Abstract: Accurate monitoring and forecasting of vegetation health is essential for natural resource management, food security planning, and climate adaptation in water-stressed semi-arid environments. This study presents a comprehensive deep learning framework for forecasting the Enhanced Vegetation Index (EVI) across the four governorates of the Kurdistan Region of Iraq (KRI) --- Erbil, Duhok, Sulaymaniyah, and Halabja --- using a nine-year monthly record (January 2016 -- December 2024) derived from Sentinel-2 Level-2A Surface Reflectance imagery accessed via Google Earth Engine (GEE). Nine deep learning architectures spanning recurrent, hybrid convolutional-recurrent, and attention-based categories were trained and evaluated on a multivariate feature set comprising EVI, precipitation, air temperature, and cyclic month encoding. The Bidirectional Long Short-Term Memory (BiLSTM) model achieved the highest mean R² of 0.945 across all four governorates, with outstanding performance in Sulaymaniyah (R² = 0.977) and Halabja (R² = 0.964). Hybrid CNN-recurrent architectures, particularly CNN-BiLSTM-GRU, also demonstrated strong performance with the highest mean tolerance accuracy (0.985), confirming the complementarity of local convolutional feature extraction and temporal sequence modeling; however, BiLSTM remains the top-ranked model by R². By contrast, the standalone Transformer model performed poorly (mean R² = 0.132) due to the absence of positional encoding in the shallow single-block architecture. Predictive uncertainty was quantified using Monte Carlo Dropout inference, revealing well-calibrated epistemic uncertainty that peaks during the spring vegetation growing season. Autoregressive five-year EVI forecasts (2026--2030) and an exploratory ten-year projection (2026--2035) were generated by the BiLSTM model; forecasts commence in January 2026 as TerraClimate climate forcing data for 2025 were not yet publicly available at the time of analysis. Projected mean annual EVI values range from 0.145 to 0.194 across governorates, consistent with the historical climatological baseline. The 2022 regional drought anomaly is clearly captured in the historical record, confirming the sensitivity of the EVI signal to precipitation deficits. These results establish deep learning-based EVI forecasting as a viable and scalable tool for operational vegetation health monitoring in the KRI and comparable semi-arid dryland systems.

Abstract: The city of Baghdad is witnessing a continuous increase in traffic and urbanization, which has led to frequent traffic jams and deterioration of the urban environment and quality of life due to pollution and the waste of time and energy. Hence, it has become necessary to adopt integrated planning concepts that regulate land uses, promote transport efficiency, and support sustainable urban development. This research aims to investigate the concept of transport-oriented development (TOD) and explore its applicability in the city of Baghdad, focusing on identifying obstacles and challenges that may face the implementation of this concept in the local context, whether related to transport infrastructure, urban planning, or community participation, to provide an analytical framework that can be relied upon in the development of effective strategies to promote sustainable transport and integrated urban development. The BRT bus rapid transit system is an essential part of the Comprehensive Development Plan for Baghdad 2030, aiming to improve mass transit and reduce congestion on major streets such as Palestine Street by providing fast, efficient transportation that connects the city's neighborhoods and encourages walking and the use of sustainable transport. The project supports sustainable urban development by integrating the principles of TOD, increasing residential and commercial density around the stations, and adopting an integrative methodology that analyzes the relationships among transport, land uses, and urban density to provide a scientific framework to support planning and future decision-making.

Abstract: The contemporary green transformation of the economy is a strategic imperative for businesses, especially small and medium-sized enterprises (SMEs) operating in the energy market, forcing the integration of sustainable practices in decision-making processes, including investment efficiency assessment. Classic financial tools, such as the internal rate of return and net present value, commonly used in the SME sector, do not always adequately account for environmental, regulatory, and social risks associated with green transformation. The goal of the study was to determine the impact of nominal and real discount rates, adjusted for a synthetic measure of green transformation, on investment decisions. The research methodology combines advanced multicriteria analysis techniques with sustainable finance concepts, offering an innovative approach to investment decision-making in the SME sector. The study shows that integrating environmental factors increases the cost of capital and reduces the net present value while maintaining the profitability of the analysed projects. Incorporating green components into the discount rate enhances valuation appropriateness and improves investment risk management, especially in conditions of macroeconomic uncertainty. The findings contribute to the development of research on dynamic methods of evaluating investment projects.

