IntroductionAccurate prediction of maize (Zea mays L.) grain yield is critical for efficient resource management and enhancing productivity in sustainable agriculture, particularly in low-input systems. The integration of biofertilizers, such as plant growth-promoting rhizobacteria (PGPR) and arbuscular mycorrhizal fungi (AMF), offers a promising avenue to improve crop performance while reducing environmental impacts. However, the complexity of ecophysiological data and their interactions necessitates advanced modeling techniques for precise yield prediction. Machine learning (ML) algorithms, combined with optimization methods, provide robust tools to address this challenge (Ingole et al., 2025). This study proposes a novel hybrid approach combining the Non-dominated Sorting Genetic Algorithm II (NSGA-II) for feature selection and the eXtreme Gradient Boosting (XGBoost) algorithm for predictive modeling. By leveraging ecophysiological data, this approach aims to optimize maize yield predictions under biofertilizer applications, supporting precision agriculture and climate adaptation strategies. The objectives were to identify key predictive features, enhance model accuracy, and interpret the contributions of selected variables to yield outcomes. Materials and MethodsThe study utilized data from 96 experimental plots at the Ferdowsi University of Mashhad's research fields, collected over two years. A comprehensive dataset comprising 75 features (32 primary and 43 interaction terms) was compiled, including ecophysiological variables such as chlorophyll content index (SPAD), canopy temperature, maximum photosynthesis rate, specific root length, and soil phosphorus percentage. The methodology consisted of two main phases: feature selection and predictive modeling. First, NSGA-II, a multi-objective optimization algorithm, was employed to select an optimal subset of features by simultaneously maximizing prediction accuracy (coefficient of determination, R²) and minimizing the number of features. NSGA-II iteratively evaluated feature combinations to identify a Pareto-optimal set, balancing model simplicity and performance. Subsequently, the selected features were used to train an XGBoost model, a gradient-boosting framework known for its robustness in handling complex datasets. The model was validated using 5-fold cross-validation to ensure generalizability. Model interpretability was enhanced through SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) methods. SHAP analysis provided global and local feature importance, while LIME elucidated individual prediction contributions. Counterfactual analysis was also conducted to assess the impact of removing key features on model predictions. Results and DiscussionNSGA-II successfully identified nine key features critical for yield prediction, including canopy temperature at the dough stage (Canopy Temp_4), chlorophyll content index at the milk stage (SPAD_3), soil respiration rate, and maximum photosynthesis rate. These features were selected for their ability to maximize R² while maintaining model parsimony. The trained XGBoost model achieved an R² of 0.63 and a root mean square error (RMSE) of 2.171 tons per hectare, indicating moderate predictive accuracy suitable for agricultural applications. SHAP analysis revealed that SPAD_3 (mean SHAP value: 0.2603 t/ha) and Canopy Temp_4 (0.2512 t/ha) were the most influential predictors, positively contributing to yield predictions. Conversely, complex interactions, such as the interaction between leaf area index at the silking stage and the squared mean canopy temperature, had a slight negative effect (-0.0674 t/ha). LIME analysis further highlighted the negative influence of ear length (weight: -0.9252), suggesting its role in reducing predicted yields in specific cases. The Pareto front generated by NSGA-II corroborated the trade-off between feature count and prediction accuracy, while feature importance plots aligned with SHAP and LIME findings. Counterfactual analysis demonstrated that excluding key features significantly altered predictions, underscoring their importance. The integration of NSGA-II and XGBoost proved highly effective in optimizing maize yield predictions under biofertilizer influence, offering a robust framework for low-input agriculture. The selection of nine key features by NSGA-II reduced model complexity while maintaining predictive power, aligning with the principles of precision agriculture. The high influence of SPAD_3 and Canopy Temp_4 underscores the importance of physiological and environmental factors in yield determination, particularly in biofertilizer-enhanced systems. The negative contribution of certain interaction terms and ear length suggests the need for careful consideration of variable interactions in model development. The use of SHAP and LIME enhanced model transparency, providing actionable insights for farmers and researchers. Compared to traditional models, this hybrid approach outperformed baseline methods, achieving a higher R² and lower RMSE. The findings support the adoption of advanced ML techniques in sustainable agriculture, enabling precise resource allocation and adaptation to climatic variability. Future research could explore additional biofertilizer types and larger datasets to further refine predictive accuracy and generalizability. ConclusionIn conclusion, this study successfully developed and validated a hybrid modeling framework integrating NSGA-II for multi-objective feature selection with XGBoost for predictive modeling, enabling accurate maize grain yield prediction under biofertilizer applications in low-input systems. By identifying a parsimonious set of nine key ecophysiological features—most notably chlorophyll content index at the milk stage (SPAD_3) and canopy temperature at the dough stage—the approach achieved a respectable R² of 0.63 and RMSE of 2.171 t/ha, demonstrating moderate yet practical predictive power suitable for precision agriculture in variable environments. Interpretability analyses via SHAP and LIME underscored the dominant positive contributions of physiological indicators while highlighting nuanced negative effects from certain interactions and traits like ear length, providing valuable insights into biofertilizer-mediated yield dynamics. This methodology not only outperformed traditional baselines by balancing model complexity and accuracy but also supports sustainable resource management and climate-resilient strategies in arid and semi-arid regions. Future efforts should expand datasets, incorporate diverse biofertilizer regimes, and test generalizability across broader agroecological zones to further enhance predictive robustness and real-world applicability.
