Irrigation Scheduling Research Articles

Effect of Irrigation Scheduling on Growth, Yield and Irrigation Water use Efficiency of Linseed (Linum usitatissimum L.)

A field experiment was conducted to study the effect of irrigation scheduling on growth, yield and water use efficiency of linseed (Linum usitatissimum L.) at Main Agricultural Research Station (MARS), Raichur, during the rabi season of 2023-24. The experiment was laid out in a randomized complete block design with five treatments, replicated four times. There were five treatments viz., T1: Pre sowing irrigation only, T2: Pre sowing irrigation fb one irrigation at vegetative stage (30-35 DAS), T3: Pre sowing irrigation fb two irrigations at vegetative stage (30-35 DAS) and flowering stage (40-45 DAS), T4: Pre sowing irrigation fb three irrigations at vegetative stage (30-35 DAS), flowering stage (40-45 DAS) and capsule development stage (60-65 DAS) and T5: Rainfed condition. The results revealed that significantly higher plant height (60.94 cm), number of branches plant-1 (6.18), leaf area (36.94 cm2 plant-1), total dry matter production (16.41 g plant-1), number of capsules plant-1 (44.27), number of seeds (8.18 capsule-1), seed weight (2.98 g palnt-1), seed yield (1106 kg ha-1) and straw yield (2344 kg ha-1) was registered with pre-sowing irrigation fb three irrigations at vegetative stage (30-35 DAS), flowering stage (40-45 DAS) and capsule development stage (60-65 DAS) which was found to be on par with pre-sowing irrigation fb two irrigations at vegetative stage (30-35 DAS) and flowering stage (40-45 DAS). Further, (T4) recorded significantly lower water use efficiency (5.26 kg ha-mm-1). Whereas the treatment under rainfed conditions (T5) recorded significantly higher water use efficiency (13.59 kg ha-mm-1) than all other treatments.

Optimizing Irrigation Scheduling to Enhance Nutrient Uptake and Soil Microbial Activity in Linseed Cultivation (Linum usitatissimum L.)

Linseed crop cultivated under residual moisture and water scarcity conditions in rabi season. To improve the productivity of linseed irrigation water is applied at different stages of crop. So, to optimize the irrigation scheduling and enhance the nutrient uptake and soil microbial activity, this experiment was conducted at Main Agriculture Research Station, University of Agricultural Sciences, Raichur (which comes under North Eastern Dry zone of Karnataka) (India) during rabi 2023-24. The experiment was carried out with Randomized Complete Block Design (RCBD) with five treatments and four replications. The results revealed that, pre sowing irrigation fb three irrigations at vegetative stage (30-35 DAS), flowering stage (40-45 DAS) and capsule development stage (60-65 DAS) (T4) recorded significantly higher nutrient uptake by linseed crop (46.07, 19.87 and 39.83 NPK kg ha-1). The rainfed condition treatment (T5) recorded significantly lower nutrient uptake by the crop (19.35, 8.15 and 18.40 NPK kg ha-1). Among the different treatments, pre sowing irrigation fb three irrigations at vegetative stage (30-35 DAS), flowering stage (40-45 DAS) and capsule development stage (60-65 DAS) recorded significantly higher soil microbial population of bacteria (16.1 X 106 cfu g-1 of soil), fungi (13.8 X 104 cfu g-1 of soil) and actinomycetes (6.8 X 103 cfu g-1 of soil) as compared to other treatments. The soil enzymatic activity was significantly influenced by scheduling of irrigation at different growth stages in linseed. At harvest among the different treatments, pre sowing irrigation fb three irrigations at vegetative stage (30-35 DAS), flowering stage (40-45 DAS) and capsule development stage (60-65 DAS) recorded significantly higher dehydrogenase, urease and alkaline phosphatase activity (18.63 μg TPF g-1 soil day-1, 22.5 μg NH4-N g-1 soil hr-1 and 14.4 µg PNP g-1 soil hr-1, respectively).

