Irrigation and Drainage最新文献

Essentially, drainage systems (DSs) frequently suffer from blockages, thus resulting in costly maintenance. Therefore, various studies have focused on detecting blockages arising in DSs; however, this has been difficult during pandemic situations. Therefore, this article aims to implement a fully automated system for real-time blockage removal in DSs via a hybrid fuzzy deep learning approach. The sensor data are primarily gathered. During preprocessing, noise removal is performed via Spearman's rank correlation coefficient applied via the pairwise attribute noise detection algorithm (SRCC-PANDA). Thereafter, the proposed two-sided Gaussian-fuzzy C-means clustering (TSG-FCMC) is established to group the data into three different classes. If the data are clustered into a blockage class, then the manhole status is determined via the rule-based decision controller (RBDC). Afterward, to locate the blockage, the unmanned autonomous surface vehicle (UASV) is used. Additionally, the proposed APTx activated-active-learned-recurrent neural network (AAL-RNN) significantly categorizes the types of blockages. Thus, the proposed approach achieved a noticeable accuracy, precision and recall of 97.7%, 98.1% and 97.3%, respectively. Hence, the outcome showed that the proposed technique outperformed conventional methods with effective performance measures. The proposed work is highly recommended for large-scale deployment, thus enhancing public health safety.

The unclear hydraulic performance of aeration pipelines is an important factor restricting their further application in agricultural fields. Methods for predicting changes in the flow of aeration pipelines often rely on empirical models and often lack high precision. In this paper, a new method was proposed to predict the flow rate of a non-discharge pipeline along an air-filled path via the CatBoost machine learning algorithm. A total of 3600 sets of flow data were collected and randomly divided into 7:3 ratios for training and testing using the PLC-based water–gas automation system. The grid search method was used for multiple cross-validations and empirical calculations, and parameters such as n estimators, tree depth and learning rate were optimized. A prediction model was then built using these optimal parameters. The results revealed that the mean absolute error (MAE) and root mean square error (RMSE) of the CatBoost model were 86 and 71, respectively. This research provides a foundation for optimizing aeration irrigation systems, enabling precise flow control that can achieve 5%–10% water savings while maintaining crop productivity. The developed model can be integrated into automated irrigation management systems to support sustainable agricultural practices.

The unclear hydraulic performance of aeration pipelines is an important factor restricting their further application in agricultural fields. Methods for predicting changes in the flow of aeration pipelines often rely on empirical models and often lack high precision. In this paper, a new method was proposed to predict the flow rate of a non-discharge pipeline along an air-filled path via the CatBoost machine learning algorithm. A total of 3600 sets of flow data were collected and randomly divided into 7:3 ratios for training and testing using the PLC-based water–gas automation system. The grid search method was used for multiple cross-validations and empirical calculations, and parameters such as n estimators, tree depth and learning rate were optimized. A prediction model was then built using these optimal parameters. The results revealed that the mean absolute error (MAE) and root mean square error (RMSE) of the CatBoost model were 86 and 71, respectively. This research provides a foundation for optimizing aeration irrigation systems, enabling precise flow control that can achieve 5%–10% water savings while maintaining crop productivity. The developed model can be integrated into automated irrigation management systems to support sustainable agricultural practices.

The leaf area index (LAI) is a vital parameter in crop eco-physiology because it substantially influences key processes such as evapotranspiration, light interception, photosynthesis and ultimately seed yield. Together with plant height, the LAI serves as a crucial indicator of crop growth and yield potential. Understanding the dynamic variations in LAI and developing reliable predictive models are essential for advancing research and improving agricultural practices. In this study, we employed a simple, experimentally validated logistic model driven by growing degree days (GDDs) to predict the LAI of fodder maize cultivated under both pulse and continuous irrigation regimes in the dry and semiarid regions of Varamin, Iran. Additionally, we propose a novel logistic equation that permits LAI estimation across different irrigation treatments (60%, 80% and 100% water requirements) independent of GDD and plant height. Evaluations via the R², RMSE and NSE indices demonstrated high accuracy in LAI estimation throughout the entire growth period, with the logistic model consistently outperforming the Gaussian model. Our results highlight the usefulness of LAI modelling for monitoring crop development and devising effective management strategies while emphasizing the importance of integrating advanced modelling techniques into agricultural management, especially in water-scarce regions. These findings offer promising insights.

