Search Results (575)

Reverse osmosis (RO) desalination is a major technology for freshwater production in arid regions, but its energy demand becomes more challenging when the system is supplied by variable renewable energy. This study presents an offline digital-twin-assisted decision-support framework for dynamic RO under Kuwait solar-availability conditions. Within this framework, the predictive models are driven primarily by the dynamic RO process variables, while NASA Prediction Of Worldwide Energy Resources (POWER) data provide the Kuwait solar-availability context, and the PV power margin serves as a scenario-level energy indicator. The purpose is to predict instantaneous permeate flow rate, estimate specific energy consumption, and identify energy-efficient operating conditions using machine learning. Kuwait City was used as the solar case-study location. Hourly solar and meteorological data were obtained from NASA POWER, while dynamic RO membrane data were obtained from the open experimental wave desalination dataset published by the National Renewable Energy Laboratory (NREL) through Data.gov and the Marine and Hydrokinetic Data Repository. The RO dataset includes steady-state, ramp, sinusoidal, and Wave Energy Converter SIMulator (WEC-Sim) pressure/flow experiments. The process-flow image used in the system description was also taken from the same NREL dataset and is cited in the figure caption. The raw RO files were cleaned, harmonized, and transformed into a process-informed modeling dataset. Derived features included pressure rate, recovery ratio, salt rejection, estimated pump power, specific energy consumption (SEC), PV power margin, and rolling pressure/flow features. Three supervised regression models were tested: Gradient Boosting, Random Forest, and XGBoost. A representative subset of 60,000 records was used to preserve the main experimental conditions while reducing redundancy in the densely sampled sequential data. Results show that permeate flow rate can be predicted with high accuracy using Gradient Boosting (R² = 0.981; RMSE = 0.161 L/min). The moderate energy prediction performance yielded an R² of 0.654 and RMSE of 7.570 kWh/m³ for Random Forest. The accuracy of permeate conductivity predictions was lower (R² = 0.257; RMSE = 245.44 µS/cm) because membrane and feed characterizing parameters should be included for an adequate water quality control. The proposed approach is best suited as an offline decision-support framework for dynamic RO process analysis. Full article

Quantifying the impacts of climate change and extreme climatic events on crop yields is essential for safeguarding global food security. The rapid growth of data availability and advances in computational capacity have established machine learning (ML) as a critical tool for unraveling the complex, nonlinear relationships between climatic factors and agricultural productivity. This systematic review synthesizes evidence from 137 peer-reviewed studies published between 2015 and 2025 that applied ML models to assess the effects of both long-term climate trends and discrete extreme events on crop yields worldwide. Bibliometric and thematic analyses reveal a rapidly evolving field, with over 85% of studies published since 2020, and a strong concentration on staple cereals—wheat, maize, and rice—in major agricultural regions including China, the United States, and India. Random Forest (RF) was the most commonly used algorithm; ensemble and deep-learning models achieved high predictive accuracy within well-resourced study contexts. Temperature and precipitation extremes emerged as the most frequently examined stressors, with distinct methodological patterns: studies focusing on climate change trends predominantly employed RF and LSTM models, whereas those investigating extreme events increasingly adopted hybrid approaches that integrate ML with process-based crop models. This review highlights the transformative potential of ML while identifying persistent challenges, such as geographical imbalances in research coverage, the need for enhanced interpretability in extreme event attribution, and the critical importance of modeling compound extremes. Future research should prioritize the development of explainable, causally informed, and transferable ML frameworks to support equitable climate adaptation strategies in global agriculture. Full article