Reinforcement Learning Algorithm for Optimising Durian Irrigation Systems: Maximising Growth and Water Efficiency

This study presents a Reinforcement Learning-based algorithm designed to optimise irrigation for Durio Zibethinus (i.e., durian) trees, aiming to maximise tree growth and reduce water usage. Traditional irrigation methods, as well as current machine learning models, often focus only on soil moisture and weather data, neglecting critical factors like actual tree growth. This study proposed a reinforcement learning irrigation (RL-Irr) algorithm incorporating tree growth stages, soil moisture, and weather conditions to determine precise irrigation needs. The algorithm was developed by calibrating the AQUACROP model using data from actual durian plantations where rain-fed irrigation (rain-fed) was practised. Daily irrigation volumes were calculated based on real-time soil moisture, weather forecasts, and weekly tree growth measurements. The reinforcement learning method was used to optimise irrigation schedules, with rewards based on soil moisture, tree growth, rainfall, and weather conditions. The algorithm was tested using AQUACROP simulations and compared against soil moisture balance irrigation (SMB-Irr) and rain-fed. The results showed that the RL-Irr reduced water use by up to 75 percent while maintaining tree growth. These findings suggest the algorithm could significantly improve water efficiency in durian farming, though real-world applications should consider potential model limitations.

Comparison of transformer, LSTM and coupled algorithms for soil moisture prediction in shallow-groundwater-level areas with interpretability analysis

Accurate quantification of soil moisture is essential for understanding water and energy exchanges between the atmosphere and the Earth’s surface, as well as for agricultural applications. Predicting soil moisture content is vital for efficient water management, irrigation scheduling, and drought monitoring. Traditional forecasting methods, such as numerical regression models, often struggle due to various influencing factors and poor observation data quality. In contrast, deep learning algorithms, particularly recurrent and convolutional neural networks, show promise in predicting nonlinear data like soil moisture. This study focuses on shallow groundwater regions, using groundwater levels and meteorological data as features while coupling the Transformer model with other neural network structures. We investigate the potential of attention-based neural networks for soil moisture time series prediction. Our findings demonstrate that the Transformer model achieves an average R2 of 0.523 across different time lags, outperforming the LSTM model with an R2 of 0.485. The introduction of LSTM enhances the Transformer’s stability in handling temporal changes. Additionally, we verified the importance of groundwater for soil moisture prediction. This study introduces new methods for soil moisture prediction and offers new insights and recommendations for the development of artificial intelligence technology for soil moisture prediction.

Precision Agriculture using ML for Soil and Weather Prediction

Agriculture is the backbone of many economies and plays a critical role in global food security. However, with growing challenges posed by climate change, erratic weather patterns, and soil degradation, the need for precise and predictive techniques in agriculture has never been more urgent. This paper focuses on the application of machine learning (ML) techniques in soil fertility prediction and weather forecasting, two critical components that can significantly impact agricultural productivity. By analysing soil properties, such as moisture, pH, and nutrient levels, and combining them with accurate weather predictions, our system aims to help farmers make informed decisions regarding crop selection, irrigation scheduling, and pest control. Leveraging algorithms like Naive Bayes for soil classification and Long Short-Term Memory (LSTM) networks for weather prediction, we provide a comprehensive solution for precision agriculture. This system not only enhances productivity but also promotes sustainable agricultural practices by optimizing resource use and reducing wastage

Optimizing wheat supplementary irrigation: Integrating soil stress and crop water stress index for smart scheduling

A two-year field experiment was conducted to integrate soil moisture stress with the Crop Water Stress Index (CWSI) for optimizing irrigation in winter wheat (Triticum aestivum L.) under varying irrigation regimes. The study took place at the Water Technology Centre (WTC-02) of ICAR-IARI, New Delhi, where the climate shows a blend of monsoon-influenced humid subtropical and semi-arid conditions. Using a randomized block design (RBD), five irrigation treatments were applied: full irrigation and deficit irrigation (DI) at 15 %, 30 %, 45 %, and 60 % levels. Canopy and ambient air temperature data, along with vapor pressure deficit (VPD), were recorded using a developed integrated sensing device to empirically determine the lower baseline equations and upper threshold for CWSI computation at pre-heading and post-heading stages. The slope (m), intercept (c) of the lower baseline equation, and upper threshold (UL) for pre-heading and post-heading were found: m: −1.94, c: −1.33, UL: 1.92°C and m: −1.30, c: −2.37, UL: 2.0°C, respectively. Results showed that increasing water deficit levels led to significant reductions in grain yield, biomass production, and harvest index. A strong negative correlation (R² = 0.95 and 0.93) between mean seasonal CWSI and yield attributes highlighted the utility of CWSI in yield prediction under varying irrigation regimes. It is recommended to schedule irrigation based on the CWSI approach when CWSI ≥0.35 for optimum wheat yields. Integrating CWSI with soil moisture stress provides valuable real-time insights into crop water status, enabling more precise and smart irrigation scheduling.