Abstract: Surface modification of metallic powders plays a critical role in improving their chemical stability, interfacial characteristics, and processing behavior in powder metallurgy applications. In this study, micron-sized iron powders were treated using a controlled gas-phase phosphating process to investigate surface layer formation and microstructural evolution. The influence of treatment conditions on phase stability, surface morphology, and elemental distribution was systematically analyzed using X-ray diffraction (XRD), scanning electron microscopy (SEM), and energy-dispersive spectroscopy (EDS). The results confirm the preservation of the body-centered cubic α-Fe phase within an optimized temperature range, while a conformal phosphate-based surface layer was successfully formed. Increased treatment severity led to partial surface oxidation and localized microstructural heterogeneity. Elemental mapping revealed homogeneous phosphorus distribution under controlled processing conditions, indicating uniform coating development. The study establishes clear correlations between gas-phase processing parameters and surface layer formation mechanisms. These findings provide insight into the controlled surface engineering of iron powders and offer practical guidance for optimizing gas-phase phosphating routes in advanced powder metallurgy and metallurgical applications.

Abstract: The thermal drift of microring resonators is one of the key obstacles hindering their practical applications. Employing polymers with negative thermo-optic coefficients to compensate for temperature-induced wavelength shifts represents a common solution. This study utilizes polymethyl methacrylate (PMMA) to compensate silicon nitride microring resonators, achieving thermal drift magnitudes below 2.0 pm/K within the temperature range of 15℃ to 70℃. Furthermore, nonlinear thermal drift characteristics were experimentally observed, and simulations revealed that these nonlinearities primarily originate from the temperature-dependent Young's modulus and Poisson's ratio of PMMA. This research provides design references for waveguide compensation using negative thermo-optic coefficient materials and proposes a conceptual framework for dual-function devices capable of both athermal operation and thermal tuning.

Abstract: Background: Timely prehospital management is critical for survival after traumatic injury. In rapidly growing metropolises, emergency medical service (EMS) systems often struggle to provide equitable care amid urban sprawl and traffic congestion. This study investigated spatiotemporal inequalities in trau-ma-related EMS response in a rapidly expanding capital city (Astana, Kazakh-stan) to inform healthcare optimization and urban health equity. Methods: We analyzed a five-year population-based dataset of 26,073 trauma-related EMS calls recorded between 2020 and 2024. Spatial patterns were examined using Kernel Density Estimation (KDE) and Getis–Ord Gi* hotspot analysis. Road-network modeling assessed accessibility at 3, 5, and 10-minute thresholds using a GIS-based network analyst framework. Results: Males accounted for 60.1% of utilization and had higher clinical severity (hospitalization rate: 45.5% vs 40.3%, p < .001). Demand peaked at 20:00, coinciding with peak traffic. The mean total response time was 21.63 minutes, and only 16.9% of calls met the 10-minute benchmark. Significant accessibility gaps were found in the Baikonur district (61.4% delay rate). Conclusions: The findings demonstrate that while the EMS system provides broad geographic coverage, it suffers from systemic spatio-temporal bottlenecks. Targeted infrastructure expansion in underserved pe-ripheral districts and the implementation of dynamic deployment models are necessary to enhance urban health equity and reduce preventable mortality in expanding metropolitan areas.

