Search Results (139)

The time series prediction of visibility in terms of various meteorological variables, such as relative humidity, temperature, atmospheric pressure, and wind speed, is presented in this paper using Single-Variable Regression Analysis (SVRA), Artificial Neural Network (ANN), and Hybrid Adaptive Neuro-fuzzy Inference System (ANFIS) techniques for several sub-tropical locations. The initial method used for the prediction of visibility in this study was the SVRA, and the results were enhanced using the ANN and ANFIS techniques. Throughout the study, neural networks with various algorithms and functions were trained with different atmospheric parameters to establish a relationship function between inputs and visibility for all locations. The trained neural models were tested and validated by comparing actual and predicted data to enhance visibility prediction accuracy. Results were compared to assess the efficiency of the proposed systems, measuring the root mean square error (RMSE), coefficient of determination (R²), and mean bias error (MBE) to validate the models. The standard statistical technique, particularly SVRA, revealed that the strongest functional relationship was between visibility and RH, followed by WS, T, and P, in that order. However, to improve accuracy, this study utilized back propagation and hybrid learning algorithms for visibility prediction. Error analysis from the ANN technique showed increased prediction accuracy when all the atmospheric variables were considered together. After testing various neural network models, it was found that the ANFIS model provided the most accurate predicted results, with improvements of 31.59%, 32.70%, 30.53%, 28.95%, 31.82%, and 22.34% over the ANN for Durban, Cape Town, Mthatha, Bloemfontein, Johannesburg, and Mahikeng, respectively. The neuro-fuzzy model demonstrated better accuracy and efficiency by yielding the finest results with the lowest RMSE and highest R² for all cities involved compared to the ANN model and standard statistical techniques. However, the statistical performance analysis between measured and estimated visibility indicated that the ANN produced satisfactory results. The results will find applications in Optical Wireless Communication (OWC), flight operations, and climate change analysis. Full article

Accurate river discharge forecasting remains a critical challenge in hydrology, particularly in data-scarce mountainous regions where in situ observations are limited. This study investigated the potential of long short-term memory (LSTM) networks to improve discharge prediction by leveraging spatially distributed reanalysis data. Using the ERA5-Land dataset, we developed an LSTM model that integrates grid-based meteorological inputs and assesses their relative importance. We conducted experiments on two snow-dominated basins with contrasting physiographic characteristics, the Uba River basin in Kazakhstan and the Flathead River basin in the USA, to answer three research questions: (1) whether full-grid input outperforms reduced configurations and models trained on Caravan, (2) the impact of spatial resolution on accuracy and efficiency, and (3) the effect of partial spatial coverage on prediction reliability. Specifically, we compared the full-grid LSTM with a single-cell LSTM, a basin-average LSTM, a Caravan-trained LSTM, and coarser cell aggregations. The results demonstrate that the full-grid LSTM consistently yields the highest forecasting performance, achieving a median Nash–Sutcliffe efficiency of 0.905 for Uba and 0.93 for Middle Fork Flathead, while using coarser grids and random subsets reduces performance. Our findings highlight the critical importance of spatial input richness and provide a reproducible framework for grid selection in flood-prone basins lacking dense observation networks. Full article

Accurate crop yield prediction is essential for stabilizing food supply chains and reducing the uncertainties in financial risks related to agricultural production. Yet, it is even more essential to understand how crop yield models make predictions depending on their relationship to Earth Observation (EO) indicators. This study presents a state-of-the-art explainable artificial intelligence (XAI) method to estimate corn yield prediction over the Corn Belt in the continental United States (CONUS). We utilize the recently introduced Kolmogorov–Arnold Network (KAN) architecture, which offers an interpretable alternative to the traditional Multi-Layer Perceptron (MLP) approach by utilizing learnable spline-based activation functions instead of fixed ones. By including a KAN in our crop yield prediction framework, we are able to achieve high prediction accuracy and identify the temporal drivers behind crop yield variability. We create a multi-source dataset that includes biophysical parameters along the crop phenology, as well as meteorological, topographic, and soil parameters to perform end-of-season and in-season predictions of county-level corn yields between 2016–2023. The performance of the KAN model is compared with the commonly used traditional machine learning (ML) models and its architecture-wise equivalent MLP. The KAN-based crop yield model outperforms the other models, achieving an R² of 0.85, an RMSE of 0.84 t/ha, and an MAE of 0.62 t/ha (compared to MLP: R² = 0.81, RMSE = 0.95 t/ha, and MAE = 0.71 t/ha). In addition to end-of-season predictions, the KAN model also proves effective for in-season yield forecasting. Notably, even three months prior to harvest, the KAN model demonstrates strong performance in in-season yield forecasting, achieving an R² of 0.82, an MAE of 0.74 t/ha, and an RMSE of 0.98 t/ha. These results indicate that the model maintains a high level of explanatory power relative to its final performance. Overall, these findings highlight the potential of the KAN model as a reliable tool for early yield estimation, offering valuable insights for agricultural planning and decision-making. Full article