Abnormal ship behavior detection is important for maritime traffic surveillance, navigation safety, and risk prevention. However, existing methods often depend on handcrafted features or a single reconstruction or prediction signal, which limits their ability to detect both sustained trajectory abnormalities and abrupt vessel movement changes. This paper proposes a Dual-Error Fusion LSTM–Transformer framework, referred to as DEFLT, for AIS-based abnormal ship behavior detection. A motion-aware vessel representation was first constructed by combining the geographical position, speed over ground, course over ground, and their temporal variations. An LSTM autoencoder reconstructs historical trajectory windows, while a Transformer prediction module estimates subsequent vessel states. The standardized reconstruction and prediction errors are fused into a unified anomaly score to capture complementary evidence from historical trajectory inconsistency and unexpected future motion. Experiments were conducted using real-world AIS data collected during September 2019 from four representative Danish waters. The study considers four abnormal behaviors: speed anomalies, course anomalies, loitering, and route deviations. Compared with KNN, LOF, Isolation Forest, Random Forest, the LSTM-AE, and the Transformer, DEFLT achieves F1-scores of 0.96, 0.97, 0.88, and 0.93 across the four study areas. For type-specific detection, the Macro-F1 values range from 0.61 to 0.86, while Macro-Recall remains between 0.88 and 0.96. Friedman and post hoc Wilcoxon signed-rank tests further demonstrate that DEFLT provides a significant and consistent improvement over all baseline methods. These results verify the effectiveness of dual-error fusion for detecting heterogeneous abnormal ship behaviors from AIS trajectories. In operational settings, DEFLT can serve as an alert-prioritization tool for vessel traffic services and port authorities by directing attention to atypical trajectories that require timely review, thereby supporting safer and more resource-efficient maritime traffic coordination. Full article

Against the backdrop of accelerating globalization and the reconfiguration of ecological security patterns, border regions—serving as critical carriers of national spatial governance—exhibit pronounced spatial heterogeneity and stage-dependent characteristics in land use evolution that warrant systematic investigation. This study focuses on global border zones to reveal the trends and evolutionary pathways of land use change, thereby providing a scientific basis for border spatial governance. Using the period of 1992–2020, four phases of global land cover data from the European Space Agency (ESA) were employed. Buffer zones of 50 km, 100 km, and 150 km were established along global national boundaries, and the study period was divided into three decadal stages. Border types were classified into terrestrial borders, coastal borders, and island borders. An integrated indicator system was constructed, including the Single Land Use Dynamic Degree (SLUDD), Integrated Land Use Dynamic Degree (ILUDD), and Weighted Composite Transition Intensity. A multi-scale nested analytical framework coupled with transition matrices was applied to assess land use evolution across global, continental, and bilateral national scales. The results indicate the following: (1) Distinct evolutionary pathways exist among border types. Terrestrial borders exhibit a combination of development and ecological restoration, with staged peaks in urban expansion; coastal borders are dominated by a unidirectional conversion from cropland to built-up land; and island borders demonstrate concurrent agricultural decline, ecological recovery, and built-up expansion. (2) From 1992 to 2020, global border land use underwent a transition from high-intensity transformations to low-intensity steady adjustments. Major changes were centered on the expansion of production space, outward diffusion of built-up areas, and vegetation restructuring. High-intensity changes were concentrated near boundary zones and attenuated significantly with increasing buffer distance. (3) At the continental scale, stable hierarchical patterns emerge in terms of change intensity, spatial gradients, and transition structures. Borders in Eurasia and North America show higher activity, Africa exhibits widespread diffusion, and South America and Oceania are characterized by forest boundary reshaping and vegetation adjustments, respectively. (4) Typical border regions can be categorized into three evolutionary types: forest ecological frontiers, agricultural expansion zones, and land–sea composite corridors. Regional trajectories vary significantly, with Southeast Asia transitioning rapidly toward stabilization, West Africa retaining periodic high-intensity disturbances, and South America remaining in a low-intensity adjustment state. This study clarifies the evolutionary patterns and boundary effect ranges of global border land use, providing theoretical support and empirical references for resource allocation and ecological regulation in border regions. It also lays the groundwork for refining border typologies, quantifying driving mechanisms, and developing differentiated cross-border governance strategies. Full article

