Irrigation Scheduling Research Articles

Estimation of crop coefficient for radish using digital lysimeter under polyhouse

Accurate quantification of crop water requirements of any crop is essential for irrigation scheduling and water management. The objective of this study was to estimate the crop coefficient of radish for different phenological stages under protected cultivation using digital lysimeter. The experiment was carried in the Agricultural Engineering College and Research Institute, Kumulur, Trichy. The experiment layout has been made to accommodate the three treatments (T1 - 120 % of ETc, T2 - 100 % of ETc and T3- 80 % of ETc) and four replications in drip irrigated polyhouse. The actual crop evapotranspiration (mm day-1) measured from digital lysimeter and ETo is the reference evapotranspiration (mm day-1) measured from Hargreaves model. The crop coefficient value of radish grown under protected cultivation during initial stage (Kcin), development stage (Kcdev), mid-stage (Kcmid) and final stage (Kcfin) for T1 was 0.72, 0.99, 1.01 and 0.81, T2 was 0.58, 0.84, 0.85 and 0.63 and T3 was 0.43, 0.61, 0.62 and 0.48 respectively. The study demonstrated that supplying additional water had no significant effect in radish yield under polyhouse. The crop coefficient (Kc) value obtained for treatment 100 % of ETc is suggested for optimal use of irrigation water for cultivating of radish crop in naturally ventilated greenhouse.

Textural Analysis and GIS Mapping of Agricultural Soil Samples from the Karha River Basin, Pune District, Maharashtra, India

Understanding soil texture is vital for sustainable agriculture, as it directly affects water retention, nutrient dynamics, and root development. This study aims to assess and map the spatial variability of agricultural soil texture in the Lower Karha River Basin using granulometric analysis and GIS techniques. A total of 48 soil samples were collected using a 10×10 fishnet grid overlay and analyzed using mechanical sieving method for proportion of granule (0.49%–50.42%), sand (25.24%–64.40%), and silt-clay (21.91%–49.94%) fractions. The soils are predominantly sand-rich, with localized zones of finer textures in the southern and lower basin areas. Grain-size statistical parameters were computed to evaluate sedimentological behavior. Mean grain size ranged from –0.73 to 2.20 ϕ, indicating a spectrum from coarse to fine textures. Sorting indices varied between 1.45 ϕ and 2.75 ϕ, classifying most soils as moderately to poorly sorted. Skewness (–0.23 ϕ to 0.83 ϕ) and kurtosis (0.55 ϕ to 1.76 ϕ) values showed diverse asymmetry and peakedness, reflecting heterogeneous depositional environments across the basin. Spatial distribution maps were generated using Inverse Distance Weighting (IDW) in a GIS environment, enabling high-resolution visualization of texture classes and statistical patterns. The results offer critical insights for precision agriculture, informing crop suitability, irrigation scheduling, and localized land-use planning. The study underscores the significance of integrating geostatistical tools with soil texture analysis for effective soil resource management in semi-arid river basins.

Influence of Organic Manure and Hydrogel-based Irrigation Scheduling on Brown Mustard (Brassica juncea L.)

Background: With the increase in population and number of industries in Sikkim, water scarcity is increasing day by day. Thus, water availability for agriculture purpose is a serious concern for the state, whose State’s Gross Domestic Product (SGDP) depends up on agriculture. Therefore, a study was formulated with the possibility to mitigate the vulnerability of brown mustard towards water stress. Methods: The experiment was laid out as pot experiment in the rabi season, 2021-2022 under a CRD setup with 13 treatments replicated thrice. Pot capacity was measured and one seedling was planted per pot. Before planting, hydrogel was applied at recommended doses i.e., 40 g/pot and 20 g/pot. Result: The investigation concluded that the treatment T5 (Vermicompost @ 250 g/pot + Irrigation water @ 100% pot capacity + Hydrogel @ 20 g/pot) was found superior in terms of growth and yield parameters. Vermicompost combined with hydrogel effectively enhanced growth and yield parameters under water stress condition in brown mustard, leading to increased yield. Therefore, treatment T5 can be further scaled up as a standard practice for brown mustard.