Smart Irrigation System Using Soil Moisture Prediction with Deep CNN for Various Soil Types

Soil moisture sensing plays a crucial role in agriculture as it directly impacts plant growth and can significantly enhance crop productivity. With the advent of technology, agriculture applications have undergone a revolution, enabling more advanced and efficient practices. One such advancement is the use of soil moisture sensors, which provide valuable information about the current water level of the soil, including whether it is dry, wet, or excessively saturated. These sensors have become indispensable tools for farmers and growers, empowering them to make informed decisions regarding irrigation schedules, water management strategies, and overall crop health. By accurately assessing soil moisture levels, farmers can optimize water usage, prevent water stress or overwatering, and promote healthier plant development, ultimately leading to improved yields and sustainability in agriculture. The objective of the proposed study is to investigate the effective soil moisture sensors by considering three sensors and an automated system for watering the soil for agriculture. A comparative analysis is performed for different commercial off-the-shelf soil moisture sensors in cost, accuracy, durability, and corrosion resistance. Secondly, this study further gives soil moisture reading as data input to the Convolutional Neural Network (CNN) to classify whether water is required or not for the soil at a particular temperature which would help to conserve water and develop agriculture. An automated system which can help the farmer for irrigation and cultivation of the soil obtained accuracy as 95.23%.

Determination of Optimal Soil Moisture Depletion Levels for Sweet Basil (Ocimum basilicum L.) at Wondo Genet, Ethiopia

Determining allowable soil moisture depletion level is critical for determining proper irrigation scheduling. The study was conducted at Wondo Genet Agricultural Research Center, Ethiopia, latitude 8°25'59'', longitude 39°01'44''and altitude of 1800 m.a.s.l to determine optimal soil moisture depletion level for sweet basil (Ocimum basilicum L.). Six levels of soil moisture depletion (20, 30, 40, 50, 60 and 100% of total available water (TAW) of the soil), with three replication were used as treatments to evaluate the yield and yield component of sweet basil in randomized complete block design. Different levels of soil moisture depletion levels significantly affected all recorded yield and yield components of sweet basil including its water productivity. Significantly higher yield and yield components were associated with frequently irrigated treatment under lower soil moisture depletion levels before irrigation. However, when sweet basil was irrigated beyond 40% TAW lowest yield and yield components were recorded. Therefore, sweet basil could be irrigated when the soil moisture content is depleted by 40% of the total available water content in the soil to enhance yield and water use efficiency in the study area and similar agro ecologies.

Response of Mungbean (Vigna radiata L. Wilczek) to Rhizobium inoculation and Irrigation Schedule in Siraha, Nepal

Mungbean (Vigna radiata L.) productivity in Nepal is indeed lower compared to its potential yield due to inadequate nutrient management and soil moisture depletion. Use of effective plant growth promoting bacteria and proper irrigation scheduling in mungbean can enhance its production and productivity. To study the response of Rhizobium inoculation and irrigation schedule on growth and yield of mungbean, a field experiment was conducted in a split-plot field layout at a farmers' field in Dhangadimai Municipality, Siraha, Nepal from March 2023 to June 2023. The treatments consisted of four levels of irrigation (i.e. Rainfed, Irrigation at vegetative stage (V), irrigation at reproductive stage (R) and irrigation at both (V and R) in main plots and two levels of biofertilizer (with and without Rhizobium inoculation) in sub plots which was replicated three times. Plant height, leaf numbers, number of effective branches, pod length, and grain per pod were recorded highest in mungbean inoculated with rhizobium, and irrigation at both V and R stages. The highest grain yield (1.81 Mtha-1) was obtained from the treatment having irrigation at both V and R stages, followed by irrigation scheduled at R (1.56 Mtha-1), V (1.47 Mtha-1), and rainfed condition (1.34 Mtha-1). The grain yield was higher in inoculated (1.58 Mtha-1) than in non-inoculated mungbean (1.50 Mtha-1). Rhizobium inoculated crops irrigated during V stage only, irrigated during R stage only and irrigated at both V and R stages increased grain yield by 6.32%, 5% and 17% respectively as compared to rainfed conditions. Number of effective nodules per plant was 79 % higher in inoculated (15.72) than in non-inoculated plots (4). The best combination was found in the treatment where irrigation was applied in both V and R stages with Rhizobium inoculation. Thus, application of rhizobium inoculation and irrigation at V and R stages showed a positive response to growth parameters, yield attributing characters, and yield.

