Search Results (58)

Accurate field-scale surface soil moisture (SSM) measures are important for agricultural water management. Conventional satellite SSM products remain too coarse for within-field applications. Here, we developed sequence-aware deep learning models for growing-season SSM estimation by fusing data from Sentinel-1 C-band SAR, harmonized Landsat-8/Sentinel-2 (HLS), and local ancillary datasets. We assembled a multi-source dataset on Sentinel-1 overpass time for 2016–2024 (May–September), yielding 1469 samples and 65 features per sample, including SAR and optical features, meteorological data, soil texture and bulk density, topography, crop labels, irrigation-likelihood flag, and irregular-time-step encoding. We compared long short-term memory (LSTM) and temporal convolutional neural network (TCN) architectures together with attention-augmented variants, including feature attention (FA), temporal attention (TA), and the combined feature–temporal attention (FTA). Models were trained and tested on seven years of data and were validated based on a temporal generalization using combined data of a wet year (2016) and a dry year (2023). The best model, FTA-TCN, achieved R² = 0.851, RMSE = 0.024 m³.m⁻³, and MAE = 0.020 m³.m⁻³ on the withheld validation years, outperforming the base LSTM (R² = 0.422; RMSE = 0.053 m³.m⁻³; MAE = 0.043 m³.m⁻³) and the base TCN (R² = 0.746; RMSE = 0.034 m³.m⁻³; MAE = 0.022 m³.m⁻³). Shapley additive explanations (SHAP) analysis indicated that antecedent precipitation and short-term rainfall accumulations were dominant forcings, while soil texture, elevation, incidence angle, and vegetation indices modulated SSM variability. Satellite-derived features accounted for ~28.5% of aggregated SHAP importance. Overall, the results show that dual-attention temporal convolution can capture field-scale SSM dynamics across wet and dry seasons when satellite signals are coupled with local soil-meteorological-management context. Full article

Operational crop mapping requires classifiers capable of robust generalization across years. While feature importance is routinely used for model optimization, its temporal stability has rarely been systematically investigated, creating a critical gap in deploying reliable monitoring systems. This study moves beyond identifying “most important” features to systematically evaluate and quantify their inter-annual stability for enabling automated classification. Using six agricultural years (2018, 2019, 2020, 2023, 2024 and 2025) of Sentinel-1 and Sentinel-2 data over Morocco, we extracted 156 multi-sensor features across 12 monthly composites and analyzed their importance stability through statistical metrics, clustering, and novel composite indices: the Reliability Index (RI) and Automatic Selection Score (AuSS). This framework automates feature selection by ranking features with RI and AuSS and then applying Pareto optimization to identify a minimal stable feature set—without requiring annual retraining or expert intervention. Our analysis confirms a fundamental tension: the most discriminative features (e.g., NDVI, VH, VV) are also the most volatile, while stable features (e.g., NDRE, MSI, NDMI) offer modest predictive power. Hierarchical clustering revealed four behavioral typologies (Dominant Stable, Performant Volatile, Stable Minor, and Noise), guiding strategic feature management. Crucially, a Pareto analysis demonstrated that a refined portfolio of 6 indices (VH, VV, NDVI, NDRE, GCVI, RVI) captures 57.2% of cumulative predictive importance, filtering out inter-annual noise while preserving discriminative signal. The Voting Ensemble leveraging this Stable Portfolio maintained consistent high accuracy (87.4% accuracy, 87.2% F1-score) with minimal performance degradation during temporal transfer, while models based on volatile top features exhibited significant drops. Entropy analysis confirmed that all features in the Stable Portfolio provide consistent informational certainty, indicating that stability-driven selection does not increase model uncertainty. We conclude that feature stability is not merely a diagnostic metric but a foundational criterion for operational design. We propose a practical, metrics-driven framework for constructing automated crop classification systems that are more resilient to inter-annual climate variability. Full article