Abstract: This paper introduces Bayesian R-LayerNorm, a novel normalization layer that extends the previously proposed R-LayerNorm with formal mathematical foundations and uncertainty quantification. Building upon the empirical success of R-LayerNorm, we present a complete mathematical formalism using sta-tistical field theory, renormalization group methods, and information geometry. Our approach provides provable stability guarantees through three theorems: numerical stability, gradient stability, and training convergence. The Bayesian extension incorporates uncertainty estimation through a stable ψ-function, enabling adaptive noise suppression based on local entropy estimates. A key contribution is the integration of uncertainty quantification directly into the normal-ization operation, providing confidence estimates for each normalized activation without additional cost. The method is adaptive to local noise, varying its normalization strength spatially based on estimated noise levels. Despite its theoretical depth, the implementation is simple and serves as a drop-in replacement for existing normalization layers, adding only two learnable parameters per layer. Experimental validation on the full CIFAR-10-C dataset demonstrates consistent improvements: Bayesian R-LayerNorm achieves average accuracy gains of +0.49% over standard LayerNorm across four common corruptions, with the largest improvement of +0.74% on shot noise. The method requires minimal computational overhead (∼ 10%) and we provide complete open-source implementation. We further show that the learned λ parameters offer interpretability, revealing which layers adapt most strongly to different corruptions. While the accuracy gains are modest, the framework opens new di-rections for trustworthy and interpretable normalization in safety-critical applications where uncertainty matters as much as accuracy.

Abstract: The effect of water on the dynamics and ionic conductivity of the ionic liquids 1-ethyl-1-methylpyrrolidinium levulinate ([C₂C₁Pyr]Lev) and 1-butyl-1- methylpyrrolidinium levulinate ([C₄C₁Pyr]Lev) was investigated using differential scanning calorimetry (DSC) and broadband dielectric spectroscopy (BDS) over a wide temperature range. Although both ILs share the same levulinate anion, water induces markedly different dynamical responses depending on cation structure. In both systems, water acts as a plasticizer, lowering the glass transition temperature; however, the extent of plasticization and the resulting relaxation dynamics are cation-dependent. Stronger water–cation interactions are observed in [C₂C₁Pyr]Lev, whereas in [C₄C₁Pyr]Lev, water primarily disrupts alkyl-chain packing, enhancing ionic mobility. Increasing hydration shifts the main relaxation to higher frequencies and increases liquid fragility, while translational ionic motion remains partially decoupled from structural relaxation. These results demonstrate that water plays a cation-specific and mechanistically distinct role in levulinate-based ILs, providing new insights into hydration-controlled glassy dynamics and charge transport relevant for the design of IL-based electrolytes under non-anhydrous conditions.

Abstract: Intestinal dysbiosis is common in people living with HIV/AIDS (PLWH), yet fungal communities of the gut microbiota (mycobiota) remain poorly characterized, especially in severely immunosuppressed patients. We analyzed the gut mycobiota of 33 PLWH and 20 healthy controls from a public hospital in central Argentina. Most PLWH presented severe immunosuppression (<200 CD4+ T cells/μL) and acute or chronic diarrhea, with or without antibiotic exposure or antiretroviral therapy. Fecal DNA was extracted and the ITS2 region was sequenced using next-generation sequencing. Beta-diversity analyses revealed significant segregation between PLWH and controls (PERMANOVA, Adonis: p = 0.001, R² = 0.0989). LEfSe analysis identified 17 fungal species enriched in PLWH, predominantly Candida albicans, Candida dubliniensis, and Nakaseomyces glabratus, whereas 31 species were more abundant in controls, including Penicillium spp., Candida sake, and Clavispora lusitaniae. Histoplasma capsulatum, an endemic pathogen in the region, was more prevalent in PLWH and associated with CD4+T-cell counts. Dirichlet multinomial mixture analysis revealed two mycobiotypes: M1, with a balanced fungal composition predominating in controls, and M2, dominated by Candida species and present in PLWH. These findings provide novel insights into gut mycobiota alterations in severely immunosuppressed PLWH in Argentina, highlighting Candida-driven dysbiosis and the regional relevance of H. capsulatum.