Drought tolerance and recovery capacity of two ornamental shrubs: Combining physiological and biochemical analyses with online leaf water status monitoring for the application in urban settings

When plants are transferred from nursery to urban environments, they often face drought stress due to inadequate maintenance, such as insufficient irrigation. Using drought tolerant species may help mitigate the adverse impact of drought stress in urban settings. Additionally, utilizing novel technologies for water status monitoring may help optimize irrigation schedules to prevent transplanting failures. This study investigated the physiological and biochemical responses of two ornamental shrubs, Photinia x fraseri and Viburnum tinus, subjected to water stress of increasing severity and rewatering. Water relations, gas exchanges, chlorophyll fluorescence and biochemical analyses were conducted alongside real-time monitoring of water status using leaf-water-meter sensors (LWM).The progression of water stress had a notable negative impact on leaf gas exchanges and water relations in both species. Notably, P. fraseri avoided photoinhibition by reducing chlorophyll content and actual efficiency of PSII. Adjustments in leaf phenolic compounds played a significant role in enhancing drought tolerance of both species due to their antioxidant and photoprotective properties.Upon rewatering, both species exhibited complete recovery in their physiological functions, underscoring their remarkable tolerance and resilience to drought stress. Additionally, LWM sensors efficiently tracked the dehydration levels, exhibiting a rising trend during the water stress progression and a subsequent decline after rewatering for both species. These findings confirm the reliability of LWM sensors in monitoring physiological status of plants in outdoor contexts, making them a suitable tool for use in urban settings.

Water volumes and mulches affect plant growth, leaf nutrient status and orchard soil mineral content of sweet orange cv. Mosambi

Day-by-day increasing irrigation water scarcity requires the application of water-saving irrigation techniques to sustain agriculture production. A two-year field investigation was conducted during 2018 to 2020 to determine the effects of various mulches and irrigation volumes on the growth, leaf chemicals and soil properties of one-year-old sweet oranges (Citrus sinensis) cv. Mosambi. The study included three irrigation schedules, viz.100% ETc (I1), 80% ETc (I2), and 60% ETc (I3), and five different mulches were used, viz. without mulch, white polythene, coriander straw, dry grass and black polythene mulches, replicated thrice. Results demonstrated that drip irrigation with 100% ETc and mulching with black polythene mulch significantly increase the plant growth attributes like height of the plant (28.64%) (30.31%), rootstock girth (36.61%) (37.90%), plant canopy spread (E-W and N-S) (EW- 63.82%, NS- 63.87%) (EW- 67.56%, NS- 67.90%) and leaf area (2.4%) (2.34%). Furthermore, plant leaf chlorophyll content (2.41 mg g-1) (2.41 mg g-1) and leaf mineral content such as N (2.39%) (2.40%), P (0.16%) (0.165%), K (1.57%) (1.59%), Ca (47.34 g kg-1) (47.80 g kg-1), Mg (4.54 g kg-1) (4.57 g kg-1), Fe (120.51 g kg-1) (123.15 g kg-1) and Zn (39.00 g kg-1) (37.84 g kg-1) were noted to be significantly (p ≤ 0.05) higher in plants that received 100% (were ETc (I1) and mulching with black polythene mulch (M1) treatment. Taken together, the results suggested that treatments I1 and M1 have the potential to maximize plant growth, leaf chemicals and soil nutrients of sweet orange (Citrus sinensis) cv. Mosambi plants.