Quantum key distribution (QKD) networks require relaying when distant key management entities share no direct quantum link. Most relay strategies, however, rely on centralized control or globally maintained routing state. This paper asks whether useful security and efficiency can still be obtained with topology-oblivious stochastic forwarding. It studies the security-overhead trade-off in a model in which fragmented key material is relayed via random-walk variants and reconstructed under privacy amplification. The analysis asks whether strictly local forwarding can retain useful information-theoretic security (ITS). Evaluation on the GÉANT topology, representing a European academic backbone network, shows clear differences between random-walk variants. The proposed highest-score-neighbor local path-diversification heuristic reduces the probability that relayed key material passes through a compromised node. The evaluation also shows that scouting-based loop erasure significantly shortens sampled routes and improves throughput in the model. Against one- to three-node cartels, random flow protects slightly more source–target pairs than a static disjoint-multipath method on the evaluated topologies. These findings position topology-oblivious stochastic forwarding as a simpler decentralized design for QKD relaying without centralized orchestration or gossip protocols. Full article

This study evaluates the potential of L-band passive microwave data for monitoring soil moisture (SM) in boreal and temperate forests using SMAP and SMOS AM and PM overpasses. SMAP and SMOS Level 3 SM products were first assessed for spring and summer seasons. SMOS showed lower accuracy (r² = 0.04–0.24, ubRMSE = 0.09–0.13 m³/m³), while SMAP performed better (r² = 0.18–0.62, ubRMSE = 0.05–0.07 m³/m³) across sites and overpasses. Given the larger number of SMAP TB observations at a fixed incidence angle and greater temporal coverage over the study area, SMAP was selected for SM estimation using ML models. Feature importance analysis identified brightness temperature (TB) as the most influential variable, followed by vegetation water content (VWC), air and soil temperatures, and the microwave polarization difference index (MPDI). Soil and air temperatures were interchangeable during AM overpasses, whereas PM overpasses showed distinct differences, likely due to thermal absorption by dense vegetation. Using optimal features, SM was estimated with CatBoost, Gradient Boosting (GB), Random Forest (RF), and Principal Component Regression (PCR), using stratified shuffle split (SSS) and leave-one-year-out cross-validation (LOYOCV). In SSS, CatBoost achieved slightly higher accuracy than the other ensemble models (AM: r² = 0.73; PM: R² = 0.74), while PCR yielded substantially lower accuracy across both overpasses. LOYOCV showed closer rankings among models, with CatBoost ranking highest overall (r² = 0.58 for AM and 0.54 for PM). Results highlight the feasibility of improved SM estimation in forests using L-band TB, VWC, temperature variables, and MPDI. Full article

This research explores how coalitions of leaders who score high in the Dark Triad traits—narcissism, Machiavellianism, and psychopathy—rebuild moral architectures in organizations to consolidate power, suppress dissent, and secure their rule. Contrary to work that has focused predominantly on individual toxic leaders, this research examines the collective processes that emerge when multiple high-DT-scoring leaders coalesce and unify their moral leadership front. Adopting a qualitative, article-based document analysis methodology, this study synthesizes and critiques evidence from 55 peer-reviewed articles published between 2015 and 2025. Thematic analysis identified three fundamental dynamics through which Dark Triad leaders collectively exercise dominance. The first, the Ethics Cartel, involves the construction of a shared moral façade that legitimates power and shields wrongdoing. The second, Mutual Cover, outlines forms of mutual protection in which leaders shield one another from accountability and scrutiny. The third, Cultural Capture, outlines processes through which organizational culture is increasingly reconfigured such that “ethics” are structured to favor leadership over employees or wider stakeholders. This study illustrates how these coalitions cross over into individual transgressions, creating systemic risk that warps the fabric of organizational culture. Employees are confronted with a work culture that positions ethics as a means of developing survival adaptive mechanisms, such as silence, withdrawal, or compliance. These processes not only harm psychological safety and break trust but also disable accountability mechanisms established to maintain integrity. This study contributes to the study of leadership and organizational ethics by framing ethics not as merely an individual moral stance but as a collective instrument of power. It calls for more attention to the risks that follow collaboration among toxic leaders and for governance arrangements that address the organizational and systemic consequences of these unions. By situating these findings within the broader debate on power, people, and performance, this paper aligns with the focus of the Special Issue “Power, People, and Performance: Rethinking Organizational Leadership and Management” by showing how collective Dark Triad leadership distorts organizational performance outcomes while reshaping power relations in ways that undermine people’s trust and well-being. These insights extend Alowais & Suliman’s findings, highlighting the systemic feedback loops sustaining ethical distortion. Full article