Abstract: Urban scaling theory establishes that socioeconomic outputs scale superlinearly with city population (β > 1), attributed to social-interaction density, but its applicability to resource-constrained sectors remains untested. We analyse a panel of ∼ 2 , 800 Chinese counties (2000–2023) with GDP decomposed into primary, secondary, and tertiary sectors. Using the urbanization ratio as a continuous moderator in interaction-term regressions, we estimate sector-specific crossover thresholds from sub- to super-linear scaling; a Scale-Adjusted Agricultural Index (SAAI) quantifies each county’s deviation from size-expected output. A robust sectoral spectrum emerges—βpri = 0.87 < βter = 0.96 < βsec = 1.08—whose rank order is preserved across all 24 sample years. The tertiary sector crosses β = 1 at urbanization ratio u∗ = 0.80 (95% CI [0.72, 0.92]), with interaction coefficient β1 = 1.48 (p < 0.001). Province fixed effects confirm the urbanization interaction for secondary and tertiary sectors (p < 0.001) but not primary (p = 0.248), consistent with the crossover being specific to interaction-intensive activities. China’s 832 designated poverty counties exhibit systematically negative SAAI values (Cohen’s d = 0.55–0.87), revealing a persistent scaling deficit that conventional output comparisons obscure. These results show that the scaling exponent is a continuous function of economic structure, identify a quantifiable urbanization threshold for the onset of increasing returns, and supply a boundary condition for Bettencourt’s theory of urban scaling.

Abstract: Genomic regulation is typically interpreted through observable molecular states such as gene expression, chromatin accessibility and epigenetic modifications. However, biological systems also contain large reservoirs of genomic information that remain transcriptionally inactive for extended periods while retaining the capacity to influence future regulatory behaviour. This phenomenon, referred to here as gene latency, suggests that genomes may preserve forms of biological memory beyond currently expressed molecular states. Recent advances in artificial intelligence—particularly transformer-based architectures—demonstrate how complex systems can encode structured information within latent representational spaces that influence outputs without continuous activation (Vaswani et al., 2017; Brown et al., 2020). In this study, we propose a conceptual framework that interprets gene latency as a form of genomic memory using principles derived from latent representation learning in artificial intelligence. By aligning concepts from systems biology, epigenetics and machine learning, we outline theoretical and computational perspectives for identifying latent regulatory potential within genomic systems. This framework suggests that genomes may contain distributed reservoirs of regulatory capacity shaped by developmental history and environmental exposure. Integrating artificial intelligence with genomic theory may therefore enable new approaches for modelling latent regulatory states and predicting transitions from genomic latency to activation.

Abstract: Hemoglobinopathies are common inherited blood disorders, affecting 7% of the global population. In India, β-thalassemia, sickle cell disease, and other variants show varied prevalence across regions and ethnic groups due to genetic diversity and consanguinity. This study analyzed the demographic profile and prevalence of hemoglobinopathies among 4,336 patients registered at the Thalassemia and Sickle Cell Society (TSCS), Hyderabad. Of the 4,336 cases registered from 1998–2025, the highest were in 2023 (9.85%), with minimal contributions from 1998–2002 (each < 1.2%). Blood samples were evaluated using CBC and HPLC to assess RBC indices and hemoglobin fractions. Among 4,336 individuals, 57.7% were male and 42.2% female, with mean age of 16.24 years. Most patients were aged 10–20 years (39.58%) and about 39.4% reported consanguineous marriages. Most patients were from Telangana (71.2%) and Andhra Pradesh (23.8%). Hinduism was the predominant religion (76.4%), with Lambadi, Madiga, and Mala being the most represented castes. Beta-thalassemia major was the most prevalent disorder (59.96%), followed by sickle cell disease (22.3%) and sickle beta-thalassemia (9.1%). Other less common hemoglobinopathies included E beta-thalassemia, thalassemia intermedia, delta beta thalassemia and rare variants HbH disease and HPFH. These findings underscore the significant public health burden of hemoglobinopathies in Telangana. The high prevalence of β-thalassemia, highlights the urgent need for targeted genetic screening, counseling, and community-based awareness programs. A coordinated approach involving early detection, multidisciplinary care, and advanced therapies is essential to reduce disease impact. Institutions like TSCS exemplify a successful model of integrated care, combining diagnostics, treatment, and patient support.