IntroductionWheat (Triticum aestivum L.) is a strategic global crop, vital for food security, providing approximately 20-25% of the world's caloric intake and a significant share of dietary protein. With the global population projected to reach 9.6 billion by 2050, the implementation of sustainable agricultural practices has become imperative to meet escalating food demands without exacerbating environmental degradation. Traditional farming, heavily reliant on chemical fertilizers and pesticides, has led to soil and water pollution, threatening ecosystem health and human safety. In this context, soil microorganisms, particularly arbuscular mycorrhizal fungi (AMF), play a pivotal role in sustainable production by enhancing nutrient cycling and improving the bioavailability of essential elements like nitrogen and phosphorus. Nitrogen is a major yield-limiting factor in wheat production, with peak demand during tillering, heading, and grain filling stages. However, conventional nitrogen sources like urea are prone to leaching in light soils, contaminating groundwater. Bio-fertilizers and plant growth-promoting rhizobacteria (PGPR) offer a sustainable and eco-friendly alternative to chemical fertilizers, improving both targeted plant nutrition and soil physicochemical properties. Furthermore, plant hormones, such as cytokinins, act as chemical messengers and are crucial in mediating plant responses to environmental stresses. Cytokinins regulate key processes including cell division, chlorophyll synthesis, delay of senescence, and ultimately, yield enhancement. The Pishgam wheat cultivar, developed for cultivation under normal and limited irrigation in Iran's cold climates, has shown promising performance. However, limited information exists on its response to co-application of mycorrhizal fungi and cytokinin hormones. Therefore, this study was conducted to investigate the effects of different inoculation levels of mycorrhizal fungi, urea fertilizer, and cytokinin foliar application on the yield and yield components of irrigated Pishgam wheat. Materials and MethodsThe experiment was carried out during the 2022-2023 cropping season at the research farm of Islamic Azad University, Mahabad Branch, West Azerbaijan, Iran. The study was arranged as a factorial experiment based on a Randomized Complete Block Design (RCBD) with three replications. The experimental factors included: first, mycorrhizal organic fertilizer (containing mycorrhizal fungi) at three levels (2, 4, and 6 kg per 100 kg of seed); second, urea fertilizer from a urea source at three levels (0, 50, and 100 kg per hectare); and third, cytokinin foliar application (6-benzylaminopurine) at three stages (no application, application at flowering stage—Zadoks code 55, and application at the beginning of grain filling stage). The seeds of the Pishgam cultivar were disinfected with 70% ethanol and sodium hypochlorite before being inoculated based on the treatment groups. Soil analysis indicated a loamy clay texture with neutral to weak alkaline pH, negligible urea, and sufficient levels of phosphorus and potassium. Seeds were planted at a depth of 4 cm with a density of 180 kg.ha-1. Urea fertilizer was applied in two splits: one-third at planting and the remaining two-thirds at the beginning of stem elongation and before flowering. A 3 mM cytokinin solution was prepared and applied at a rate of 1.5 liters per plot using a hand sprayer, with Tween 20 added as a surfactant. Standard weed, pest, and disease management practices were uniformly applied. At physiological maturity, plants from a one-square-meter area per plot were harvested. Measured traits included plant height, flag leaf length, spike length, number of fertile spikes per square meter, number of grains per spike, thousand-kernel weight, biological yield, grain yield, and harvest index. Data were subjected to analysis of variance (ANOVA) using SAS software (version 9.4), and mean comparisons were performed using Duncan's Multiple Range Test at a 5% probability level. Results and DiscussionThe analysis of variance revealed that the interaction effects between the factors were highly significant. The interaction between mycorrhizal fungi and urea fertilizer significantly influenced flag leaf length, spike length, number of spikes per square meter, and biological yield. Similarly, the interaction between mycorrhizal fungi and cytokinin application had a significant effect on plant height, flag leaf length, grain yield, and harvest index. Furthermore, the interaction between urea fertilizer and cytokinin application timing significantly affected spike length, number of spikes per square meter, thousand-kernel weight, grain yield, and harvest index. The highest grain yield (approximately 12 tons.ha-1) was achieved with the combined application of 4 kg.ha-1 mycorrhiza, 50 kg.ha-1 urea, and cytokinin spraying at the flowering stage. This combination outperformed the control and other treatments, highlighting a strong synergistic effect. The results