Search Results (287)

In various applications, IoT temporal data play a crucial role in accurately predicting future trends. Traditional models, including Rolling Window, SVR-RBF, and ARIMA, suffer from a potential accuracy decrease because they generally use all available data or the most recent data window during training, which can result in the inclusion of noisy data. To address this critical issue, this paper proposes a new forecasting technique called Adaptive Holt–Winters (AHW). The AHW approach utilizes two models grounded in an exponential smoothing methodology. The first model is trained on the most current data window, whereas the second extracts information from a historical data segment exhibiting patterns most analogous to the present. The outputs of the two models are then combined, demonstrating enhanced prediction precision since the focus is on the relevant data patterns. The effectiveness of the AHW model is evaluated against well-known models (Rolling Window, SVR-RBF, ARIMA, LSTM, CNN, RNN, and Holt–Winters), utilizing various metrics, such as RMSE, MAE, p-value, and time performance. A comprehensive evaluation covers various real-world datasets at different granularities (daily and monthly), including temperature from the National Climatic Data Center (NCDC), humidity and soil moisture measurements from the Basel City environmental system, and global intensity and global reactive power from the Individual Household Electric Power Consumption (IHEPC) dataset. The evaluation results demonstrate that AHW constantly attains higher forecasting accuracy across the tested datasets compared to other models. This indicates the efficacy of AHW in leveraging pertinent data patterns for enhanced predictive precision, offering a robust solution for temporal IoT data forecasting. Full article

In a warming climate, rising temperature are expected to influence atmospheric humidity. This study examined the spatio-temporal dynamics of temperature (TEMP) and relative humidity (RH) across Equatorial Africa from 1980 to 2020. The analysis used RH data from European Centre of Medium-range Weather Forecasts Reanalysis v.5 (ERA5) reanalysis, TEMP and precipitation (PRE) from Climate Research Unit (CRU), and soil moisture (SM) and evapotranspiration (ET) from the Global Land Evaporation Amsterdam Model (GLEAM). In addition, four teleconnection indices were considered: El Niño-Southern Oscillation (ENSO), Indian Ocean Dipole (IOD), North Atlantic Oscillation (NAO), and Pacific Decadal Oscillation (PDO). This study used the Mann–Kendall test and Sen’s slope estimator to analyze trends, alongside multiple linear regression to investigate the relationships between TEMP, RH, and key climatic variables—namely evapotranspiration (ET), soil moisture (SM), and precipitation (PRE)—as well as large-scale teleconnection indices (e.g., IOD, ENSO, PDO, and NAO) on annual and seasonal scales. The key findings are as follows: (1) mean annual TEMP exceeding 30 °C and RH less than 30% were concentrated in arid regions of the Sahelian–Sudano belt in West Africa (WAF), Central Africa (CAF) and North East Africa (NEAF). Semi-arid regions in the Sahelian–Guinean belt recorded moderate TEMP (25–30 °C) and RH (30–60%), while the Guinean coastal belt and Congo Basin experienced cooler, more humid conditions (TEMP < 20 °C, RH (60–90%). (2) Trend analysis using Mann–Kendal and Sen slope estimator analysis revealed spatial heterogeneity, with increasing TEMP and deceasing RH trends varying by region and season. (3) The warming rate was higher in arid and semi-arid areas, with seasonal rates exceeding annual averages (0.18 °C decade⁻¹). Winter (0.27 °C decade⁻¹) and spring (0.20 °C decade⁻¹) exhibited the strongest warming, followed by autumn (0.18 °C decade⁻¹) and summer (0.10 °C decade⁻¹). (4) RH trends showed stronger seasonal decline compared to annual changes, with reduction ranging from 5 to 10% per decade in certain seasons, and about 2% per decade annually. (5) Pearson correlation analysis demonstrated a strong negative relationship between TEMP and RH with a correlation coefficient of r = − 0.60. (6) Significant associations were also observed between TEMP/RH and both climatic variables (ET, SM, PRE) and large scale-teleconnection indices (ENSO, IOD, PDO, NAO), indicating that surface conditions may reflect a combination of local response and remote climate influences. However, further analysis is needed to distinguish the extent to which local variability is independently driven versus being a response to large-scale forcing. Overall, this research highlights the physical mechanism linking TEMP and RH trends and their climatic drivers, offering insights into how these changes may impact different ecological and socio-economic sectors. Full article