Comprehensive Assessment of PeriodiCT Model for Canopy Temperature Forecasting

Canopy temperature is an important indicator of plants’ water status. The so-called PeriodiCT model was developed to forecast canopy temperature using ambient weather variables, providing a powerful tool for planning crop irrigation scheduling. As this model requires observed data in its parameter training before implementing the forecast, it is important to understand the data requirements in the model training such that accurate forecasts are attained. In this work, we conduct a comprehensive assessment of the PeriodiCT model in terms of sample size requirement and predictabilities across sensors in a field and across seasons for the full model and sub-models. The results show that (1) 5 days’ observations are sufficient for the full model and sub-models to achieve very high predictability, with a minimum coefficient of efficiency of 0.844 for the full model and 0.840 for the sub-model using only air temperature. The predictability decreases in the following order: full model, sub-model without radiation S, with air temperature Ta and vapor pressure VP, and with only Ta. The predictions perform reasonably well even when only one day’s observations are used. (2) The predictability into the future is very stable as the prediction steps increase. (3) The predictabilities of the full and sub-models when using a trained model from one sensor for another sensor perform comparatively well, with a minimum coefficient of efficiency of 0.719 for the full model and 0.635 for the sub-model using only air temperature. (4) The predictabilities of the sub-models without solar radiation when using trained models from one season for another season perform comparatively well, with a minimum coefficient of efficiency of 0.866 for the full model and 0.764 for the sub-model using only air temperature, although the cross-season performances are not as good as the cross-sensor performances. The importance of the predictors is in the order of air temperature, vapor pressure, wind speed, and solar radiation, while vapor pressure and wind speed have similar contributions, and solar radiation has only a marginal contribution.

Enhancing Soil Characteristics and Physiological Parameters of Soil Cultivated with Marigold (Tagetes erecta L.) cv. Calcutta Orange Using Pusa Hydrogel

The issue of water management has assumed paramount importance and occupied the centre stage of politico-economic debates in the world. Marigold is a versatile flowering plant that belongs to the Asteraceae family with numerous uses in the floriculture industry, which can be grown in varied agroclimatic conditions, hence used for the present study. The study aimed to understand the effect of different regimes of irrigation, soil characteristics and physiological parameters of soil during the cultivation of Marigold (Tagetes erecta L.) cv. Calcutta orange. The study was conducted at the College of Horticulture, Bagalkot, University of Horticultural Sciences, Bagalkot, Karnataka, India. Healthy seedlings of the marigold cultivar “Culcutta Orange” were used for the experiment, collected from Kisan Nursery, Arabhavi. The recorded observations included soil parameters, physiological parameters, Crop growth rate, Relative Growth Rate, and Net Assimilation Rate. The results revealed significantly higher moisture content in marigold grown field soil irrigated with 100 per cent Cumulative Pan Evaporation (CPE) (20.72, 17.50 and 12.24 per cent, respectively) at 30, 60 and 90 Days After Transplanting (DAT). High pH (8.03) and bulk density (1.48 g/cm3) were observed at 80 (I2) and 60 (I3) per cent CPE, respectively. Relative water content was significantly highest in I2: 80 per cent CPE (75.51 and 63.75 per cent, respectively) at 45 and 75 DAT. Maximum values of Crop Growth Rate (CGR) (1.79 g m-2 day-1), Relative Growth Rate (RGR) (0.58 g g-1day-1 × 102) and NAR (0.48 g m-2 day-1) were obtained in the irrigation schedule at 80 per cent CPE. Relative water content of the plant was significantly highest (82.07 and 71.47 per cent, respectively) in 80 per cent CPE with 5.25 kg/ha hydrogel (I2H4) at 45 and 75 DAT. The maximum value of CGR (2.20 g m-2 day-1) was obtained in the irrigation schedule at 80 per cent CPE with 5.25 kg/ha hydrogel (I2H4). Relative growth rate (RGR) and net assimilation rate (NAR) were found to be non-significant with respect to the treatment combination of different levels of irrigation and hydrogel.