In crisis times, traditional models of water quality assessment and water resources management lose their effectiveness. In the current conditions of local climate change, accidental pollution, emergencies or military operations, there is an urgent need to transition from traditional descriptive hydrochemical monitoring toward intelligent analysis of spatial-temporal datasets. In this paper, the integrated approach combining spatial cluster analysis, GIS-based visualization, and machine learning is proposed for assessing the surface water quality under conditions of limited and incomplete hydrochemical monitoring data. A geospatial assessment of nutrient impacts on surface water quality was conducted using 192 hydrochemical observations collected during the 2024–2025 monitoring period at eight state monitoring stations located in the basins of the Teteriv, Uzh, Irsha, Ubort, Sluch, Hnylopiat, and Voznia rivers, Polissia, Ukraine. Permutation feature importance analysis based on the Random Forest model showed that nitrate concentration accounted for approximately 75% of the total relative importance, whereas phosphate concentration contributed approximately 14%, indicating that these variables were the most informative predictors among the investigated hydrochemical parameters. The latter parameters are associated with dissolved oxygen variability among the analyzed hydrochemical parameters. According to the results of this study, three interpretable groups of monitoring stations were formed: Cluster 1, representing moderate water quality with increased nutrient pressure, Cluster 2, representing comparatively favourable background conditions, and Cluster 3, representing a nitrate-dominated hydrochemical type. The Random Forest model demonstrated limited predictive performance (R² = 0.154), indicating that nutrient-related variables alone explain only a small proportion of dissolved oxygen variability. Hence, additional factors, including hydrological conditions, water temperature, organic matter decomposition, biological productivity, and catchment-specific characteristics, also play an important role in shaping oxygen dynamics. The spatial visualization of cluster membership showed that geographical location alone does not fully determine the surface water quality patterns in Ukrainian Polissia. Instead, the local catchment characteristics and land-use conditions appear to exert a stronger influence on the formation of nutrient-related water quality differences. The authors propose to employ the spatial cluster analysis and machine learning as a basic supporting tool for the transition from retrospective interpretation of hydrochemical monitoring data to predictive and adaptive water resources management. The integration of geospatial analysis and machine learning provides a practical decision-support framework for the early detection of anomalies, identification of potential pollution sources, and prioritization of river sub-basins for implementing nature-based solutions. Full article

This study aims to examine fuelwood S4 as a forest bioenergy resource in Poland by analysing real price dynamics, sales-volume changes and short-term price–volume relationships in 2005–2024. This study contributes to the literature by linking the S4 fuelwood assortment with local biomass-energy availability and by analysing its monthly price–volume dynamics in an institutionally managed primary timber market. Monthly data from the State Forests National Forest Holding for five species groups—pine, spruce, oak, beech and birch—were used. The analysis combined descriptive statistics, seasonal indices, stationarity and cointegration diagnostics, Granger-type predictive tests and autoregressive distributed lag (ARDL)-type fixed-effects dynamic panel models. The results show that sales volume was more volatile than real prices and displayed strong seasonality, with the highest average sales in March and the lowest in January. Pine accounted for the largest share of sales volume, while oak and beech represented higher-priced segments. Between 2005 and 2024, total timber sales increased by 27.1%, whereas S4 fuelwood sales increased by 77.0%. The diagnostics did not provide consistent evidence of a stable long-term equilibrium between real prices and sales volume; therefore, the main econometric analysis focused on short-term dynamics. Lagged real price changes were positively and significantly associated with subsequent sales-volume dynamics, and this relationship remained robust across alternative lag specifications. The sum of lagged real-price coefficients was positive and statistically significant in all ARDL-type specifications, ranging from 1.053 to 2.162, with Wald-test p-values from <0.001 to 0.018. The findings indicate that fuelwood S4 should be interpreted not only as a timber assortment, but also as a limited forest bioenergy resource whose market behaviour is shaped by species structure, seasonal patterns and short-term adjustment within an institutionally managed timber sales system. Full article