Surface soil moisture (SM) is a critical factor in hydrological modeling, agricultural management, and numerical weather forecasting. This paper presents a highly effective soil moisture retrieval algorithm developed for the FY-3E (FengYun-3E) GNOS-R (GNSS Occultation Sounder II-Reflectometry) instrument. The algorithm incorporates a first-order vegetation model that considers vegetation density and volume scattering. Utilizing multi-angle GNOS-R observations, the algorithm derives surface reflectivity, which is combined with ancillary data on opacity, vegetation water content, and soil moisture from SMAP (Soil Moisture Active Passive) to optimize the retrieval process. The algorithm has been specifically tailored for different surface conditions, including bare soil, areas with low vegetation, and densely vegetated regions. The algorithm directly incorporates the angle-dependence of observations, leading to enhanced retrieval accuracy. Additionally, a new approach parameterizes surface roughness as a function of angle, allowing for refined corrections in reflectivity measurements. For vegetated areas, the algorithm effectively isolates the soil surface signal by eliminating volume scattering and vegetation effects, enabling the accurate estimation of soil moisture. By leveraging multi-angle data, the algorithm achieves significantly improved retrieval accuracy, with root mean square errors of 0.0235, 0.0264, and 0.0191 (g/cm³) for bare, low-vegetation, and dense-vegetation areas, respectively. This innovative methodology offers robust global soil moisture estimation capabilities using the GNOS-R instrument, surpassing the accuracy of previous techniques. Full article

Accurately representing land–atmosphere interactions is essential for numerical weather prediction models, as they have a significant effect on forecasted near-surface meteorological parameters. We used the SURFEX soil model, coupled with the AROME non-hydrostatic numerical weather prediction model at HungaroMet Hungarian Meteorological Service. Land data assimilation techniques are employed to provide the most accurate initial conditions for the AROME-SURFEX system. Initially, the Optimal Interpolation (OI) method was applied to determine the initial conditions for soil temperature and moisture. This study focuses on implementing the more complex and advanced Simplified Extended Kalman Filter (SEKF) for surface data assimilation. The SEKF corrects the soil temperature and soil moisture content using screen-level observations (2-m temperature and relative humidity), offering improvements over OI. We highlight the advantages of the SEKF across different seasons, noting that it is a more physically-based approach with dynamically varying Jacobians. We demonstrate how outlier Jacobians can be filtered using linearity check to handle system nonlinearity. The tuning of appropriate data assimilation parameters, such as observational and background errors, is also crucial for achieving optimal results. We evaluate the impact of the SEKF by conducting forecast verification against in situ atmospheric observations, comparing its performance with that of OI. Our results indicate a significant improvement in winter forecasts. Additionally, a moderate improvement is observed in spring, highlighting the seasonal dependency of the efficiency of the SEKF. Full article

Accurate irrigation volume prediction is crucial for sustainable agriculture. This study enhances precision irrigation by integrating diverse datasets, including historical irrigation records, soil moisture, and climatic factors, collected from a small-scale commercial estate vineyard in southwestern Idaho, the United States of America (USA), over a period of three years (2017–2019). Focusing on long-term irrigation forecasting, addressing a critical gap in sustainable water management, we use machine learning (ML) methods to predict future irrigation needs, with improved accuracy. We designed, developed, and tested a Long Short-Term Memory (LSTM) model, which achieved a Mean Squared Error (MSE) of 0.37, and evaluated its performance against a simpler baseline linear regression (LinReg) model, which yielded a higher MSE of 1.29. We validate the results of the LSTM model using a cross-validation technique, wherein a mean MSE of 0.18 was achieved. The low value of the statistical analysis (p-value = 0.0009) of a paired t-test confirmed that the improvement is significant. This research shows the potential of Artificial Intelligence (AI) to optimize irrigation planning and advance sustainable precision agriculture (PA), by providing a practical tool for long-term forecasting and that supports data-driven decisions. Full article