Electronic atmometer: a sustainable irrigation management device

Abstract The objective of this study is to evaluate the evapotranspiration calculated with the use of an electronic atmometer (ETG; mm) against the Penman–Monteith evapotranspiration (ETP-M; mm) by retrieving climatic data from a telemetric weather station. Evapotranspiration was overestimated by the atmometer with the daily mean ratio of ETG to ETP-M calculated at 1.88 (± 0.55). A linear regression model for predicting ETP-M from ETG was developed (ETP-M = 0.49ETG + 0.17) with coefficient of determination r2 = 0.78 and with a beta value of 0.88. Once calibrated, atmometer provide a simple and cost-effective method for determining crop water needs, without relying on complex instrumentation. This is particularly important for irrigation scheduling, especially in semi-arid regions. However, daily evapotranspiration calculations should be preferred over hourly ones, due to the stronger correlation obtained between the ETG and ETP-M.

Impact of three irrigation scheduling tools on irrigation and alfalfa productivity under center pivots

Abstract Determining the amount and timing of irrigation events using scientific irrigation scheduling (SIS) may help optimize water use. Soil moisture sensors, commercial irrigation schedulers, and water balance programs are common SIS tools. These three methods were evaluated to test their impact on alfalfa (Medicago sativa) mass, nutritive value, and irrigation productivity, in comparison to experience‐based irrigation depths chosen by cooperating growers. Trials were conducted at 10 farms across central Utah in 2019. Trials were repeated at nine of these farms in 2020 and six in 2021. Alfalfa mass was measured in a total of 47 cuttings from across all these fields over 3 years. The three SIS methods only impacted alfalfa mass in five cuttings, and it occurred inconsistently at various fields and years. Three cuttings had improved mass with SIS methods and two had reduced production. Forage nutritive value was more often impacted by SIS method than mass, but impacts were rarely large enough to change forage market value. Applied water was lower with most SIS methods than the grower control in 2019 and 2021 but not 2020. This was influenced heavily by the drought conditions and water restrictions during the latter 2 years of this study. As one of the first studies to directly compare how four irrigation scheduling methods for center pivots affect crop production and irrigation levels, results indicated that all three SIS approaches had comparable performance, and in some situations (especially wet years) could reduce applied water by 6%–25% without impacting alfalfa mass or nutritive value.

Comparison of smart applications for evapotranspiration assessment automation with manual estimation using the Thornthwaite method

Abstract. Evapotranspiration assessment is critical for effective agricultural water management, as it is the primary factor influencing decisions regarding the amount, location, timing, and method of crop irrigation. Manual evapotranspiration calculations are time-consuming and labor-intensive, particularly for long-term assessments. Consequently, various automated approaches have been developed in recent decades to improve the speed and accuracy of evapotranspiration estimation. However, not all automated methods demonstrate sufficient reliability for practical applications. The primary objective of this study was to evaluate the performance of widely used and innovative evapotranspiration calculation tools, namely EVAPO, AgSAT, and Evapotranspiration Calculator (Ukraine), and compare their results with the reference Thornthwaite method. The study was conducted in Kherson Oblast from September 2022 to June 2025, utilizing the data from the regional hydrometeorological center and the default settings of the applications. The statistical analysis involved generating evapotranspiration distribution plots, box plots, scatter plots, residual plots, and Bland-Altman plots for each application, alongside calculations of mean differences, root mean square error (RMSE), mean absolute error (MAE), R-squared, and Nash-Sutcliffe Efficiency (NSE). The overall comparisons were conducted using Repeated Measures ANOVA or the Friedman Test, with the Bonferroni correction applied for multiple paired comparisons. The results revealed that the EVAPO application provided the closest evapotranspiration estimates to the reference method (RMSE = 0.78 mm, MAE = 0.60 mm, R-squared = 0.74, NSE = 0.72), while the AgSAT application exhibited the poorest performance. Additionally, AgSAT tended to underestimate evapotranspiration, whereas Evapotranspiration Calculator (Ukraine) tended to overestimate it. These tendencies should be considered when using these applications without prior calibration. The results yielded by ANOVA confirmed that all the evaluated approaches significantly differed from the reference manual estimations using the Thornthwaite method, indicating that even the best-performing application, EVAPO, requires refinement before practical implementation in irrigation scheduling.