Abstract: In standard quantum mechanics, the electron is treated as a fundamental particle whose wavefunction describes a spatial probability distribution. While this formalism provides extremely accurate predictions, the conceptual relationship between orbital geometry, particle localization, and wave–particle duality remains interpretatively open. In this work, we propose a geometric reinterpretation within the framework of Viscous Time Theory (VTT). In this view, atomic orbitals arise as stabilized basins of informational curvature within a viscous informational manifold, and the electron emerges as the undissipated residual of this geometric formation. By introducing the Informational Hessian as the curvature tensor associated with coherence deviation ΔC, orbital stability can be formulated as a positive-definite curvature condition over the informational manifold. Within this framework, electron mass is reinterpreted as an integrated curvature excess associated with stabilized orbital geometry. This approach provides: (i) a geometric interpretation of wave–particle duality as periodic coherence recall, (ii) a reinterpretation of excited states as metastable curvature attractors, and (iii) a potential structural mechanism for residual mass generation within stabilized informational structures. The proposed framework is presented as a constructive extension compatible with Schrödinger dynamics. Rather than replacing the standard formalism, we suggest the existence of a deeper geometric layer whose implications invite further mathematical and physical investigation.

Abstract: Antimicrobial resistance is often framed as a problem acquired outside the patient through transmission of resistant strains and genes. This view is important, but it is incomplete for immunocompromised patients, where there is substantial evidence that drug-resistant bacteria can evolve within the host during therapy. In haematological malignancy, transplantation, and other states of impaired immunity, infections persist longer, immune clearance is reduced, and prolonged use of last-line antibiotics creates repeated selection events. These conditions favour stepwise evolution toward the hardest-to-treat phenotypes, including carbapenem resistance, tigecycline resistance, colistin resistance, and resistance to ceftazidime–avibactam, often alongside persistence in reservoirs such as the gastrointestinal tract. This essay argues that antibiotic escalation alone is therefore an incomplete strategy in these settings and that care should be explicitly evolution-aware. Adjunct and alternative approaches should be prioritised earlier to reduce bacterial burden, shorten time under selection, and limit reliance on prolonged sequential antibiotic regimens. Bacteriophages are highlighted as one promising adjunct because they are highly specific, generally well tolerated, can self-amplify at sites where susceptible bacteria are present, and can be iterated through approaches such as training and rational cocktails. Phage–antibiotic synergy is also discussed as a practical strategy to improve killing and reduce escape.

Abstract: Intracranial fusiform aneurysms represent a rare but clinically aggressive subtype of cerebrovascular disease, characterized by circumferential arterial dilation and a high risk of growth, ischemic complications, and rupture. Unlike saccular aneurysms, fusiform lesions lack well-established medical therapies to prevent progression or stabilize the aneurysm wall. Tumor necrosis factor–alpha (TNF-α) has emerged as a central mediator of aneurysm-associated inflammation and vascular remodeling, raising interest in TNF-α modulation as a potential therapeutic strategy. To systematically review and synthesize the available clinical and translational evidence evaluating TNF-α signaling and anti–TNF-α therapies in the context of intracranial fusiform aneurysms. A systematic literature search was conducted in PubMed/MEDLINE, Embase, and Google Scholar from database inception through February 2026 in accordance with PRISMA guidelines. Eligible studies included human, animal, and translational investigations examining TNF-α biology or anti–TNF-α interventions in relation to intracranial fusiform aneurysms, intracranial dolichoectasia, or vertebrobasilar dolichoectatic aneurysms. Study selection, deduplication, and screening were performed using Covidence systematic review software. Extracted outcomes included aneurysm growth, rupture, ischemic events, imaging characteristics, inflammatory signaling, and vascular remodeling. Given substantial heterogeneity in study design and outcome reporting, findings were synthesized narratively using structured evidence mapping. From 368 records identified, 14 studies met inclusion criteria following full-text review. Included studies encompassed preclinical models, translational mechanistic investigations, and limited clinical observational data. Across experimental models, TNF-α signaling was consistently associated with macrophage infiltration, matrix metalloproteinase activation, vascular smooth muscle cell phenotypic modulation, and aneurysm wall degeneration. TNF-α inhibition was associated with reduced aneurysm progression and rupture in preclinical settings, including when initiated after aneurysm formation. Clinical evidence remains limited but suggests a potential association between TNF-α modulation and aneurysm stability, although direct therapeutic data in intracranial fusiform aneurysm populations are sparse. Existing translational and preclinical evidence supports a contributory role for TNF-α–mediated inflammation in the progression of intracranial fusiform aneurysms and suggests that TNF-α inhibition may represent a promising disease-modifying strategy. However, clinical data remain insufficient to support routine therapeutic use. Prospective observational studies and early-phase clinical trials are needed to define the safety, timing, and efficacy of anti–TNF-α therapies in patients with intracranial fusiform aneurysms.