Bibliometric Analysis of Root Research under Drip Irrigation Based on Web of Science

The study delves into the prevailing focal points and developmental trends within the international sphere of crop root research under drip irrigation. It leverages the Web of Science core database and employs VOSviewer for a systematic review of the literature spanning 2001 to 2022. The analysis encompasses publication counts, publishing journals, contributing authors, research institutions, and keywords. Findings indicate that research on root systems under drip irrigation has become a notable area of interest in the field of irrigation, attracting global scholarly attention. There is a marked upward trend in publication output, with institutions in China and the United States taking on central roles. Journals like Agricultural Water Management and Acta Horticulturae are key publication venues, with Vadose Zone Journal being notable for high-impact articles. The research primarily involves agronomy, water resources, and horticulture, focusing on yield enhancement through drip irrigation, root distribution under various techniques, crop quality in response to partial root-zone drying, and irrigation scheduling model development. Scholars like Jiri Simunek and Yaohu Kang have made substantial contributions. The field’s established framework calls for continued international collaboration to drive further innovation. The identified trends and parameters can be a valuable reference for researchers, policymakers, and practitioners, guiding efforts to optimize agricultural productivity and resource use.

Impact of Stage-Specific Irrigation on the Growth and Yield of Wheat

Stage-specific irrigation is essential for ensuring optimal water use at critical growth stages in wheat (Triticum aestivum), leading to increased yield and improved grain quality. Therefore, determining an appropriate irrigation schedule for wheat is crucial for enhancing productivity. Keeping this view in mind, an experiment was conducted at the farmer’s fields of Dinajpur Sadar Upazila, Dinajpur, Bangladesh from November 2020 to April 2021, aimed to evaluate the impact of irrigation schedules on the growth and yield of wheat (BARI Gom-33). A randomized complete block design (RCBD) with seven treatments and three replications was implemented. Treatments included varying irrigation timings: T0 (no irrigation), T1 (one irrigation at maximum tillering), T2 (one irrigation at booting), T3 (one irrigation at heading), T4 (two irrigations at maximum tillering and heading), T5 (milking dough), and T6(two irrigations at booting and milking dough). Key metrics assessed included plant height, leaf count, tiller number, dry matter, growth stages, grain number, thousand grain weight, and overall yield at different days’ intervals. Results indicated that irrigated treatments (T1-T6) significantly improved the parameters for growth and yield compared to the control (T0). Notably, T4, with two irrigations, yielded the highest grain production at 5.20 t/ha, followed closely by T6. These findings highlight the significance of proper irrigation scheduling for optimizing wheat yield, indicating that applying two irrigations at the maximum tillering and heading stages can significantly enhance agricultural productivity.

Effect of Irrigation and Nitrogen Application at Early Tillering, Panicle Initiation and Flowering Stages on the Yield and Yield Attributes of Boro Rice

The study aimed to evaluate the impact of irrigation scheduling and nitrogen splitting on the yield and yield attributes of boro rice, with particular emphasis on critical growth stages including early tillering, panicle initiation and flowering stages. The experiment was executed at the Agronomy Field Laboratory of the Department of Agronomy and Agricultural Extension, University of Rajshahi, from December 2022 to May 2023. The experiment setup was demonstrated using a split plot design, incorporating three replications. Two factors were determined for the experiment: the first included three different watering schedules aiming critical growth stages: early tillering (I1), early tillering and flowering (I2), and early tillering, panicle initiation and flowering panicle initiation (I3). The second factor was distinct nitrogen splitting techniques, which consisted of four levels: control (N0), 138 kg N ha-1 as basal (N1), 69 kg N ha-1 at early tillering and flowering stages (N2), and 46 kg N ha-1 at early tillering, panicle initiation and flowering stages (N3). The highest reading of chlorophyll content was noticed in I3 along with productive tillers (15.67), grains (115.25) and yield outcome (4.44 t ha-1). Regarding nitrogen application, the greatest chlorophyll content, number of functional tillers (13.32), productive grains (112.44) panicle-1 and grain yield (4.48 t ha-1) was recorded in treatment N3. Therefore, the research finding suggest that the application of water at early tillering, panicle initiation and flowering stages along with the application of 46 kg N ha-1 will be helpful to maximize the production of rice in drought prone areas. This approach not only maximizes yield but also helps to mitigate water wastages associated with excessive irrigation.