This study investigates the structural and cyclical determinants of tropical hardwood exports among member countries of the International Tropical Timber Organization (ITTO) over the period 1995–2022—a sector historically characterized by persistent value imbalances. The central research issue addresses the enduring asymmetries in the global value chain, shaped by unequal industrial capacities, limited access to environmental certifications, and entrenched North–South trade relations. The study pursues three main objectives: (1) to develop a typology of exporting countries; (2) to estimate heterogeneous trade elasticities; (3) to propose a policy framework that reconciles equity with sustainability. The empirical findings identify four export profiles: (i) raw producers with minimal local processing; (ii) marginal players with weak trade integration; (iii) high-value-added re-export platforms (notably in Asia); (iv) major consumer markets. Trade effects vary across regions. In the short term, imports boost exports (+0.33%), particularly in re-export models seen in Asia, the USA, and the EU, while local production remains limited in Africa due to weak industrial capacity. In the long term, both domestic production and imports have a positive impact (+0.38% and +0.37%), but only countries with strong industrial bases fully benefit. Population size (+1.29%) also reinforces the advantage of large markets like China and India, supported by short-term economic growth elasticity (+1.1%), likely driven by improved logistics or rising demand from importing countries. In response, the policy implications converge around the proposal of a “Fair and Digital Timber Trade Model” (F&DTTT), structured around three pillars: (a) specialized economic zones aligned with SDGs 8, 12, and 15; (b) blockchain-based traceability systems to enhance supply chain transparency; (c) South–South cooperation strategies aimed at commercial, regulatory, and institutional rebalancing, including potential cartelization initiatives among Southern countries. Supported by a robust methodological framework, this study provides a forward-looking pathway for transforming the tropical timber trade into a vector of equity and sustainability. Full article

This study analyzed terrestrial water storage (TWS) changes across the Inner Niger Delta (IND) in Mali (West Africa) from April 2002 to September 2022 using Gravity Recovery and Climate Experiment (GRACE), GRACE-Follow-On (GRACE-FO), and Global Land Data Assimilation System (GLDAS) products. TWS changes exhibited strong seasonal patterns (−170 mm to 330 mm) with a high correlation between GRACE/GRACE-FO and GLDAS (r = 0.92, RMSE = 35 mm). The TWS trend was positive (7.3 to 9.5 mm/year). Maximum TWS changes occurred in September, while minimum values were observed between April and May. Wavelet analysis identified dominant seasonal cycles (8–16 months). Finally, we examined the climatic effects on TWS changes along the Niger River, from its source in the humid zones of Guinea to the semi-arid Sahelian zones of the IND in Mali. Precipitation (P) and potential evapotranspiration (PE) influence TWS changes only in the humid regions (r = 0.18–0.26, p-value < 10⁻²). Surface water bodies (SWB) exhibited a significant correlation with TWS in all regions, with r exceeding 0.50 in most cases. Groundwater changes, estimated from GRACE/GRACE-FO and GLDAS, showed strong agreement (r > 0.60, RMSE < 120 mm), with recharge rates increasing in semi-arid and Sahelian regions (r > 0.70, p-value < 10⁻³). This study highlights that precipitation, surface water bodies, and groundwater recharge appear as primary drivers of TWS in different regions: precipitation in the humid forest of Guinea, surface water bodies in the Southern and Northern Guinea Savanna along the Guinea–Mali border, and groundwater recharge in the semi-arid and IND Sahelian regions of central Mali. Full article