demonstrated that mycorrhizal inoculation, particularly at 4 kg.ha-1, significantly enhanced nutrient uptake, especially phosphorus, leading to improved photosynthetic capacity and longer flag leaf duration. Cytokinin application, especially at the flowering and grain filling stages, effectively delayed senescence, increased the number of fertile tillers, and improved grain filling efficiency. The combination of these treatments allowed for a substantial reduction in urea fertilizer input by 50% (from 100 to 50 kg.ha-1) without any compromise in yield, underscoring the role of bio-fertilizers and growth regulators in enhancing nutrient use efficiency. The improvement in yield components, including spike length, number of spikes per unit area, and thousand-kernel weight, was directly linked to better resource allocation and reduced oxidative stress under the integrated management approach. ConclusionThe findings of this research conclusively show that the integrated application of mycorrhizal fungi (at an optimal rate of 4 kg.ha-1), reduced urea fertilizer (50 kg.ha-1), and cytokinin foliar spraying at critical reproductive stages (flowering and early grain filling) can significantly enhance the yield and yield components of Pishgam wheat. This management strategy works through multiple mechanisms: improved nutrient and water uptake via expanded root systems mediated by mycorrhizae, enhanced photosynthetic activity and delayed leaf senescence induced by cytokinins, and more efficient allocation of photo-assimilates to the grains. The study successfully demonstrates that it is possible to replace a significant portion of chemical urea fertilizer with organic amendments and growth regulators, thereby promoting a more sustainable and environmentally friendly wheat production system without sacrificing productivity. For achieving high and stable yields in wheat cultivation under similar agro-climatic conditions, it is highly recommended to adopt this integrated approach using 4 kg.ha-1 mycorrhizal seed inoculation, 50 kg/ha urea application, and cytokinin foliar spray at the flowering stage. AcknowledgementThe authors of this article feel it necessary to sincerely express their gratitude for the cooperation and support of the officials of the Faculty of Agriculture and the laboratory experts at Islamic Azad University, Mahabad Branch, who extended their utmost assistance during various stages of this research.
IntroductionThis temperature varies for each species, but there is a linear relationship between growing degree-days and plant growth rate. Growing degree-days (GDD) are used to classify plants by their flowering date, to estimate harvest maturity, and to predict the length of time between two growth stages. In a study in Ardabil, the findings indicated that the temperature of the region is correlated with the temperature of corn growth, and based on the zoning, about 16% of the total area of the province was identified as very suitable, 22% as suitable, 27% as moderate, and about 35% as unsuitable for corn cultivation. The aim of this study is to zone GDD and identify ranges of cumulative growth degree days, which can be used to more accurately determine the amount of crop cultivation and their production management in different counties of Isfahan province. Materials and MethodsIn this study, 30-year daily temperature statistics (minimum, maximum, and average) from 33 meteorological stations were used to calculate GDD and growing season length (1984 to 2021). To calculate thermal units, the first growing season length for temperature thresholds of 5°C and 10°C was extracted using the Jillosy coding method (March 3rd with code 1 and March 2nd with code 365), and then the growing season thermal units were calculated by subtracting the average daily temperature from the base temperature. Finally, zoning maps were drawn for each indicator in Arc GIS. Despite different definitions of the growing season, temperature and humidity play a special role in all of these definitions. According to the definition of the World Meteorological Organization's Commission on Climatology/Climate Variability, the length of the growing season is the time interval between the first period after July 10th in which the average daily temperature is above 5°C for at least 6 consecutive days (as the starting point) and the first 6-day period with an average daily temperature below 5°C (as the ending point). Results and DiscussionThe cities of Isfahan province were divided into 4 groups based on a base temperature of 5°C, which received a range of 2500 to 5000-degree days of temperature growth. This number changed from 1500 to 4500 degrees Celsius for a base temperature of 10°C. Based on a base temperature of 5°C, the shortest growing season length of 114-200 days was observed in the western and southern regions of the province, and the longest growing season length of 365-331 days was observed in the northern and eastern regions of Isfahan province. For a base temperature of 10°C, a