Abstract: In side-channel analysis, simple power analysis (SPA) is a widely used technique for recovering secret information by exploiting differences between operations in traces. However, in realistic measurement environments, SPA is often hindered by noise, temporal misalignment, and weak or transient leakage, which obscure secret-dependent features in single or very few power traces. In this paper, we provide a systematic analysis of moving-skewness-based trace preprocessing for enhancing asymmetric leakage characteristics relevant to SPA. The method computes local skewness within a moving window along the trace, transforming the original signal into a skewness trace that emphasizes distributional asymmetry while suppressing noise. Unlike conventional smoothing-based preprocessing techniques, the proposed approach preserves and can even amplify subtle leakage patterns and spike-like transient events that are often attenuated by low-pass filtering or moving-average methods. To further improve applicability under different leakage conditions, we introduce feature-driven window-selection strategies that align preprocessing parameters with various leakage characteristics. Both simulated datasets and real measurement traces collected from multiple cryptographic platforms are used to evaluate the effectiveness of the approach. Experimental results indicate that moving-skewness preprocessing improves leakage visibility and achieves higher SPA success rates compared to commonly used preprocessing methods.

Abstract: Polycystic ovary syndrome (PCOS) is a prevalent endocrine–metabolic disorder affecting 5.5–11.5% of women of reproductive age. While reduced adiponectin levels have been con-sistently demonstrated in adult women with PCOS, findings in adolescents remain less clearly defined. A systematic review and meta-analysis was conducted in accordance with PRISMA guidelines. PubMed, Embase, Scopus, and Google Scholar were searched from inception to October 31, 2025. Observational studies comparing adiponectin levels in post-pubertal adolescents with PCOS and controls were included. A random-effects model with REML estimator was applied. Study heterogeneity and publication bias were as-sessed. Eighteen studies comprising 1,590 participants (679 PCOS; 911 controls) were in-cluded. Adolescents with PCOS demonstrated significantly lower adiponectin levels com-pared to controls (mean difference [MD] −3.17 µg/mL; 95% CI −4.27 to −2.07; p = 0.001), I² = 94.6%. Egger’s (p = 0.81) and Begg’s (p = 0.16) tests indicated no evidence of publication bias. Adolescents with PCOS exhibit significantly reduced circulating adiponectin levels, suggesting that adipose tissue dysfunction and metabolic dysregulation are present early in the disease course. These findings support the role of adiponectin as a potential early biomarker of cardiometabolic risk in adolescent PCOS and underscore the importance of early metabolic screening and intervention.

Abstract: Objective: The study investigates the effects of modeling liquids (MLs) on the staining of composite resins, with a focus on unichromatic resins. Materials and methods: The research was carried out by subjecting samples of monochromatic resin (2mm height x 6mm internal diameter) to the immersion protocol in coffee solution (Nescafé Tradição Forte), with color evaluation after 21 days. Results: Statistics showed that the adhesive group presented greater color change when compared to the modeling group (p = .000). There was no statistically significant difference between water and experimental staining (= 0.104). Among the staining group factors, there was a difference for ∆E in the interactions mC-mE (p = 0.004), mC-aC (p < 0.001), mC-aE (p < 0.001), cE-aC (p = 0.015), cE-aE (p = 0.007), cC-aC (p = 0.033) and cC-aE (p = 0.017). Conclusion: These results indicate the need for further clinical studies on the applicability of modeling liquids to support decision-making in clinical practice.