Background/Objectives: A critical part of the maize life cycle takes place during the summer, and due to climate change, its growth and development are increasingly exposed to the irregular and unpredictable effects of drought stress. Developing and using new cultivars with increased drought tolerance for farmers is the easiest and cheapest solution. One of the concepts to screen for drought tolerance is to expose germplasm to various growth scenarios (environments), expecting that random drought will occur in some of them. Methods: In the present study, thirty-two maize hybrids belonging to four FAO maturity groups were tested for grain yield at six locations over two consecutive years. In parallel, data of the basic meteorological elements such as air temperature, relative humidity and precipitation were collected and used to compute two indices, scPDSI (Self-calibrating Palmer Drought Severity Index) and VPD (Vapor Pressure Deficit), that were assessed as indicators of drought (water deficit) severity during the vegetation period. Practical implementation of these indices was carried out indirectly by first analyzing yield data using a factor analytic model to detect latent environmental variables affecting yield and then correlating those latent variables with drought indices. Results: The first latent variable, which explained 47.97% of the total variability, was correlated with VPD (r = −0.58); the second latent variable explained 9.57% of the total variability and was correlated with scPDSI (r = −0.74). Furthermore, latent regression coefficients (i.e., genotypic sensitivities to latent environmental variables) were correlated with genotypic drought tolerance. Conclusions: This could be considered an indication that there were two different acting mechanisms in which drought affected yield. Full article

The interaction between atmospheric moisture condensation (AMC) on leaf surfaces and vegetation health is an emerging area of research, particularly relevant for advancing our understanding of water–vegetation dynamics in the contexts of remote sensing and hydrology. AMC, particularly in the form of dew, plays a vital role in both hydrological and ecological processes. The presence of AMC on leaf surfaces serves as an indicator of leaf water potential and overall ecosystem health. However, the large-scale assessment of AMC on leaf surfaces remains limited. To address this gap, we propose a leaf area index (LAI)-derived condensation potential (LCP) index to estimate potential dew yield, thereby supporting more effective land management and resource allocation. Based on psychrometric principles, we apply the nocturnal condensation potential index (NCPI), using dew point depression (ΔT = T_a − T_d) and vapor pressure deficit derived from field meteorological data. Kriging interpolation is used to estimate the spatial and temporal variations in the AMC. For management applications, we develop a management suitability score (MSS) and prioritization (MSP) framework by integrating the NCPI and the LAI. The MSS values are classified into four MSP levels—High, Moderate–High, Moderate, and Low—using the Jenks natural breaks method, with thresholds of 0.15, 0.27, and 0.37. This classification reveals cases where favorable weather conditions coincide with low ecological potential (i.e., low MSS but high MSP), indicating areas that may require active management. Additionally, a pairwise correlation analysis shows that the MSS varies significantly across different LULC types but remains relatively stable across groundwater potential zones. This suggests that the MSS is more responsive to the vegetation and micrometeorological variability inherent in LULC, underscoring its unique value for informed land use management. Overall, this study demonstrates the added value of the LAI-derived AMC modeling for monitoring spatiotemporal micrometeorological and vegetation dynamics. The MSS and MSP framework provides a scalable, data-driven approach to adaptive land use prioritization, offering valuable insights into forest health improvement and ecological water management in the face of climate change. Full article

The Huang-Huai-Hai Plain is one of China’s primary winter wheat production regions, making accurate yield estimation critical for agricultural decision-making and national food security. In this study, a yield estimation framework was developed by integrating Sentinel-2 and Landsat-8 satellite data with the WOFOST crop growth model and deep learning techniques. Initially, a multi-scenario sample dataset was constructed using historical meteorological and agronomic data through the WOFOST model. Leaf Area Index (LAI) values were then derived from Landsat-8 and Sentinel-2 imagery, and a GRU (Gated Recurrent Unit) neural network was trained on the simulation samples to establish a relationship between LAI and yield. This trained model was applied to the remote sensing-derived LAI to generate initial yield estimates. To enhance accuracy, the results were further corrected using county-level statistical data, producing a spatially explicit winter wheat yield dataset for the Huang-Huai-Hai Plain from 2014 to 2022. Validation against statistical yearbook data at the county level demonstrated a correlation coefficient (r) of 0.659, a root mean square error (RMSE) of 578.34 kg/ha, and a mean relative error (MRE) of 6.63%. These results indicate that the dataset provides reliable regional-scale yield estimates, offering valuable support for agricultural planning and policy development. Full article