The growing demand for wood raw materials and the need to reduce pressure on forest resources are driving the search for alternative wood species for industrial applications. In this context, paulownia wood is a promising raw material for the production of wood-based materials due to its rapid growth, the possibility of harvesting it from plantations, and its favorable strength-to-weight ratio. Its use can contribute to the diversification of the wood industry’s raw material base. The aim of this article is to systematize the current state of knowledge regarding the potential use of paulownia wood in the production of boards intended for interior design and construction, including particleboards, oriented strand boards (OSBs), plywood, solid wood panels (SWPs), and sandwich panels. The article analyzed the availability and properties of paulownia as a raw material for the board industry, the advantages and limitations associated with its use in specific technologies, and the environmental aspects resulting from its utilization. It was found that paulownia wood can be a valuable raw material for the production of lightweight wood-based boards and sandwich panels. However, its effective use requires adjustments to production technology, particularly the pressing parameters, the gluing process, and the composition of the boards’ raw materials. Further research should focus on optimizing manufacturing processes and verifying the feasibility of implementing this raw material in industrial production. Full article

This article presents a spatial assessment of rangeland productivity, forage resources, and the potential carrying capacity of saiga (Saiga tatarica (L., 1766)) habitats within the Korgalzhyn State Nature Reserve (Kazakhstan). This research integrated field geobotanical surveys, remote sensing data, and spatial modelling approaches. During fieldwork conducted in July 2025, 44 geobotanical descriptions were completed. Long-term Sentinel-2 imagery (2015–2025), spectral vegetation indices, and ensemble machine learning algorithms (Random Forest and Gradient Boosted Decision Trees) were used to model rangeland productivity. The study area includes 16 types of rangelands. The forage resource base is primarily formed by dry-steppe communities dominated by Stipa, Festuca, and Artemisia. At the same time, halophytic vegetation containing Atriplex, Bassia, and Halocnemum provides additional forage resources under arid and saline conditions. The total annual forage reserve was estimated at 3,308,921.2 centners, and the potential annual carrying capacity was calculated at 363,033 saiga individuals across 313,868 ha. These values represent the theoretical forage-carrying capacity of the territory and should not be interpreted as actual population estimates. The results demonstrate the effectiveness of integrating remote sensing, field observations, and machine learning methods for assessing forage resources and spatial heterogeneity of rangeland ecosystems in the steppe regions of Kazakhstan. Full article

Land-use conflicts in non-urbanized areas are fundamentally governance problems rather than purely environmental ones: sustainability outcomes increasingly depend on integrated, cross-sectoral decision-making reconciling forestry, agriculture, tourism, infrastructure, and urbanization within a finite land resource. This study examines whether statutory land acquisitions by a public forest administration can be understood as such a governance instrument rather than simply forest-area expansion, using an original transaction-level database of 911 land purchases by the Polish State Forests (Lasy Panstwowe) through statutory pre-emption rights between 2022 and mid-2026. The database covers 2806.1 hectares and, for the 903 transactions with a determinable price, approximately 114.2 million PLN. Using descriptive statistics, concentration indices (Gini, Herfindahl–Hirschman), an exploratory hedonic-style log–log regression of unit price on parcel area with location and year fixed effects, and a spatial-autocorrelation analysis (Moran’s I), the study examines spatial concentration, price differentiation, and parcel-size effects. Results show pronounced sub-regional concentration (county-level Gini = 0.615, more than double the voivodeship-level value of 0.284), a systematic price premium for parcels below 0.5 ha, and a dominant role of location over parcel size in explaining price variation (R-squared rising from 0.042 to 0.198 with location fixed effects); these are descriptive associations rather than causal estimates, given the absence of parcel-level quality covariates and a fully specified spatial–econometric model. The findings support interpreting statutory pre-emption purchases as a market-based institutional mechanism contributing to boundary rationalization, ownership consolidation, and mediation of competing land-use pressures, with implications for county-level monitoring and cross-sectoral coordination with spatial planning. Full article