Comparative analysis of advanced deep learning models for predicting evapotranspiration based on meteorological data in bangladesh.

Evapotranspiration is one of the crucial elements in water balance equations and plays a pivotal role in the water and energy cycle of an area. An accurate and precise estimation and prediction of reference evapotranspiration (ETo) is necessary for regional management of water resources and irrigation scheduling. The challenge of predicting daily evapotranspiration with limited meteorological data in Bangladesh. This study aims to predict daily evapotranspiration using limited meteorological data of Bangladesh by three deep learning (CNN, GRU, LSTM) and one hybrid (CNN-GRU) model. The novel method of hybrid CNN-GRU models, which have not been commonly used for this purpose. The performance of models was evaluated by five accuracy matrices R2, RMSE, MAE, MAPE, and CE and comparison is visualized by radar graphs. The study's novelty lies in the use of hybrid CNN-GRU models to estimate reference evapotranspiration, as this algorithm has not been commonly used for this purpose. In the case of the Rangpur station, the hybrid CNN-GRU algorithm outperformed other models, achieving the best values across various statistical metrics during both the training and testing phases. The highest correlation coefficient values of approximately 0.994 and 0.995. Moreover, during training and testing stages, the hybrid model had the lowest MAE (0.076, 0.068) and RMSE (0.138, 0.106) at the Rangpur station. Additionally, in the Sreemangal station, it can be notable that the statistical parameter RSME found superior results in the hybrid model around 0.225 and 0.174, respectively. In addition, the highest R2 and CE values were noted as 0.986, 0.987 and 0.985, 0.986 during the training and testing phases, respectively. The comparison suggests that the hybrid model will be best suited for prediction with the limited meteorological data. The outcome of the present research signifies the ability of deep learning methods in the prediction of evapotranspiration and the dominant variables affecting the changes the in context of Bangladesh.

Optimization of irrigation scheduling using crop–water simulation, water pricing, and quantitative weather forecasts

Optimization of irrigation scheduling using crop–water simulation, water pricing, and quantitative weather forecasts

Optimizing yield and irrigation water productivity of wheat under Sahel conditions in North East Nigeria

Unsustainable irrigation practices are a major threat to the available water resources and food security of the country. This research was conducted to determine the optimal wheat grain yield and water productivity (WP) under limited irrigation practices for the enhanced livelihood of small farmer holdings in the Sahel region of northeast, Nigeria. The research was carried out in randomized complete block design (RCBD) with split plot arrangement and replicated three times. The main plot treatment was 7 (I1), 10 (I2), and 14(I3) days irrigation intervals, while the subplot factor was 100 (V1), 85 (V2), and 70% (V3), of crop water requirement (ETc) replacement. The cropWat model was used to determine the crop water requirement (ETc) of the wheat (var. Norman) used in the research. The findings indicated that a 7-day irrigation interval increased grain yield by 20.18 over a 10-day irrigation interval and by 63.10% over 14-day irrigation intervals. Grain yield was found to decrease by 44.80 and 747.25kgHa-1 respectively for 85 and 70% ETc replacement irrigations from full ETc replacement irrigation. Crop water use efficiency was higher and better (0.74 mm-kg/ha) with I1V2 irrigation treatment for wheat and saved 11.55.50 m3 irrigation water over other irrigation schedules. It is recommended that 7 7-day irrigation interval be maintained, while irrigation depth can be reduced by up to 15% for optimum water productivity.