Drought is a complex and interconnected natural phenomenon, involving multiple drought types that mutually influence each other. To capture this complexity, various composite drought indices have been developed using diverse methodologies. Traditionally, Principal Component Analysis (PCA) has served as the primary method for extracting index weights, predominantly capturing linear relationships among variables. This study proposes an innovative approach by employing Independent Component Analysis (ICA) to develop an ICA-based Composite Drought Index (ICDI), capable of addressing both linear and nonlinear interdependencies. Three drought indices—representing meteorological, hydrological, and agricultural droughts—were integrated. Specifically, the Standardized Precipitation Index (SPI) was adopted as the meteorological drought indicator, whereas the Standardized Reservoir Supply Index (SRSI) was utilized to represent both hydrological (SRSI(H)) and agricultural (SRSI(A)) droughts. The ICDI was derived by extracting optimal weights for each drought index through ICA, leveraging the optimization of non-Gaussianity. Furthermore, constraints (referred to as ICDI-C) were introduced to ensure all index weights were positive and normalized to unity. These constraints prevented negative weight assignments, thereby enhancing the physical interpretability and ensuring that no single drought index disproportionately dominated the composite. To rigorously assess the performance of ICDI, a PCA-based Composite Drought Index (PCDI) was developed for comparative analysis. The evaluation was carried out through three distinct performance metrics: difference, model, and alarm performance. The difference performance, calculated by subtracting composite index values from individual drought indices, indicated that PCDI and ICDI-C outperformed ICDI, exhibiting comparable overall performance. Notably, ICDI-C demonstrated a superior preservation of SRSI(H) values, yielding difference values closest to zero. Model performance metrics (Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and correlation) highlighted ICDI’s comparatively inferior performance, characterized by lower correlations and higher RMSE and MAE. Conversely, PCDI and ICDI-C exhibited similar performance across these metrics, though ICDI-C showed notably higher correlation with SRSI(H). Alarm performance evaluation (False Alarm Ratio (FAR), Probability of Detection (POD), and Accuracy (ACC)) further confirmed ICDI’s weakest reliability, with notably high FAR (up to 0.82), low POD (down to 0.13), and low ACC (down to 0.46). PCDI and ICDI-C demonstrated similar results, although PCDI slightly outperformed ICDI-C as meteorological and agricultural drought indicators, whereas ICDI-C excelled notably in hydrological drought detection (SRSI(H)). The results underscore that ICDI-C is particularly adept at capturing hydrological drought characteristics, rendering it especially valuable for water resource management—a critical consideration given the significance of hydrological indices such as SRSI(H) in reservoir management contexts. However, ICDI and ICDI-C exhibited limitations in accurately capturing meteorological (SPI(6)) and agricultural droughts (SRSI(A)) relative to PCDI. Thus, while the ICA-based composite drought index presents a promising alternative, further refinement and testing are recommended to broaden its applicability across diverse drought conditions and management contexts. 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 performed in-season yield prediction, about 2–3 months before the harvest, for cereals and rapeseed at the province level in Poland for 2009–2024. Various models were employed, including machine learning algorithms and multiple linear regression. The satellite-derived normalized difference vegetation index (NDVI) and climatic water balance (CWB), calculated using meteorological data, were treated as predictors of crop yield. The accuracy of the models was compared to identify the optimal approach. The strongest correlation coefficients with crop yield were observed for the NDVI at the beginning of March, ranging from 0.454 for rapeseed to 0.503 for rye. Depending on the crop, the highest R² values were observed for different prediction models, ranging from 0.654 for rapeseed based on the random forest model to 0.777 for basic cereals based on linear regression. The random forest model was best for rapeseed yield, while for cereal, the best prediction was observed for multiple linear regression or neural network models. For the studied crops, all models had mean absolute errors and root mean squared errors not exceeding 6 dt/ha, which is relatively small because it is under 20% of the mean yield. For the best models, in most cases, relative errors were not higher than 10% of the mean yield. The results proved that linear regression and machine learning models are characterized by similar predictions, likely due to the relatively small sample size (256 observations). Full article