Climate change is having a significant impact on groundwater storage, affecting water resources in many parts of the world. To characterize this impact, remote sensing and machine learning are essential tools to analyze the data accurately and efficiently. This study aims to predicting the variations of groundwater storage (GWS) using GRACE/GRACE-FO and multi-source remote sensing data, combined with machine learning techniques. The approach was applied over the Canadian Prairies region. The study area was classified into three zones of different aquifer potentials (low, medium, and high) using a combination of remote sensing data and the Classification and Regression Trees (CART) approach. The prediction model was developed using a machine-learning approach based on multiple linear regression to estimate GWS variations as a function of various environmental parameters. The results showed that the developed model was able to predict GWS variations with satisfactory accuracy (up to 95% of the explained variance) and good robustness (96% success rate). They also provided a better understanding of the variations in groundwater storage in the Canadian Prairies. Therefore, this work provides a promising method for predicting GWS, which could eventually be applied to other similar environmental conditions. Full article

Quantifying forest carbon storage to better manage climate change and its effects requires accurate estimation of forest structural parameters such as canopy height. Variables from remote sensing data and machine learning models are tools that are being increasingly used for this purpose. This study modeled the canopy height of forest–savanna mosaics in the Sudano–Guinean zone of Togo. Relative heights were extracted from GEDI and ICESat-2 products, which were combined with optical, radar, and topographic variables for canopy height modeling. We tested four methods: Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN). The RF algorithm obtained the best predictions using 98% relative height (RH98). The best-performing result was obtained from variables extracted from GEDI data (r = 0.84; RMSE = 4.15 m; MAE = 2.36 m) and compared to ICESat-2 (r = 0.65; RMSE = 5.10 m; MAE = 3.80 m). Models that were developed during this study can be applied over large areas in forest–savanna mosaics, enhancing forest dynamics monitoring in line with REDD+ objectives. This study provides valuable insights for future spaceborne LiDAR and other remote sensing data applications in similar complex ecosystems and offers local decision-makers a robust tool for forest management. Full article

Demand response management (DRM) significantly influences the prospective advancement of electricity smart grids. This paper introduces three distinct game-theoretic duopoly models for the smart grid demand response management problem. It delineates several rational assumptions regarding the model variables, functions, and parameters. The first model adopts a Cournot duopoly form, offering a unique closed-form equilibrium solution. The second model adopts a Stackelberg duopoly structure, also providing a unique closed-form equilibrium solution. Following a comparison of the economic viability of the two model equilibria and an assessment of their sensitivity to parametric changes, the paper proposes a third model with a Cartel structure and discusses its advantages over the earlier models. Finally, the paper examines how demand forecasting affects the equilibrium quantities and pricing solutions of each model. Full article

The detection and deterrence of collusive agreements among firms, such as price-fixing cartels, remain pivotal in maintaining market competition. This study investigates the application of machine learning methodologies in the behavioral screening process for detecting collusion, with a specific focus on parallel pricing behaviors in the wholesale fuel market. By employing unsupervised learning techniques, this research aims to identify patterns indicative of collusion—referred to as collusion markers—within time series data. This paper outlines a comprehensive screening research plan based on the CRISP-DM model, detailing phases from business understanding to monitoring. It emphasizes the significance of machine learning methods, including distance measures, motifs, discords, and semantic segmentation, in uncovering these patterns. A case study of the Polish wholesale fuel market illustrates the practical application of these techniques, demonstrating how anomalies and regime changes in price behavior can signal potential collusion. The findings suggest that unsupervised machine learning methods offer a robust alternative to traditional statistical and econometric tools, particularly due to their ability to process large and complex datasets without predefined models. This research concludes that these methods can significantly enhance the detection of collusive behaviors, providing valuable insights for antitrust authorities. Full article

Digital twins are increasingly gaining popularity as a method for simulating intricate natural and urban environments, with the precise segmentation of 3D objects playing an important role. This study focuses on developing a methodology for extracting buildings from textured 3D meshes, employing the PicassoNet-II semantic segmentation architecture. Additionally, we integrate Markov field-based contextual analysis for post-segmentation assessment and cluster analysis algorithms for building instantiation. Training a model to adapt to diverse datasets necessitates a substantial volume of annotated data, encompassing both real data from Quebec City, Canada, and simulated data from Evermotion and Unreal Engine. The experimental results indicate that incorporating simulated data improves segmentation accuracy, especially for under-represented features, and the DBSCAN algorithm proves effective in extracting isolated buildings. We further show that the model is highly sensible for the method of creating 3D meshes. Full article