Quantifying the effects of irrigation schedule on groundwater level variability using a linked APSIM-MODFLOW model framework

Quantifying the effects of irrigation schedule on groundwater level variability using a linked APSIM-MODFLOW model framework

Synergistic effects of irrigation scheduling and mulching on growth, productivity, and quality attributes of chilli in a semi-arid agroecosystem

Synergistic effects of irrigation scheduling and mulching on growth, productivity, and quality attributes of chilli in a semi-arid agroecosystem

Estimates of Irrigation Water Volume by Assimilation of Satellite Land Surface Temperature or Soil Moisture Into a Water‐Energy Balance Model in Morocco

Abstract The agricultural sector is the biggest and least efficient water user, accounting for around 80% of total water use in North Africa, which is already strongly impacted by climate change with prolonged drought periods, imposing limitations on irrigation water availability. The objective of this study was to estimate irrigation water use for the irrigation district of Doukkala in Morocco from 2017 to 2022 at daily resolution. The approach is based on the energy‐water balance model FEST‐EWB, which computes continuously in time on a pixel basis the main processes of the hydrological cycle and models evapotranspiration and soil moisture (SM) dynamics in the agricultural soil layer by solving the energy and water mass balance equations. Three different approaches were implemented to quantify actual irrigation volumes: (a) FAO‐approach with the irrigation scheduling based on soil moisture and crop stress thresholds, (b) assimilation of satellite land surface temperature (LST) (downscaled Sentinel‐3 data) and (c) assimilation of satellite soil moisture (SMAP‐Sentinel‐1 data). The model was first calibrated over non‐irrigated areas, against LST from LANDSAT and Sentinel‐3. The three irrigation approaches were then validated against soil moisture and evapotranspiration from reference models (MOD16 and WaPOR). The assimilation of LST gave the best estimates of total irrigation volumes compared to observed water allocation data (relative error = 1.5%). The FAO approach also performed well but slightly overestimated the observed data by 15%. On the other hand, coarse pixel resolution and low revisit time affected the performance of the satellite SM assimilation (relative error of −80%).

Sustainable Water Management in Agriculture: Wastewater Treatment and IoT-Enabled Automated Irrigation

Water scarcity and ineffective water utilisation in agriculture provide considerable obstacles to global food security and environmental sustainability. This study investigates the amalgamation of wastewater treatment and IoT-enabled automated irrigation systems as pioneering approaches for sustainable water management in agriculture. Farmers can diminish reliance on freshwater by treating and reusing wastewater, while IoT-enabled irrigation systems enhance water utilisation via real-time monitoring, data analysis, and precise control. This study assesses the technical, economic, and environmental advantages of integrating various technologies, emphasising their capacity to improve water efficiency, crop productivity, and resource conservation. Case studies and experimental findings illustrate the efficacy of IoT-enabled devices in minimising water waste and enhancing irrigation scheduling. The report also examines the obstacles to using these technologies, including as expenses, infrastructure, and farmer uptake. The results highlight the revolutionary potential of combining wastewater treatment with IoT-based irrigation to attain sustainable agricultural practices, enhance water conservation, and facilitate the shift towards a circular economy in agriculture. This study offers practical insights for policymakers, agricultural stakeholders, and technology developers to further scalable and sustainable water management strategies.

Impact of drip irrigation scheduling and nitrogen levels on nitrogen use efficiency, phenology and soil nitrogen dynamics of okra (Abelmoschus esculentus L.)