Dry weather can severely limit water availability, harming agriculture and natural habitats. Several drought indices assess meteorological conditions relative to historical norms, but absolute indices, expressed in millimeters of water depth, are particularly crucial for agriculture. Every millimeter of water that a crop cannot evaporate results in an almost proportional yield loss. Using daily precipitation, potential evapotranspiration, and temperature data, we calculated five absolute drought indices for a sandy area in the Netherlands. We then validated these indices against the annual registered amount of irrigation water from 2001 to 2021, which served as a proxy for the drought experienced by farmers. The cumulative potential precipitation deficit calculated with (a) a temperature sum-dependent start of the growing season or (b) a start in the wet winter season most closely matched irrigation amounts (R² = 95% and 94%, respectively). The latter index is likely to be applicable in climates where a dry growing season follows a wet season. These indices can be updated daily, providing real-time insight into drought development and can be used in climate projections. To our knowledge, this is the first study to validate meteorological drought indices using irrigation data, which advances the assessment of drought events. Full article

Agriculture is a vital contributor to global food security but faces escalating threats from environmental fluctuations and pest incursions. Among the most prevalent and destructive pests, Jassid (Amrasca biguttula) and Thrips (Thrips tabaci) frequently afflict cotton, okra, and other major crops, resulting in substantial yield losses worldwide. This paper integrates five machine learning (ML) models to predict pest incidence based on key meteorological attributes, including temperature, relative humidity, wind speed, sunshine hours, and evaporation. Two ensemble strategies, soft voting and stacking, were evaluated to enhance predictive performance. Our findings indicate that a stacking ensemble yields superior results, achieving high multi-class AUC scores (0.985). To demystify the underlying mechanisms of the best-performing ensemble, this study employed SHapley Additive exPlanations (SHAP) to quantify the contributions of individual weather parameters. The SHAP analysis revealed that Standard Meteorological Week, evaporation, and relative humidity consistently exert the strongest influence on pest forecasts. These insights align with biological studies highlighting the role of seasonality and humid conditions in fostering Jassid and Thrips proliferation. Importantly, this explainable approach bolsters the practical utility of AI-based solutions for integrated pest management (IPM), enabling stakeholders—farmers, extension agents, and policymakers—to trust and effectively operationalize data-driven recommendations. Future research will focus on integrating real-time weather data and satellite imagery to further enhance prediction accuracy, as well as incorporating adaptive learning techniques to refine model performance under varying climatic conditions. Full article

Milk yield and its composition show individual variation due to the effects of the environment. Previous studies suggest that meteorological variables exert negative effects on milk yield and composition, especially during summer. This study aimed to examine the effects of meteorological variables on bulk milk composition in the Sardinian sheep production system. In this work, a total of 218,170 records belonging to 4562 dairy sheep farms were merged with the meteorological data provided by 60 meteorological stations located on Sardinia Island (Italy). Milk composition in the late spring and summer recorded during a 5-year period was used to evaluate the impact of climate exposure on bulk milk traits. The milk quality was analyzed using a linear mixed model that included the fixed effects of the year of sampling, the flock size, the temperature humidity index (THI) and the random effect of the flock. The variability of milk composition explained by flock and management ranged from 30 to 64%. The flock size exerted a significant effect on milk composition: large flocks characterized by advanced management and feeding techniques resulted in higher milk quality (e.g., higher protein and fat, lower lactose) compared to traditionally managed small flocks. The impact of THI on milk composition was statistically significant across different milk quality traits (p < 0.001); the effect of thermal stress varied according to the month of lactation. For instance, milk fat content in May increased by +0.4% for THI > 76. In June, no relevant differences were observed, whereas a decrease in fat percentage was observed in July as THI values increased (up to −0.5% for THI > 76). While somatic cell counts remained relatively stable across different conditions, total bacterial count showed greater seasonal variability, peaking during warmer periods. In addition, using factor analysis, we developed a multivariate meteorological index (MMI), which explained 51% of the variance of the original meteorological data. MMI was highly correlated with THI (r = 0.75). The same linear mixed model applied for modeling THI was used to assess the effect of MMI on milk traits. Fat, protein fractions and lactose showed significant variation across MMI classes (p-value < 0.001) in the same direction as those based on THI. Overall, our findings underscore the impact of both flock size and environmental conditions on milk quality, with heat stress and traditional versus modern management practices leading to measurable differences in milk traits. Full article