As smart agriculture gradually shifts from single-yield monitoring toward the coordinated optimization of input efficiency, resource conservation, and farm profitability, the use of multi-source agricultural data to support precise water, fertilizer, and pesticide inputs has become an important issue. To address the inconsistent sampling frequencies, heterogeneous semantic scales, and difficulty in directly modeling input–profit relationships among field images, meteorological environments, soil states, and agricultural management records, a Multimodal Agricultural Input–Output Optimization Network, termed MAION, is proposed. In this framework, a unified plot–time-window agricultural state representation is constructed through a cross-modal spatiotemporal alignment module. The potential effects of different input behaviors on yield, cost, and net profit are estimated through an input–output causal profit modeling module, and profit-driven reinforcement learning is further used to generate input strategies oriented toward long-term net profit maximization. Since the task belongs to yield, cost, and profit regression prediction and continuous agricultural decision optimization rather than classification or recognition, classification metrics such as accuracy, precision, and recall were not adopted. Instead, RMSE, MAE, $R^2$, Net Profit Improvement, Input–Output Ratio, Cumulative Reward, Policy Stability, and Regret were used for evaluation. Experimental results show that MAION achieves the best performance in yield, cost, and net profit prediction, with RMSE values of $0.587$, $0.531$, and $0.648$, respectively, and corresponding $R^2$ values of $0.914$, $0.891$, and $0.883$. These results are markedly superior to those of Random Forest, XGBoost, LSTM, GRU, Transformer, Multimodal Transformer, and reinforcement learning baseline models. In the economic decision-making experiment, MAION achieves a Net Profit Improvement of $17.68\%$, an Input–Output Ratio of $1.71$, a Cost Efficiency Gain of $15.46\%$, and a Cumulative Reward of $301.27$, while obtaining the lowest policy fluctuation and regret. The results indicate that the proposed framework can provide effective data-driven decision support for precision input, cost control, and profit optimization in smart agriculture. Full article

Pipeline corrosion critically threatens the safe operation of chemical industrial park pipeline networks, making accurate corrosion growth prediction essential for preventing catastrophic failures. Mechanistic models assume steady states, which conflict with in-service corrosion dynamics; data-driven approaches, however, presume complete datasets but frequently face missing parameters due to sensor failures and limited samples from costly inspections, increasing the risk of noise and overfitting. In this paper, the TinyTransCorrosion model was proposed, which is a lightweight Transformer-based corrosion growth prediction model specifically designed for small-sample scenarios. A cross-validation residual analysis is employed for data cleaning, while five physical embedding features are constructed to encode domain knowledge and compensate for missing parameters. A compact Transformer encoder containing only 6433 parameters was adopted, and a corrosion gating mechanism along with a classification (CLS) token was introduced to achieve efficient feature interaction. Evaluated on a real-world pipeline inspection dataset with 215 records, TinyTransCorrosion attains an R² of 0.6411 and an MAE of 0.1608 mm, outperforming nine conventional baseline models, including Mean predictor, Linear Regression, Ridge, SVR-RBF, Random Forest, XGBoost, LSTM, MLP, and CNN. While these results are limited to a single-site dataset and require external validation on independent multi-source data, the proposed lightweight physics-guided architecture demonstrates promising predictive capability for small-sample pipeline corrosion assessment, with model error approaching the metrological limit imposed by field ultrasonic gauge accuracy. It provides an acceptable pathway for prioritizing inspection intervals and optimizing maintenance scheduling in resource-constrained industrial settings. Full article

