model to identify the impact of green finance reform policies on corporate “greenwash” and its underlying mechanisms. The results show that the pilot policy induces corporate “greenwash”, but this effect exhibits significant temporal characteristics and does not persist in the long run. Heterogeneity analysis further indicates that the aggravating effect is more pronounced among non-state-owned enterprises, non-heavily polluting firms, and large-scale firms. Mechanism analysis reveals that the pilot policy promotes corporate “greenwash” by intensifying external competitive pressure and internal performance pressure, while such behavior can be mitigated through optimizing firms’ internal strategic decision-making and external capital structure. Based on these findings, this study proposes policy recommendations in three aspects, namely establishing a dynamic policy adjustment mechanism, improving the competitive environment, and strengthening corporate governance, thereby providing a policy basis for mitigating corporate “greenwash”. Full article

Climate change is intensifying hydroclimatic extremes and agricultural water scarcity, sharpening trade-offs among yield stability, water saving, and farm incomes in major grain regions. Existing studies often optimise cropping patterns or irrigation schedules separately, seldom embedding yield robustness and policy instruments in one decision framework. We propose an integrated Machine-learning–System-dynamics–Non-dominated-sorting-genetic-algorithm-II (ML–SD–NSGA-II) framework linking long-horizon meteorological scenario generation, crop–water–economy feedback and multi-objective optimisation of crop areas and irrigation depths. ML models generate daily climate sequences to drive an SD model of soil moisture, yield formation, basin-scale allocable water, and farm returns; NSGA-II searches Pareto-optimal strategies that maximise profit and irrigation water productivity while minimising yield deviation. Applied to a rice–wheat irrigation system in the middle Yangtze River Basin, knee-point solutions lift irrigation water productivity by about 14%, maintain near-baseline profits, and reduce yield deviation. Scenario tests with block tariffs, quota-based subsidies, and extreme drought show pricing mainly curbs low-value water use in normal years, while under drought, physical scarcity dominates and economic tools offer limited buffering. This reveals the existence of a scarcity-regime threshold beyond which economic instruments become second-order relative to binding biophysical constraints. The framework supports transparent ex ante testing of tariff–subsidy packages for irrigation governance and adaptation. Full article

Hybrid renewable energy systems (HRES) combining photovoltaic, wind, fuel cell, and energy storage technologies are becoming established as viable options for reliable, environmentally friendly distributed electricity generation. In this review, we examine the key architectures, monitoring and forecast approaches, and control systems that improve the efficiency of HRES and facilitate the just-energy transition to low-carbon power generation systems. The main optimization and decision-aware approaches, particularly the evolutionary generation algorithms and machine learning-based prediction models, are addressed with a focus on improving energy allocation, cost minimization, and increased use of clean renewable energy sources. Technical, economic, and environmental performance indicators, such as the levelized cost of energy (LCOE), net present cost (NPC), renewable fraction (RF), and CO₂ emissions reduction, have been compared to demonstrate the feasibility of various system scenarios. This paper evaluates and summarizes recent case studies from around the world and presents the best practices and the challenges they encounter, including resource availability, governance, and economic drivers. The balance of the paper demonstrates that smart forecasting with advanced energy management approaches is crucial for developing sustainable and resilient hybrid distributed power systems for the future. Full article

This study investigates a typical valley city, Lanzhou, China, to reveal the nonlinear relationships and interaction mechanisms between gray–green space morphology and seasonal diurnal land surface temperature (LST) using multi-source remote sensing and land use data. A comprehensive morphological indicator system encompassing scale, complexity, connectivity, and structural integrity was constructed through landscape metric screening and the CRITIC objective weighting method, combined with the XGBoost-SHAP explainable machine learning framework. The findings highlight that: (1) Gray–green space impacts on LST exhibit significant seasonal and diurnal variations—daytime LST is predominantly governed by gray space morphology (e.g., fragmentation degree), while nighttime LST is driven by green space morphology (e.g., coverage intensity). (2) Key indicators demonstrate pronounced nonlinear and threshold characteristics: the cooling effect of green space coverage intensity (GCI) saturates beyond 0.25; gray space morphological structure factor (GRMSF) demonstrates cooling potential when exceeding 0.25, mitigating its warming effect. (3) Significant synergistic interaction effects exist between gray and green spaces. Interaction analysis reveals that “high green coverage with low structural connectivity of gray space” produces optimal synergistic cooling effects, representing the most effective spatial configuration for nighttime LST mitigation. This study deepens theoretical and methodological understanding of the complex relationships between spatial morphology and thermal environments, providing quantified, temporally differentiated spatial optimization guidance for climate-adaptive planning in valley cities. Full article

Coastal freak waves (CFWs) are sudden and hazardous wave events that occur near shorelines and can pose serious threats to coastal visitors and infrastructure. Due to the complex interactions among coastal bathymetry, wave dynamics, and environmental conditions, the mechanisms governing CFW formation remain poorly understood, making reliable prediction difficult. This study investigates the feasibility of applying machine learning techniques to predict CFW occurrences using observational environmental data. Three machine learning algorithms, the Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), were developed to generate probability-based predictions of CFW events. Environmental variables derived from buoy observations, including wave characteristics, wind conditions, swell parameters, wave grouping indicators, and nonlinear wave interaction indices, were used as model inputs. Hyperparameters were optimized using grid search combined with k-fold cross-validation. The results show that all three models achieved comparable predictive performance, with AUC values close to 0.80 and overall prediction accuracy around 74%. The ANN model achieved the highest recall, indicating strong capability in detecting CFW events, while the RF and SVM models showed more balanced precision and recall. Analysis of high-probability prediction events suggests that CFW occurrences are associated with swell-dominated conditions, strong wave grouping behavior, and enhanced nonlinear wave interactions. These results demonstrate that machine learning provides a promising framework for probabilistic prediction of coastal freak waves and has potential applications in coastal hazard assessment and early warning systems. Full article