Weather forecasting is essential for agriculture, yet current methods often lack the localized accuracy required to manage extreme weather events and optimize irrigation. The MAGDA Horizon Europe/EUSPA project addresses this gap by developing a modular system that integrates novel European space-based, airborne, and ground-based technologies. Unlike conventional forecasting systems, MAGDA enables precise, field-level predictions through the integration of cutting-edge technologies: Meteodrones provide vertical atmospheric profiles where traditional data are sparse; GNSS-reflectometry offers real-time soil moisture insights; and all observations feed into convection-permitting models for accurate nowcasting of extreme events. By combining satellite data, GNSS, Meteodrones, and high-resolution meteorological models, MAGDA enhances agricultural and water management with precise, tailored forecasts. Climate change is intensifying extreme weather events such as heavy rainfall, hail, and droughts, threatening both crop yields and water resources. Improving forecast reliability requires better observational data to refine initial atmospheric conditions. Recent advancements in assimilating reflectivity and in situ observations into high-resolution NWMs show promise, particularly for convective weather. Experiments using Sentinel and GNSS-derived data have further improved severe weather prediction. MAGDA employs a high-resolution cloud-resolving model and integrates GNSS, radar, weather stations, and Meteodrones to provide comprehensive atmospheric insights. These enhanced forecasts support both irrigation management and extreme weather warnings, delivered through a Farm Management System to assist farmers. As climate change increases the frequency of floods and droughts, MAGDA’s integration of high-resolution, multi-source observational technologies, including GNSS-reflectometry and drone-based atmospheric profiling, is crucial for ensuring sustainable agriculture and efficient water resource management. Full article

Soil moisture (SM) estimates are essential for drought monitoring, hydrological modeling, and climate resilience planning applications. While satellite and model-derived SM products effectively capture SM dynamics, their coarse spatial resolutions (~10–36 km) hinder their ability to represent SM variability in heterogeneous landscapes influenced by local factors. This study proposes a novel downscaling framework that employs an Artificial Neural Network (ANN) on a cloud-computing platform to improve the spatial resolution and representation of multi-source SM datasets. A data analysis was conducted by integrating Google Earth Engine (GEE) with the computing capabilities of the python language through Google Colab. The framework downscaled Soil Moisture Active Passive (SMAP), European Centre for Medium-Range Weather Forecasts Reanalysis 5th Generation (ERA5-Land), and Famine Early Warning Systems Network Land Data Assimilation System (FLDAS) at 500 m for Kenya, East Africa. This was achieved by leveraging ten input variables comprising elevation, slope, surface albedo, vegetation, soil texture, land surface temperatures (day and night), evapotranspiration, and geolocations. The coarse SM datasets exhibited spatiotemporal consistency, with a standard deviation below 0.15 m³/m³, capturing over 95% of the variability in the original data. Validation against in situ SM data at the station confirmed the framework’s reliability, achieving an average UbRMSE of less than 0.04 m³/m³ and a correlation coefficient (r) over 0.52 for each downscaled dataset. Overall, the framework improved significantly in r values from 0.48 to 0.64 for SMAP, 0.47 to 0.63 for ERA5-Land, and 0.60 to 0.69 for FLDAS. Moreover, the performance of FLDAS and its downscaled version across all climate zone is consistent. Despite the uncertainties among the datasets, the framework effectively improved the representation of SM variability spatiotemporally. These results demonstrate the framework’s potential as a reliable tool for enhancing SM applications, particularly in regions with complex environmental conditions. Full article