Accurate estimation and regular monitoring of soil moisture is very important for many agricultural, hydrological, or climatological applications. Our objective was to evaluate potential contributions of polarimetry to soil moisture estimation during crop growing cycles using RADARSAT-2 C-band images. The research focused on wheat field data collected during Soil Moisture Active Passive Validation Experiment (SMAPVEX12) conducted in 2012 in Manitoba (Canada). A sensitivity analysis was performed to select the most relevant non-polarimetric and polarimetric variables extracted from RADARSAT-2, and statistical models were developed to estimate soil moisture. In fine, three models were developed and validated: a non-polarimetric model based on cross-polarized backscattering coefficient ${\sigma }_{HV}^0$; a polarimetric mixed model using six polarimetric and non-polarimetric retained variables after the sensitivity analysis; and a simplified polarimetric mixed model considering only the phase difference (${\varphi }_{HH-VV}$) and the co-polarized backscattering coefficient ${\sigma }_{HH}^0$. The validation reveals significant positive contributions of polarimetry. It shows that the non-polarimetric model has a much larger error (RMSE = 0.098 m³/m³) and explains only 19% of observed soil moisture variation compared to the polarimetric mixed model, which has an error of 0.087 m³/m³, with an explained variance of 44%. The simplified model has the lowest error (0.074 m³/m³) and explains 53.5% of soil moisture variation. Full article

The Saskatchewan River Basin (SRB) of central Canada plays a crucial role in the Canadian Prairies. Yet, climate change and human action constitute a real threat to its hydrological processes. This study aims to evaluate and analyze groundwater spatial and temporal dynamics in the SRB. Groundwater information was derived and compared using two different approaches: (1) a mathematical modeling framework coupling the Soil and Water Assessment Tool (SWAT) and the Modular hydrologic model (MODFLOW) and (2) gravimetric satellite observations from the Gravity Recovery and Climate Experiment (GRACE) mission and its follow-on (GRACE-FO). Both methods show generalized groundwater depletion in the SRB that can reach −1 m during the study period (2002–2019). Maximum depletion appeared especially after 2011. The water balance simulated by SWAT-MODFLOW showed that SRB could be compartmented roughly into three main zones. The mountainous area in the extreme west of the basin is the first zone, which is the most dynamic zone in terms of recharge, reaching +0.5 m. The second zone is the central area, where agricultural and industrial activities predominate, as well as potable water supplies. This zone is the least rechargeable and most intensively exploited area, with depletion ranging from +0.2 to −0.4 m during the 2002 to 2011 period and up to −1 m from 2011 to 2019. Finally, the third zone is the northern area that is dominated by boreal forest. Here, exploitation is average, but the soil does not demonstrate significant storage power. Briefly, the main contribution of this research is the quantification of groundwater depletion in the large basin of the SRB using two different methods: process-oriented and satellite-oriented methods. The next step of this research work will focus on the development of artificial intelligence approaches to estimate groundwater depletion from a combination of GRACE/GRACE-FO and a set of multisource remote sensing data. Full article

Accurately estimating hydrological parameters is crucial for comprehending global water resources and climate dynamics. This study addresses the challenge of quantifying uncertainties in the global land data assimilation system (GLDAS) model and enhancing the accuracy of downscaled gravity recovery and climate experiment (GRACE) data. Although the GLDAS models provide valuable information on hydrological parameters, they lack uncertainty quantification. To enhance the resolution of GRACE data, a spectral downscaling approach can be employed, leveraging uncertainty estimates. In this study, we propose a novel approach, referred to as method 2, which incorporates parameter magnitudes to estimate uncertainties in the GLDAS model. The proposed method is applied to downscale GRACE data over Alberta, with a specific focus on December 2003. The groundwater storage extracted from the downscaled terrestrial water storage (TWS) are compared with measurements from piezometric wells, demonstrating substantial improvements in accuracy. In approximately 80% of the wells, the root mean square (RMS) and standard deviation (STD) were improved to less than 5 mm. These results underscore the potential of the proposed approach to enhance downscaled GRACE data and improve hydrological models. Full article