Injection molding process optimization has predominantly relied on simulation-generated data, which cannot capture machine-specific variability and stochastic process noise inherent in real manufacturing environments. This paper presents an experiment-driven machine learning framework for multi-objective optimization of injection molding process parameters targeting volumetric shrinkage, warpage, cycle time, and part weight. Physical experiments were conducted on an industrial injection molding machine using high-density polyethylene with a face-centered central composite design. Systematic benchmarking of four machine learning algorithms under identical cross-validation protocols identified Gaussian process regression as the best-performing surrogate model for the majority of quality metrics, while warpage prediction remained challenging across all algorithms due to its complex thermo-mechanical origins. Permutation-based feature importance analysis established a clear parameter hierarchy, identifying holding time as the dominant factor governing multiple quality responses. Constrained Bayesian optimization with progressive constraint tightening was employed to identify optimal parameter sets and fundamental process capability boundaries. The resulting parameter configurations were validated against a held-out test set. This work demonstrates that rigorous, data-driven optimization using exclusively experimental data provides a viable and practically achievable alternative to simulation-based approaches, contributing to experiment-centric smart manufacturing in polymer processing. Full article

Calcium–silicate–hydrate (C-S-H), the primary binding phase governing cement paste cohesion, undergoes progressive physicochemical transformation upon carbonation—a process that critically dictates concrete durability in atmospheric environments. When CO₂ penetrates the porous cement matrix, it triggers a cascade of degradation mechanisms: calcium leaching decalcifies the C-S-H structure, inducing polymerization of silicate chains from dimeric to longer-chain configurations, while concurrent precipitation of calcium carbonate and amorphous silica gel fundamentally reconstitutes the nanoscale architecture. These nanoscale alterations propagate to macroscopic property evolution, manifesting as initial strength and stiffness gains due to pore-filling carbonation products followed by eventual deterioration as the cohesive binding network deteriorates. This review synthesizes current understanding of carbonation-induced structural evolution, examining the coupled influences of environmental parameters—CO₂ concentration, relative humidity, and temperature—alongside C-S-H intrinsic chemistry (Ca/Si ratio, aluminum substitution, and alkali content) on reaction kinetics and material performance. However, significant knowledge gaps persist: predictive models for in-service carbonation rates remain elusive due to the disconnect between idealized laboratory conditions and the heterogeneous, cracked reality of field concrete; the causal linkage between nanoscale C-S-H alteration and macroscale cracking patterns along with physical performance is poorly resolved, and most mechanistic studies rely on synthetic C-S-H, neglecting the compositional complexity of real Portland cement systems. We further propose emerging protection strategies, including surface barrier coatings and low-carbon alternative binders (geopolymers, calcium sulfoaluminate cements, carbon-negative materials such as recycled cement), which demonstrate enhanced carbonation resistance. Future research priorities include developing effective coating barriers for carbonation protection, developing operando characterization techniques for real-time reaction monitoring, deploying machine learning algorithms to bridge atomistic simulations with structural-scale predictions, and establishing long-term field performance databases to validate laboratory-derived degradation models. Full article

Histopathological evaluation of tissue sections remains the gold standard for the diagnosis, classification, and grading of breast cancer (BC). The widespread adoption of whole-slide imaging (WSI) has enabled the digitization of histological slides and facilitated the development of artificial intelligence (AI) approaches for computational pathology. In recent years, machine learning and deep learning (DL) algorithms have been increasingly investigated for the analysis of hematoxylin and eosin (H&E)-stained images, with potential applications in tumor detection, histological classification, prognostic stratification, and prediction of treatment response. This narrative review summarizes recent developments in AI-driven models applied to BC histopathology and discusses their potential role in supporting diagnostic and prognostic assessment. Several studies have demonstrated the promising performance of DL algorithms in tasks such as the detection of lymph node metastases, assessment of residual tumor after neoadjuvant therapy, and prediction of clinical outcomes from histopathological images. Emerging research has also explored the possibility of inferring molecular and biomarker information from histology images, although these approaches currently identify statistical associations rather than direct molecular measurements. Despite the rapid expansion of this research field, significant barriers remain before routine clinical implementation can be achieved. Key challenges include dataset bias, variability in staining and image acquisition, limited external validation across institutions, and the need for transparent and reproducible model development. In addition, the translation of AI-based systems into clinical practice requires compliance with regulatory frameworks governing software used for medical purposes, such as those established by the U.S. Food and Drug Administration. Overall, AI represents a promising research direction in computational pathology and may contribute to decision-support tools capable of assisting pathologists in the analysis of digital slides. Continued efforts toward methodological rigor, large multicenter datasets, and prospective validation studies will be essential to determine the future role of AI in BC histopathology. Full article