Soil pore water electrical conductivity (EC), as a comprehensive indicator of soil nutrient status, is closely linked to crop growth and development. Accurate prediction of pore water EC is therefore essential for informed and scientific crop management. This study focuses on a greenhouse rose cultivation site in Jiangchuan District, Yuxi City, Yunnan Province, China. Leveraging multi-parameter sensors deployed within the facility, we collected continuous soil data (temperature, moisture, EC, and pore water EC) and meteorological data (air temperature, humidity, and vapor pressure deficit) from January to December of 2024. We propose a hybrid prediction model—PSO–CNN–LSTM–BOA–XGBoost (PCLBX)—that integrates a particle swarm optimization (PSO)-enhanced convolutional LSTM (CNN–LSTM) with a Bayesian optimization algorithm-tuned XGBoost (BOA–XGBoost). The model utilizes highly correlated environmental variables to forecast soil pore water EC. The experimental results demonstrate that the PCLBX model achieves a mean square error (MSE) of 0.0016, a mean absolute error (MAE) of 0.0288, and a coefficient of determination (R²) of 0.9778. Compared to the CNN–LSTM model, MSE and MAE are reduced by 0.0001 and 0.0014, respectively, with an R² increase of 0.0015. Against the BOA–XGBoost model, PCLBX yields a reduction of 0.0006 in MSE and 0.0061 in MAE, alongside a 0.0077 improvement in R². Furthermore, relative to an equal-weight ensemble of CNN–LSTM and BOA–XGBoost, the PCLBX model shows improved performance, with MSE and MAE decreased by 0.0001 and 0.0005, respectively, and R² increased by 0.0007. These results underscore the superior predictive capability of the PCLBX model over individual and ensemble baselines. By enhancing the accuracy and robustness of soil pore water EC prediction, this model contributes to a deeper understanding of soil physicochemical dynamics and offers a scalable tool for intelligent perception and forecasting. Importantly, it provides agricultural researchers and greenhouse managers with a deployable and generalizable framework for digital, precise, and intelligent management of soil water and nutrients in protected horticulture systems. Full article

This study presents an explainable machine learning framework to forecast groundwater storage dynamics, quantified as the Lake Water Equivalent (LWE), in the Urmia Lake Basin from 2003 to 2023. Satellite-based observations (GRACE, GLDAS) and climatic variables were integrated to model LWE variability. An ensemble learning approach was employed, combining Ridge Regression and Random Forest enhanced through feature re-weighting based on XGBoost-derived importance scores. Model interpretability was addressed using SHapley Additive exPlanations (SHAP), offering transparent insights into the contributions of climatic drivers. Results demonstrated that the Random Forest model achieved superior performance (RMSE = 3.27; $R^2$ = 0.89), with SHAP analysis highlighting the dominant influence of recent LWE values, temperature, and soil moisture. The proposed framework outperformed baseline models including Persistence, Standard Ridge Regression, and XGBoost in terms of both accuracy and explainability. The objectives of this study are (i) to forecast the LWE in the Urmia Lake Basin using an ensemble-based machine learning framework, (ii) to enhance predictive modeling through XGBoost-guided feature weighting, and (iii) to improve model transparency and interpretation using SHAP-based explainability techniques. By integrating ensemble learning with explainable AI, this work advances the transparent data-driven forecasting essential for sustainable groundwater management under climatic uncertainty. Full article