The AquaCrop model is crucial for assessing innovative irrigation strategies to increase water productivity, yet its reliability over multiple seasons in semi-arid Ethiopia is underexplored. Field experiments were conducted in 2020/21 and 2021/22 with four irrigation treatments, that is, 100%, 80%, 60% and 40% ETc, to evaluate the model's performance in simulating maize growth, yield, evapotranspiration and water productivity. The 2020/21 data were used for calibration, and the 2021/22 data were used for validation. The results indicated that the model underestimated canopy cover (NRMSE < 25%) but accurately simulated biomass (NRMSE < 10%). Very good simulations were achieved for grain yield and water productivity (NRMSE < 10 tons ha⁻¹, NSE > 0.75), whereas crop evapotranspiration was underestimated (NRMSE < 15%). The model was more reliable for the 100% and 80% ETc treatments than for the 60% and 40% ETc treatments. The 60% ETc treatment yielded an optimal value of 6.1–7.0 tons ha⁻¹, with a water productivity ranging from 2.4 to 2.5 kg m⁻³. These findings demonstrate that AquaCrop can effectively predict maize growth and yield, with 60% ETc as the optimal irrigation level for water-scarce regions such as Arba Minch.

Efficient irrigation strategies are essential for optimizing water use in cassava production. This study evaluated the water footprint of cassava under five irrigation regimes—drip irrigation at 100%, 80% and 60% of crop evapotranspiration (ETc), furrow irrigation, and rainfed conditions—using field data from 2008 to 2012 validated with 2021–2023 data from humid tropical India. The crop ETc showed a decreasing trend, peaking at 378.8 mm in 2008–2009 and reaching its lowest value (307.6 mm) in 2021–2022. Drip irrigation at 100% ETc significantly reduced water use and blue water dependency compared to furrow irrigation, which exhibited high inefficiencies due to surface evaporation and runoff. The blue water usage under furrow irrigation (7200 m³ in 2021–2023) was reduced to 2065 m³ with drip irrigation. This efficiency resulted in higher cassava yields, with drip irrigation at 100% ETc achieving the highest yields (45.5 ± 7.3 t ha⁻¹ in 2008–2012 and 46.7 ± 3.5 t ha⁻¹ in 2021–2023), surpassing furrow (~26%–27% lower) and rainfed (~59% lower) conditions. Drip irrigation also led to the lowest total water footprint (80.9 ± 7.0 m³ t⁻¹), representing a 65% reduction compared with furrow irrigation and a 28% reduction compared with rainfed conditions (112.2 m³ t⁻¹). These findings provide crucial insights for sustainable cassava intensification.

Increasing water scarcity and nutrient demand requires efficient irrigation and nutrient management for sustaining the productivity of the basmati rice–wheat cropping system. This study assessed the impacts of two irrigation methods (surface [DI] and subsurface drip irrigation [SDI]), four irrigation schedules (I_15%, I_25%, I_35% and I_45%, i.e., 15%, 25%, 35% and 45% depletion of available water) and two nitrogen doses (100% and 75% of the recommended dose), in comparison with the control (flood irrigation with a 100% recommended dose of nitrogen). Compared with the control, the SDI N₁₀₀ I_15%, SDI N₁₀₀ I_25%, DI N₁₀₀ I_15% and DI N₁₀₀ I_25% achieved statistically comparable grain yield and yield attributes, with higher water productivity by 10%, 12%, 6% and 9% (pooled from 2021 to 2022 and 2022 to 2023) and irrigation water savings of 185, 255, 145 and 220 mm, respectively, in wheat and basmati rice from 2021 to 2022 and 225, 300, 175 and 265 mm, respectively, in wheat and basmati rice from 2022 to 2023. Furthermore, the highest economic water productivity was recorded in the SDI N₁₀₀ I_15% treatment (17.03 INR m⁻³ pooled) over the control (16.61 INR m⁻³ pooled) in the basmati rice–heat system. These findings highlight the potential of precision irrigation strategies in enhancing water productivity without compromising yield in the basmati rice–wheat system.

The study objectives were to determine the effects of raw leachate (LR), leachate treated with filter 1 (LT F1), leachate treated with filter 2 (LT F2), leachate treated with UV (LT UV) and a control group using well water on the physiology and growth of basil and alfalfa plants. The effects on germination rates, plant height, leaf area, biomass, stomatal conductance, relative water content, total chlorophyll content, soluble sugars, proline content and mineral element contents were studied. The raw leachate had a detrimental effect on the germination of both basil and alfalfa (no seeds germinated). In contrast, irrigation with LT UV and well water resulted in high germination rates (approximately 100%). Compared with LT F1, LT F2 had positive effects on plant height and biomass. Stomatal conductance was highest in plants subjected to LT UV, with a reduced water content in plants subjected to LT F1 and LT F2. The total chlorophyll content was high in plants irrigated with LT UV and well water. Mineral elemental analysis revealed increased concentrations of nitrogen, potassium and calcium in the aerial parts of the plants; the plants were irrigated with treated leachates and sodium accumulated in the roots. Compared with untreated raw leachate, treated leachate with LT UV enhanced the growth and physiological performance of basil and alfalfa.