Weeds remain one of the major limiting factors affecting agricultural production, causin significant yield loss globally. Spot spraying of resistant weeds as an alternative to broadcast applications provides the delivery of chemicals closer to the plant canopy. Also, wind speed can cause spray displacement and can lead to inefficient coverage and environmental contamination. To mitigate this issue, this study sought to evaluate drop nozzles configured to direct the spray closer to the target. A remotely piloted aerial application system was retrofitted with a 60 cm drop nozzle comprising a straight stream and a 30° full cone nozzle. A tracer spray solution was applied on 13 Kromekote cards placed in a grid configuration. The center of deposition for each spray application was determined using the Python (3.11) software. Regardless of nozzle angle, the drop nozzle produced ca. 76% lower spray displacement than the no drop nozzle. The no drop nozzles had a narrower relative span compared to the drop nozzles. This suggests that smaller, more driftable fractions of the spray did not deposit on the targets due to spray displacement. Additional research investigating in-field weed species under various meteorological conditions is required to move this technology forward. Full article

Water scarcity, exacerbated by climate change and increasing agricultural water demands, highlights the necessity for efficient irrigation management. This study focused on estimating actual evapotranspiration (ETa) in watermelons under semi-arid Mediterranean conditions by integrating high-resolution satellite imagery and agro-meteorological data. Field experiments were conducted in Rutigliano, southern Italy, over a 2.80 ha area. ETa was measured with the eddy covariance (EC) technique and predicted using machine learning models. Multispectral reflectance data from Planet SuperDove satellites and local meteorological records were used as predictors. Partial least squares, the generalized linear model and three machine learning algorithms (Random Forest, Elastic Net, and Support Vector Machine) were evaluated. Random Forest yielded the highest predictive accuracy with an average R² of 0.74, RMSE of 0.577 mm, and MBE of 0.03 mm. Model interpretability was performed through permutation importance and SHAP, identifying the near-infrared and red spectral bands, average daily temperature, and relative humidity as key predictors. This integrated approach could provide a scalable, precise method for watermelon ETa estimation, supporting data-driven irrigation management and improving water use efficiency in Mediterranean horticultural systems. Full article

The amount of irrigation needed can be determined using reference evapotranspiration (ETo), the crop coefficient (Kc), and the water deficit index. Reference evapotranspiration is typically calculated utilizing the Penman–Monteith (PM) model, which necessitates various meteorological parameters, including temperature, humidity, net radiation, and wind speed. In regions where meteorological stations are absent, alternative methods must be employed to estimate these parameters. This study employs a combination of estimated meteorological parameters derived from different methodologies to calculate both reference evapotranspiration and irrigation rates, subsequently evaluating the results through wheat irrigation experiments. The daily irrigation rate for the T1 treatment was computed using real-time meteorological data, resulting in the highest grain yield of 561.73 g/m² and an irrigation water use efficiency of 7.61 kg/m³. The irrigation rate for the T2 treatment was determined based on real-time net radiation alongside monthly average values of temperature, humidity, and wind speed. In comparison to T1, the irrigation amount, yield, and irrigation water use efficiency for T2 decreased by 1.59%, 2.96%, and 1.42%, respectively. For the T3 treatment, the irrigation amount was calculated using monthly average values of temperature, humidity, and wind speed, with net radiation derived from daily light duration. The yield for T3 decreased by 19.4% relative to T1, the irrigation amount decreased by 12.95% relative to T1, and the irrigation water use efficiency decreased by 7.45% relative to T1. In the case of the T4 treatment, monthly average values of temperature, humidity, and wind speed were utilized, while net radiation was calculated using the Hargreaves–Samani (HS) model in conjunction with real-time temperature data. The yield for T4 decreased by 8.75% relative to T1, the irrigation amount decreased by 5.58% relative to T1, and the irrigation water use efficiency decreased by 3.39% relative to T1. For the T5 treatment, similar monthly average values were employed, and net radiation was calculated using HS methodology combined with monthly average temperature data. The yield for T5 decreased by 11.96% relative to T1, the irrigation amount decreased by 6.07% relative to T1, and the irrigation water use efficiency decreased by 6.3% relative to T1. Furthermore, the yield for the CK treatment under conventional irrigation decreased by 20.89% compared to T1, while the irrigation amount increased by 1.57% compared to T1 and the irrigation water use coefficient decreased by 22.14% compared to T1. Above all, this article posits that in areas lacking meteorological stations, monthly mean meteorological data should be utilized for parameters such as temperature, humidity, and wind speed, while the HS model is recommended for calculating net radiation. Full article