A field experiment was conducted at Water Technology Centre, College of Agriculture, PJTSAU, Rajendranagar, Hyderabad during summer 2020-21 on “Optimization of irrigation and nitrogen levels under drip fertigation in okra (Abelmoschus esculentus L.) during summer” 2020-21. The experiment was laid out in a split-plot design with Radhika hybrid (40 cm x 45 cm) and replicated thrice. The treatments comprise of three irrigation levels through drip scheduled at 0.75 Epan, 1.0 Epan and 1.25 Epan as main-plots and four nitrogen levels viz., 75 % RDN (112.5 kg N ha-1), 100 % RDN (150 kg N ha-1), 125 % RDN (187.5 kg N ha-1) and 150 % RDN (225 kg N ha-1) as sub-plots. Experimental soil was sandy clay in texture, alkaline in reaction, medium in organic carbon content, low in available nitrogen, high in available phosphorous and available potassium, respectively. The results indicated that optimized drip irrigation scheduling significantly improved NUE, with the highest efficiency observed at 1.00 Epan (I2) irrigation scheduling and 75 % RDN (N1) nitrogen level. Phenological development, including days to first flowering, days to 50 % flowering, days to first and final picking was not influenced influenced by irrigation scheduling and nitrogen supply. The number of branches per plant increased with 1.00 Epan (I2) and 100 % RDN (N2) nitrogen application, contributing to higher biomass and potential yield. Soil nitrogen content varied across treatments, with initial and final measurements providing insights into nitrogen uptake and residual soil fertility.

Estimation of Crop Evapotranspiration of Satsuma (Citrus reticulata Blanco) by Normalized Difference Vegetation Index in Nueva Vizcaya, Philippines

Evapotranspiration has a major impact on agricultural productivity particularly in maintaining soil moisture level and sustaining plant health. Crop coefficient (Kc) is an important component for evaluating crop evapotranspiration (ETc) as it incorporates crop characteristics and average effects of evaporation from the soil. This study estimated the crop evapotranspiration of Satsuma in Malabing, Kasibu, Nueva Vizcaya using Kc values from remotely sensed NDVI data. Three neighboring areas with an area of one hectare were selected for the vegetative, early fruiting, and mature fruiting stages. Satellite imagery from Landsat 9 was used in determining NDVI values which are significant in the estimation of Kc values. It was found that the computed Kc values of citrus for the vegetative stage in all the three phases (initial, mid, and late) were 0.41, 0.46, and 0.48, respectively. The Kc values for the early fruiting were 0.47 (initial), 0.45 (mid), and 0.46 (late) and for the mature fruiting stage the values were 0.65(initial), 0.58 (mid), and 0.63 (late) which follows the trend of the FAO Kc values that decrease in the mid phase. The estimated crop evapotranspiration using these Kc values shows that the highest for the vegetative stage is in the month of August and May for both early and mature fruiting stage, while the lowest ETc values were recorded in the month of January for the vegetative and December for both early and mature fruiting stage. Thus, these computed Kc values provide a site-specific value needed for the computation of crop water requirement and irrigation scheduling for citrus production in Kasibu, Nueva Vizcaya, Philippines.

EcoGold Monitor: An IoT-Based System for Real-Time Vermicompost Monitoring

EcoGold Monitor, an Internet of Things (IoT)-based system designed for real-time compost and soil condition monitoring. The prototype employs an ESP32 microcontroller integrated with a DS18B20 digital temperature sensor and a capacitive soil moisture sensor to collect composting data, environmental data pertinent to plant health and precision agriculture. Sensor data are acquired periodically and transmitted over Wi-Fi to the Blynk IoT platform, which provides cloud-based visualization, logging, and remote access through a web or mobile interface. To enhance user accessibility, the system incorporates WiFiManager, enabling dynamic network configuration without hardcoded credentials. This feature allows non-technical users to connect the device to any available Wi-Fi network through a temporary access point interface. Data are visualized in real-time via graphs and historical logs, allowing users to make informed decisions regarding irrigation scheduling and microclimate management.