On 27 February 2023, the municipality of Itajubá in southeastern Brazil experienced a short-duration yet high-intensity rainfall event, causing significant socio-economic impacts. Hence, this study evaluates the performance of the Weather Research and Forecasting (WRF) model in simulating this extreme event through a set of sensitivity numerical experiments. The control simulation followed the operational configuration used daily by the Center for Weather and Climate Forecasting Studies of Minas Gerais (CEPreMG). Additional experiments tested the use of different microphysics schemes (WSM3, WSM6, WDM6), initial and boundary conditions (GFS, GDAS, ERA5), and surface datasets (sea surface temperature and soil moisture from ERA5 and GDAS). The model’s performance was evaluated by comparing the simulated variables with those from various datasets. We primarily focused on the representation of the spatial precipitation pattern, statistical metrics (bias, Pearson correlation, and Kling–Gupta Efficiency), and atmospheric instability indices (CAPE, K, and TT). The results showed that none of the simulations accurately captured the amount and spatial distribution of precipitation over the region, likely due to the complex topography and convective nature of the studied event. However, the WSM3 microphysics scheme and the use of ERA5 SST data provided slightly better representation of instability indices, although these configurations still underperformed in simulating the rainfall intensity. All simulations overestimated the instability indices compared to ERA5, although ERA5 itself may underestimate the convective environments. Despite some performance limitations, the sensitivity experiments provided valuable insights into the model’s behavior under different configurations for southeastern Brazil—particularly in a convective environment within mountainous terrain. However, further evaluation across multiple events is recommended. Full article

Accurately estimating soil moisture (SM) without direct measurements poses significant challenges due to nonlinear interactions in meteorological variables and the lagged response of SM to precipitation. This study evaluates two approaches: the auto-regressive integrated moving average (ARIMA) model for one-day-ahead SM forecasting and a K-means clustering-based multilayer perceptron (K-MLP) for real-time SM estimation at depths of 5 cm, 20 cm, and 50 cm in Changbai Mountain region. Although the K-MLP model outperformed the MLP model, achieving a maximum R² of 0.728, its estimation accuracy remains suboptimal. By contrast, the ARIMA model effectively leveraged SM persistence, achieving high accuracy in one-day-ahead forecasting. Specifically, the ARIMA (0, 1, 6), ARIMA (1, 1, 2), and ARIMA (2, 1, 1) models yield R² values of 0.9677, 0.9853, and 0.9684 and RMSE values of 0.02 m³·m³, 0.015 m³·m³, and 0.006 m³·m³ at depths of 5 cm, 20 cm, and 50 cm, respectively. This study explores ARIMA’s robustness in short-term SM forecasting and its adaptability to dynamic meteorological conditions, offering potential applications in agricultural water management and ecological monitoring. Full article

Effective and sustainable water reserve management faces increasing challenges due to climate-induced variability, data fragmentation, and the limitations of traditional, static modeling systems. This study introduces a conceptual framework designed to address these challenges by integrating digital twins, IoT-driven real-time monitoring, game engine simulations, and AI-driven decision support systems (AI-DSS). The methodology involves constructing a digital twin ecosystem using IoT sensors, GIS layers, remote-sensing imagery, and game engines. This ecosystem simulates water dynamics and assesses policy interventions in real time. AI components, including machine-learning models and retrieval-augmented generation (RAG) chatbots, are embedded to synthesize real-time data into actionable insights. The framework enables the continuous assessment of hydrological dynamics, predictive risk analysis, and immersive, scenario-based decision-making to support long-term water sustainability. Simulated scenarios demonstrate accurate flood forecasting under variable rainfall intensities, early drought detection based on soil moisture and flow data, and real-time water-quality alerts. Digital elevation models from UAV photogrammetry enhance terrain realism, and AI models support dynamic predictions. Results show how the framework supports proactive mitigation planning, climate adaptation, and stakeholder communication in pursuit of resilient and sustainable water governance. By enabling early intervention, efficient resource allocation, and participatory decision-making, the proposed system fosters long-term, sustainable water security and environmental resilience. This conceptual framework suggests a pathway toward more transparent, data-informed, and resilient decision-making processes in water reserves management, particularly in regions facing climatic uncertainty and infrastructure limitations, aligning with global sustainability goals and adaptive water governance strategies. Full article