Groundwater is an essential natural resource for human societies and ecosystems. Traditional groundwater monitoring relies on in situ wells, which are susceptible to discontinuity, influencing water resource management. To overcome this deficiency, this study proposes a remote sensing-based groundwater level (GWL) monitoring system that uses machine learning (ML) algorithms and remotely sensed hydrological parameters to reconstruct well-specific GWL time series. Four machine learning algorithms, including K-Nearest Neighbor (KNN), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and a weight-mean Ensemble strategy, were adopted to construct the models at each well individually for monitoring GWL. Specifically, the GWL data for ~770 wells across the conterminous United States (CONUS) were modeled using remotely sensed precipitation (P), evapotranspiration (ET), terrestrial water storage anomaly (TWSA), and soil moisture (SM) datasets during the period from 2004 to 2019. Afterwards, the performances of models were evaluated during an independent period from 2020 to 2023. The results show that the Ensemble model outperforms the individual baseline models evaluated in this study (i.e., KNN, RF, and XGBoost), achieving a mean coefficient of determination (R²) of 0.81, root mean square error (RMSE) of 0.34 m, normalized RMSE (NRMSE) of 11.8%, and Nash–Sutcliffe efficiency (NSE) of 0.78. The results demonstrate that the proposed system can effectively reconstruct GWL dynamics for most wells. This can be a compensation for missing records for hydrologically significant wells, which are those with historical groundwater observations. Full article

Background: Sub-Saharan Africa suffers the greatest impact of malaria, with the 2024 Health Organization (WHO )report stating that the region represents 94% of global cases and 95% of deaths. Challenges in malaria elimination stem from weak health systems and limitations of traditional diagnostic methods like microscopy and malaria Rapid Diagnostic Tests (mRDTs), which result in missed diagnoses, delays in treatment, and preventable fatalities in resource-limited settings. This paper addresses these diagnostic limitations by developing and systematically evaluating a machine learning (ML) framework for malaria diagnosis that leverages routine clinical symptoms and demographic information tailored for these environments. Methods: Examining 637 patient records from Gutu Mission Hospital and Gweru Provincial Hospital in Zimbabwe, the research analyzed clinical symptoms (fever, chills, abdominal pain, headache, diarrhea) and demographic data (age, gender, residence, travel history). Data preprocessing involved addressing class imbalance with the Synthetic Minority Oversampling Technique (SMOTE) and employing Recursive Feature Elimination (RFE) for feature selection. Seven ML models were trained: Logistic Regression, Random Forest, Decision Trees, Gradient Boosting, K-Nearest Neighbor, Naive Bayes, and XGBoost. These individual models were used to construct ensemble models like Bagging, Stacking, Soft Voting, and AdaBoost. Performance metrics included accuracy, precision, confusion matrices, recall, F1 score, and AUC-ROC. Results: Statistically significant predictors for malaria included chills (p = 0.001), fever (p = 0.003), diarrhea (p = 0.01), and abdominal pain (p < 0.001), with travel history showing significance among demographic factors (p = 0.02). The stacking ensemble model yielded superior performance, achieving an accuracy of 0.96, precision of 0.95, recall of 0.98, F1 score of 0.96, and AUC-ROC of 0.98. Conclusions: This study underscores the potential of ML, particularly ensemble techniques, to enhance malaria management in resource-limited settings, providing a scalable and cost-effective diagnostic alternative that utilizes accessible clinical and demographic data, thereby supporting healthcare workers and control programs in areas where traditional methods are inadequate. Full article