Abstract: Both heat and photon energy are integral parts of scientific research. The study of the photon and the electron does not present up-to-date science in some phenomena. A misconception falls at the basic level. To eliminate the misconception, a discussion presents the electron dynamics in the silicon atom. The electron executes confined interstate dynamics for one forward or reverse cycle. As a result, the resulting shaped force-energy defines a unit photon. That unit photon has a shape similar to a Gaussian distribution with turned ends. A featured photon can interact with the side of a laterally orientated electron (of a semisolid or solid atom) to possibly convert into heat energy. When a featured photon interacts with the tip of a laterally oriented electron, that photon can convert into energy bits. The shapes of energy bits are similar to integral symbols. The reference point for the electron executing confined interstate dynamics is the center of a silicon atom. The north-south tips of the electrons align along the north-south poles. The energy shapes around the force tracing along the trajectory of electron dynamics. To execute confined interstate dynamics, forces of the two poles appear conservatively for turning the electron each time. The outer ring electron of the silicon atom reaches the ‘maximum limit point’ during the confined interstate dynamics. There is energy of one bit. In the remaining half cycle, that electron also generates energy of one bit. The electron dynamics of the silicon atom generate photons of a wave shape. Atoms of some other elements generate photons other than wave shapes. The execution of the electron dynamics is nearly at the speed of light. In addition to energy science, the study is useful in physical and chemical sciences.

Abstract: The Colorado River and its tributaries housed in the Colorado River Basin (CRB) are the primary source of water to the western United States and the Republic of Mexico. The river system is under intense stress due to prolonged drought and anthropogenic activities which have worsened its water quality. Total dissolved solids (TDS) and total suspended solids (TSS) are two water quality parameters (WQPs) that are crucial to the sustainability of the river system. These parameters are noted to have caused varied severity to the sustenance of the basin’s water. Monitoring of these WQPs has been conventionally conducted using field and laboratory analysis which are cost and labor-intensive. This study utilized a novel method to effectively develop machine learning (ML) models to estimate TDS and TSS concentrations in the CRB by utilizing the potential of optically sensitive multispectral Sentinel 2 A/B Multispectral Scanners (MSI) and Landsat 8 Operational Land Imager (OLI) remote sensing (RS) data retrieved from the Google Earth Engine (GEE) and in situ measurements collected from 2013-2022. Several standalone models such as linear regressions (LR), ridge regressions (Ridge), lasso regressions (Lasso), and k-nearest neighbor (KNN), and ensemble methods including the gradient boosting machines (GBM), random forest (RF), adaptive boosting (AdaBoost), eXtreme gradient boosting (XGBoost), and bagging were applied for the accurate estimation of TDS and TSS. Results found ensemble models like the XGBoost as the most optimal model estimating TDS using images from both Sentinel-2 MSI and Landsat 8 OLI with performance on the external validation dataset derived as 0.99, 26.52 mg/L, and 19.19 mg/L, respectively for R², RMSE, and MAE for Sentinel-2 images. The XGBoost yielded R², RMSE, and MAE of 0.97, 35.82 mg/L, and 27.90 mg/L, respectively. The AdaBoost was found to be best model for TSS estimations with values of 0.92, 29.48 mg/L, and 24.64 mg/L, respectively, for R², RMSE, and MAE for the Sentinel-2 image on the external validation dataset. The RF model was found to be the optimal model for TSS estimations with the Landsat 8 OLI with reported R², RMSE, and MAE of 0.90, 32.80 mg/L, and 22.91 mg/L, respectively on the external validation dataset. These findings show great potential of utilizing RS data to produce cost-efficient spatiotemporal changes on the WQPs which has an important implication for the continuous management of the limited water resources. Further study should consider the effect of land use land cover, runoff, and other climatic data to understand the complexity and dynamics of these parameters on TDS and TSS in the river.