Impact of Irrigation Intervals, Potassium Silicate and Organic Acids on Improving Water Relationships and Triticum sativa Yield in Sandy Soils

Wheat production in hot, arid climates demands a lot of water; thus, it needs to be drought resistant. Irrigation management and supplementation are critical, and accumulative pan evaporation (APE) evaluation is a useful way. The goal of this study was to determine how varied irrigation schedules, utilizing various APE and both inorganic and organic conditioners, affect wheat crop yield and drought tolerance. We carried out a field experiment at the Ismailia Agricultural Research Station in Egypt's Ismailia Governorate. The split-plot design was used with three replications, and wheat was grown across two winters (2021-2022 and 2022-2023). The main plot received three irrigation treatments (2, 1.5, and 1 based on APE). The sub-main plots had five different treatments: a control group (T1), 1000 mg SiO₂ L-1 as potassium silicate (T2), T2 plus 50 mM citric acid (T3), T2 plus 20 mM acetic acid (T4), and T2 with both 50 mM citric acid and 20 mM acetic acid (T5).Water consumptive use (WCU) and water usage efficiency (WUE) were calculated for seasons, as well as wheat crop yield, total nutrient content, and some soil chemical properties. The study indicated that WCU varied between 1365 to 2067 m³fed-1 and 1371 to 2051 m³fed-1 for wheat crop in 2021/2022 and 2022/2023, respectively. Also, interaction between coefficients of APE and adding KSi with organic acids significantly boosted wheat production, improved how well water was used, increased the total nutrients in the wheat, enhanced the soil's chemical properties, and made nutrients more available during both growing seasons In conclusion, using irrigation treatment 2 APE in conjunction with T5 was the optimum treatment and is suggested when wheat Giza 171 is planted in sandy soil with spray watering in northeast Egypt.

Effects of biochar application on sugarcane growth and physiology under combined saline and drought stress conditions

ABSTRACT Drought and salinity intrusion have been constraints on sugarcane production in coastal areas. Improving water and nutrient uptake and reducing sodium chloride accumulation by applying biochar could be an effective way to solve the problem. A pot experiment was done following a Split-plot design with three replications under greenhouse conditions. We applied four irrigation schedules for the main-plot treatments to maintain different growing conditions, including control, drought, saline, and combined saline-drought (saline stress followed by drought stress). The sub-plot factor was three application rates of oak biochar of 0, 5, and 10 tons ha−1. Here, we found that single stress conditions reduced sugarcane growth for plant height, stalk diameter, leaf number, leaf size and area, total biomass, root mass, and root volume. Physiological parameters, including leaf SPAD, the quantum efficiency of photosystem II, ion leakage, and relative water deficit, also dropped under stress effects. Our results also found that the combined saline and drought stress induced more damage than either stress alone and led to a greater reduction in sugarcane growth. Applying biochar positively affected sugarcane’s growth and recovery after these stress periods. The 10 tons of biochar ha−1 rate was the optimum dose for sugarcane production in drought and saline-affected areas.

Applications of thermal infrared remote sensing in agriculture

Agriculture is a fundamental sector globally, particularly in developing countries, as it provides food, feed and non-food products essential for economic and societal stability. Advancements in remote sensing technologies have greatly enhanced agricultural productivity and management. Thermal infrared remote sensing (TIRS) is a transformative tool in agriculture, enabling precise monitoring of crop and soil conditions by capturing and analysing the emitted radiation in the thermal infrared spectrum (3–14 μm). This technology offers criticalinsights into crop and soil health. Unlike optical sensing, thermal remote sensing supports crop water stress assessment, soil moisture detection, irrigation scheduling, evapotranspiration monitoring, drought stress analysis, disease detection, soil property mapping, crop maturity assessment, yield estimation, tile drainage mapping and residue cover analysis. Integrating TIRS with multispectral and hyperspectral imaging enhances agricultural decision-making, optimises resource allocation and improves crop health. Future research should prioritize AI-driven real-time data processing by integrating machine learning, UAV-based imaging and IoT-enabled monitoringsystems. These advancements can enhance precision agriculture, optimize resource use and improve crop stress detection. As technological innovations continue to evolve, thermal remote sensing is poised to play a pivotal role in sustainable agricultural management, offering valuable insights to improve efficiency and resilience in farming practices.