Background: Postoperative haemorrhage (POH) is a rare but potentially life-threatening complication of thyroid surgery, with an incidence of 0.6–4%. Early identification of patients at increased risk is critical to guide perioperative management, especially in the context of evolving surgical practices and increasing demand for outpatient procedures. Methods: We conducted an explorative, retrospective, single-centre case–control study using a prospectively documented quality assurance dataset including 9158 thyroidectomies (2012–2019). POH requiring revision (n = 104) were compared to matched controls (n = 416; 1:4 ratio), matched by age, sex, type of procedure (uni- vs. bilateral), and year of surgery. Univariate analysis (Chi-square and t-test) was used to identify possible associations between candidate risk factors and POH. To supplement classical univariate statistics, we applied a Random Forest machine learning model to assess the relative importance of 25 potential variables derived from the clinical dataset based on previous literature. It was also planned to use the results to develop a proposal for a quantitative risk score, system, assigning weights to each factor (3, 1, or 0 points) depending on their relative importance for predicting POH. Patients were subsequently categorized into risk classes (low, intermediate, high) based on total point scores and reclassified. Results: High-impact risk factors confirmed in univariate analysis and Random Forest modelling included reoperative thyroidectomy, smoking, relevant comorbidities, medical treatment for hyperthyroidism and advanced age and were weighted with 3 points. Moderately associated variables such as regular alcohol consumption, Graves’ disease, hyperthyroid state at surgery, duration of the procedure and thyroid weight were weighted 1 point. Factors with negligible predictive value (e.g., BMI, gender, ASA classification) were assigned 0 points. The average score among patients without haemorrhage was 5.21, whereas the average score among patients with haemorrhage was 7.61. Within the matched study cohort, patients with POH accumulated higher risk scores than controls, suggesting potential discriminatory capacity. These findings formed the basis for the development of an exploratory three-stage ‘traffic light’ risk stratification model that requires external validation. Conclusions: A simple, interpretable point-based scoring system derived from a large matched case–control cohort identified key predictors of postoperative hemorrhage (POH) after thyroid surgery and enabled risk stratification within the study population. By combining conventional statistical methods with machine-learning approaches, the score may support individualized perioperative monitoring, surgical planning, and institutional resource allocation. However, because the model was developed using a 1:4 matched case–control design, it should be considered an exploratory risk stratification tool rather than a fully validated prediction model, and it does not directly estimate absolute POH risk or population incidence. External and prospective validation in large, representative multicentre cohorts (e.g., StuDoQ, HEDOS) is ongoing and will be required to establish calibration, generalizability, and clinical utility. Full article

This study evaluates the spatial variability of hydric stress in the State of Sinaloa, northwestern Mexico, through the integrated analysis of hydroclimatic variables, multispectral remote sensing indicators, and environmental factors. Historical hydroclimatic conditions were analyzed using meteorological records from 1961 to 2020, whereas Landsat 8 imagery acquired on 7 July 2025, was used to evaluate the spatial expression of hydric stress. Reference evapotranspiration (ETo) was estimated using the FAO-56 Penman–Monteith methodology, and hydrological deficit conditions were determined from the relationship between precipitation (P) and ETo. Spectral indicators including land surface temperature ($\overline{T}$_a), the Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI), and the NDWI/MNDWI relationship were used to evaluate vegetation response, surface moisture conditions, and thermal anomalies associated with hydric stress. The results revealed persistent conditions where ETo systematically exceeded P, with hydrological deficit values ranging from approximately −1600 mm·year⁻¹ to localized positive values near 50 mm·year⁻¹. The most severe deficits were concentrated within the northwestern and north-central agricultural valleys of Sinaloa. Statistical validation revealed significant negative relationships between hydrological deficit and all evaluated spectral indicators. The strongest association was observed for MNDWI (R² = 0.387), followed by NDWI/MNDWI (R² = 0.277), NDWI (R² = 0.220), and NDVI (R² = 0.134), confirming the sensitivity of vegetation and moisture-related indicators to long-term hydrological stress conditions. Spatial analyses revealed a strong correspondence among low NDVI, negative NDWI and MNDWI responses, elevated $\overline{T}$_a, and regions characterized by high atmospheric evaporative demand. Additional spatial validation integrating land-use and vegetation-cover changes (1993–2011), regional geology, topography, and the distribution of highly productive agricultural valleys demonstrated that the most severe hydrological deficits coincided with areas affected by vegetation-cover loss, agricultural expansion, and intensive land use. Although these datasets correspond to different observation periods, they collectively reflect the cumulative environmental effects associated with persistent hydrological stress across the region. The combined effects of hydrological imbalance, forest-cover reduction, and agricultural intensification have progressively reduced ecosystem resilience and increased environmental vulnerability throughout one of the most productive agricultural regions of northwestern Mexico. These findings provide a scientific basis for water-resource management, territorial planning, ecosystem restoration, and climate-adaptation strategies under increasing water-scarcity conditions. Full article