Accurate flood monitoring and forecasting techniques are important and continue to be developed for improved disaster preparedness and mitigation. Flood estimation using satellite observations with deep learning algorithms is effective in detecting flood patterns and environmental relationships that may be overlooked by conventional methods. Soil Moisture Active Passive (SMAP) fractional water (FW) was used as a reference to estimate flood areas in a long short-term memory (LSTM) model using a combination of soil moisture information, rainfall forecasts, and floodplain topography. To perform flood modeling in LSTM, datasets with different spatial resolutions were resampled to 30 m spatial resolution using bicubic interpolation. The model’s efficacy was quantified by validating the LSTM-based flood inundation area with a water mask from Senti-nel-1 SAR images for regions with different topographic characteristics. The average area under the curve (AUC) value of the LSTM model was 0.93, indicating a high accuracy estimation of FW. The confusion matrix-derived metrics were used to validate the flood inundation area and had a high-performance accuracy of ~0.9. SMAP FW showed optimal performance in low-covered vegetation, seasonal water variations and flat regions. The estimates of flood inundation areas show the methodological promise of the proposed framework for improved disaster preparedness and resilience. Full article

Having good replication of the soil moisture evolution is desirable to properly simulate the dust emissions and atmospheric dust load because soil moisture increases the cohesive forces of soil particles, modulating the wind erosion threshold above which emissions occur. To reduce errors, one can use soil moisture retrievals from space-borne microwave radiometers. Here, we explore the potential of inserting soil moisture retrievals from the Soil Moisture Active Passive (SMAP) satellite into the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem) to improve dust simulations. We focus our analysis on the contiguous U.S. due to the presence of important dust sources and good observational networks. Our analysis extends over the first year of SMAP retrievals (1 April 2015–31 March 2016) to cover the annual soil moisture variability and go beyond extreme events, such as dust storms, in order to provide a statistically robust characterization of the potential added value of the soil moisture retrievals. We focus on the Goddard Chemistry Aerosol Radiation and Transport (GOCART) model from the Air Force Weather Agency (GOCART-AFWA) dust emission parameterization that represents soil moisture modulations of the wind erosion threshold with a parameterization developed by fitting observations. The dust emissions are overestimated by the GOCART-AFWA parameterization and result in an overestimation of the aerosol optical depth (AOD). Sensitivity experiments show that emissions reduced to 25% in the GOCART-AFWA simulations largely reduced the AOD bias over the Southwest and lead to better agreement with the standard WRF-Chem parameterization of dust emissions (GOCART) and with observations. Comparisons of GOCART-AFWA simulations with emissions reduced to 25% with and without SMAP soil moisture insertion show added value of the retrievals, albeit small, over the dust sources. These results highlight the importance of accurate dust emission parameterizations when evaluating the impact of remotely sensed soil moisture data on numerical weather prediction models. Full article

Hydrology relates to many complex challenges due to climate variability, limited resources, and especially, increased demands on sustainable management of water and soil. Conventional approaches often cannot respond to the integrated complexity and continuous change inherent in the water system; hence, researchers have explored advanced data-driven solutions. This review paper revisits how artificial intelligence (AI) is dramatically changing the most important facets of hydrological research, including soil and land surface modeling, streamflow, groundwater forecasting, water quality assessment, and remote sensing applications in water resources. In soil and land modeling, AI techniques could further enhance accuracy in soil texture analysis, moisture estimation, and erosion prediction for better land management. Advanced AI models could also be used as a tool to forecast streamflow and groundwater levels, therefore providing valuable lead times for flood preparedness and water resource planning in transboundary basins. In water quality, AI-driven methods improve contamination risk assessment, enable the detection of anomalies, and track pollutants to assist in water treatment processes and regulatory practices. AI techniques combined with remote sensing open new perspectives on monitoring water resources at a spatial scale, from flood forecasting to groundwater storage variations. This paper’s synthesis emphasizes AI’s immense potential in hydrology; it also covers the latest advances and future prospects of the field to ensure sustainable water and soil management. Full article