Comparative assessment of standalone and hybrid deep neural networks for modeling daily pan evaporation in a semi-arid environment

Evaporation represents a fundamental hydrological cycle process that demands dependable methods to quantify its fluctuation to ascertain sustainable agriculture, irrigation systems, and overall water resource management. Meteorological variables such as relative humidity, temperature, wind speed, and sunshine hours affect evaporation non-linearly, resulting in challenges while developing prediction models. To combat this, the study aimed to develop robust models for estimating evaporation in semi-arid environments by applying machine learning techniques. Daily meteorological datasets (from January 2000 to December 2010) for the above variables (input) were collected from the Sidi Yakoub meteorological station in the Wadi Sly basin, Algeria. Conventional deep neural network (DNN) coupled with support vector machine (SVM), Bayesian additive regression trees (BART), random subspace (RSS), M5 pruned, and random forest (RF) were used for developing prediction models using various input variable combinations. Model performances were compared using mean absolute error (MAE), root mean square error (RMSE), determination coefficient (R2), Nash–Sutcliffe efficiency (NSE) coefficient, and percentage bias (PBIAS). Results indicated comparatively better performance for hybrid models (DNN-SVM, DNN-BART, DNN-RSS, DNN-M5 pruned, and DNN-RF) than conventional models (standalone DNN). Among hybrid models, the DNN-SVM model outperformed others with high accuracy and performance and fewer statistical errors in the daily pan evaporation prediction during the testing phase (R²=0.65, RMSE = 3.00 mm, MAE = 2.13, NSE = 0.65, and PBIAS = 3.54). DNN-RF was in the second rank for the prediction with R2 of 0.64, RMSE of 3.00 mm, MAE of 2.16, NSE of 0.64, and PBIAS = 0.41. While the standalone DNN model gave the lowest results with MAE of 4.87, RMSE of 5.00 mm, and NRMSE of 0.65. The present framework’s success in Algeria’s Wadi Sly basin highlights its potential for scalable adoption in irrigation scheduling and drought resilience strategies, yielding implementable steps for policymakers, addressing climate-driven water scarcity. Future research should explore integrating real-time climate projections and socio-hydrological variables to improve predictive adaptability across diverse agroecological zones.

Assessment of the Crop Water Stress Index for Green Pepper Cultivation Under Different Irrigation Levels

The objective of this study was to evaluate the effects of different water levels on yield, morphological, and quality parameters, as well as the crop water stress index (CWSI), for pepper plants under a high tunnel greenhouse in a semi-arid region. For this purpose, the irrigation schedule used in this study includes 120%, 100%, 80%, and 60% (I120, I100, I80, and I60) of evaporation monitored gravimetrically. In this study, increasing irrigation levels (I100 and I120) resulted in increased stem diameter, plant height, fruit number, leaf number, and leaf area values. However, these values decreased as the water level dropped (I60 and I80). At the same time, increased irrigation resulted in improvements in fruit width, length, and weight, as well as a decrease in TSS values. While total yield and marketable yield values increased at the I120 water level, TWUE and MWUE were the highest at the I100 water level. I80 and I120 water levels were statistically in the same group. It was found that the application of I100 water level in the high tunnel greenhouse is the appropriate irrigation level in terms of morphology and quality parameters. However, in places with water scarcity, a moderate water deficit (I80) can be adopted instead of full (I100) or excessive irrigation (I120) in pepper cultivation in terms of water conservation. The experimental results reveal significant correlations between the parameters of green pepper yield and the CWSI. Therefore, a mean CWSI of 0.16 is recommended for irrigation level I100 for higher-quality yields. A mean CWSI of 0.22 is recommended for irrigation level I80 in areas where water is scarce. While increasing the CWSI values decreased the values of crop water consumption, leaf area index, total yield, marketable yield, total water use efficiency, and marketable water use efficiency, decreasing the CWSI increased these values. This study concluded that the CWSI can be effectively utilised in irrigation time planning under semi-arid climate conditions. With the advancement of technology, determining the CWSI using remote sensing-based methods and integrating it into greenhouse automation systems will become increasingly important in determining irrigation times.