ReLU surrogates in mixed-integer MPC for irrigation scheduling

Efficient water management in agriculture is important for mitigating the growing freshwater scarcity crisis. Mixed-integer Model Predictive Control (MPC) has emerged as an effective approach for addressing the complex scheduling problems in agricultural irrigation. However, the computational complexity of mixed-integer MPC still poses a significant challenge, particularly in large-scale applications. This study proposes an approach to enhance the computational efficiency of mixed-integer MPC-based irrigation schedulers by employing Rectified Linear Unit (ReLU) surrogate models to describe the soil moisture dynamics of the agricultural field. By leveraging the mixed-integer linear representation of the ReLU operator, the proposed approach transforms the mixed-integer MPC-based scheduler with a quadratic cost function into a mixed-integer quadratic program, which is the simplest class of mixed-integer nonlinear programming problems that can be efficiently solved using global optimization solvers. The effectiveness of this approach is demonstrated through comparative studies conducted on a large-scale agricultural field across two growing seasons, involving other machine learning surrogate models, specifically Long Short-Term Memory (LSTM) networks, and the triggered irrigation scheduling method. The ReLU-based approach significantly reduces solution times—by up to 99.5%—while achieving comparable performance to the LSTM approach in terms of water savings and Irrigation Water Use Efficiency (IWUE). Moreover, the ReLU-based approach achieves enhanced performance in terms of irrigation water savings and IWUE compared to the triggered approach.

Innovative Multi-Temporal Evapotranspiration Forecasting Using Empirical Fourier Decomposition and Bidirectional Long Short-Term Memory

Reference evapotranspiration (ETo) is an essential environmental variable that is intimately significant to agriculture. Managing water and crop planning relies heavily on precise forecasting of ETo. This research used a novel time series decomposition technique, Empirical Fourier Decomposition (EFD), to forecast ETo accurately. Four machine learning techniques were used to forecast ETo using decomposed lagged ETo values. The input data source was from Prince Edward Island (PEI) weather stations (Harrington and St Peters Stations). First, autocorrelation analysis was performed to determine effective lags. Then, ETo data were decomposed using EFD, and lagged data was created based on EFD results. The Kbest feature selection algorithm was used to choose effective inputs, reducing the training time. The accuracy of models was evaluated using different statistical metrics such as correlation coefficient (R) and root mean square error (RMSE). The results showed that using EFD decomposition can significantly improve forecast accuracy. The comparison between different machine learning models showed that the deep learning-based model (Bidirectional LSTM (Long Short Term Memory)) (R=0.956, RMSE= 0.451 mm/day for Harrington station and R=0.956, RMSE= 0.451 mm/day for St Peters station) performed better than the Generalized Regression Neural Network (GRNN), K-nearest neighbor (KNN), and Random Forest (RF) models. Finally, the best model (EFD-Bidirectional LSTM) was used to forecast multitemporal ETo at both stations. Results showed that the developed model can forecast ETo for up to 28 days with reasonable accuracy. However, the accuracy of multi-step ahead forecasting decreases when evapotranspiration values are high, as the models tend to underestimate these values. The findings of this study can assist in accurately calculating crop water requirements and help farmers optimize their irrigation schedules.

Capillary rise quantification improves irrigation performance in pear orchards

The shallow water table in Río Negro and Neuquén valley causes a capillary rise (CR) that modifies the water content in soil profile. Therefore, irrigation performance is expected to be affected by the capillary water input into the root zone. The aim of this study was to evaluate the effect of CR on surface irrigation performance during 2020-2021 growing season in a pear orchard. In a Bartlett pear orchard planted in 2003, three irrigation moments were evaluated, and irrigation sheets were calculated to obtain efficiency. Water table level (WTL) was measured monthly in an open aquifer piezometer. CR was calculated with the software UPFLOW. Soil water content was measured with a Frequency Domain Reflectometry (FDR) sensor at: 0.20 m, 0.40 m, and 0.60 m. Water use efficiency (WUE) and water productivity were calculated using pear crop yield and the irrigation sheets applied and the crop water demand, respectively. WTL was shallower in spring than in the rest of the season. The mean depth fluctuated between 0.70-1.20 m during spring, affecting irrigation performance. Data of FDR deepest sensor showed an increase of soil moisture due to CR. Capillary contribution negatively affects irrigation efficiency if it is not included in the water balance. Irrigation schedules can be re-arranged considering soil moisture and CR. In this way, the necessary water sheets could be applied in each crop development stage adjusted to water demand. Improving irrigation performance and WUE enables a sustainable water management strategy in pear production.