similar geographical trend was observed, with the difference that the range of the shortest and longest growing season lengths was (72-140) and (306-261) days, respectively. The correlation coefficient between GDD at base temperatures of 5 and 10°C and longitude was significant at the 95% level. The relationship between the temperature units received during the growing season and the longitude at the base temperature of 5 and 10 °C was increasing from west to east of Isfahan province. ConclusionThe results showed that in Isfahan province, the length of the growing season and the absorbed GDD increase as one move from west to east. Moving from north to south of the province was an inverse relationship. Based on the base temperature of 5°C, the shortest growing season length is 114-200 days in the western and southern regions of the province and the longest growing season length is 331-365 days in the northern and eastern regions of Isfahan province. For the base temperature of 10°C, a similar geographical trend is observed, with the difference that the range of the shortest and longest growing season lengths is (72-140) and (306-261) days, respectively. Considering the base temperatures of 5°C and 10°C, the cities of Isfahan province are classified in the range of 1500 to more than 5000 GDD. The help of this classification, it is possible to predict the time of occurrence of weeds and pests in different regions. Certainly, by combining temperature zoning with other elements required by each plant (soil, topography and precipitation), more comprehensive information will be obtained.
IntroductionSesame (Sesamum indicum L.) is a key oilseed crop, prized for its high-quality oil and protein content, making it vital to both agriculture and the economy. As global population growth drives up demand for vegetable oils, sesame production has become increasingly significant in Iran and worldwide. However, the heavy reliance on chemical fertilizers to enhance yields has caused environmental challenges, including soil degradation, reduced fertility, and water pollution. Biochar, a stable organic material produced through the thermal decomposition of plant biomass, offers a sustainable alternative by improving soil’s physical and chemical properties, enhancing water retention, and reducing nutrient loss. Combining biochar with chemical fertilizers can decrease dependency on chemical inputs while boosting crop performance, supporting sustainable farming practices. This study evaluated the effects of integrated biochar and chemical fertilizer application on sesame’s morphophysiological and agronomic traits, aiming to develop a practical strategy for improving its productivity. Materials and MethodsThis study was conducted during the 2020-2021 cropping season as a factorial experiment in a randomized complete block design with three replications in a field located in Aliabad-e Katul, Golestan Province, Iran. The experiment evaluated five biochar levels (0, 2, 4, 8, and 10 by weight, denoted as B0, B2, B4, B8 and B10) and three chemical fertilizer levels (0, 50%, and 100% of crop requirement, denoted as F0, F50%, and F100%). Soil samples from a 0-30 cm depth were analyzed for physicochemical properties before land preparation, which involved plowing, disking, and leveling. Nitrogen, phosphorus, and potassium fertilizers were applied based on soil test results, with urea, triple superphosphate, and potassium sulfate as sources. The cultivar Oltan was planted manually on June 15, 2020, in 4×5 m plots. Irrigation occurred weekly, and weed, pest, and disease control were maintained. Harvesting took place on October 12, 2020, with traits such as plant height, number of lateral branches, number of capsules per plant, number of seeds per capsule, 1000-seed weight, seed yield, biological yield, harvest index, Oil percentage, Oil yield and chlorophyll content (a, b, and total) measured. Chlorophyll was quantified using spectrophotometry at 663, 646, and 470 nm wavelengths. Results and DiscussionThe results indicated that all examined traits were significantly influenced by the main effects of biochar and chemical fertilizer. The interaction effect was significant only for the number of capsules per plant. The highest plant height (102.57 cm), number of lateral branches (4.03), number of capsules per plant (54.11), thousand seed weight (2.97 g), seed yield (1267.4 kg.ha-1), biological yield (5418.3 kg.ha-1), harvest index (22.03%), Oil yield (625.22 kg.ha-1) and chlorophyll a (1.62 mg.g-1 fresh weight) were obtained from the treatment with B8 biochar and F100% chemical fertilizer. The highest number of seeds per capsule (70.59) was recorded in the B10 biochar treatment. The highest levels of chlorophyll b and total chlorophyll were observed in the B4 biochar treatment, with 1.15 and 2.75 mg.g-1 fresh weight, respectively. The control treatment recorded the highest oil percentage of 52.82%. Biochar improved soil water and nutrient retention and enhanced the uptake of nutrients such as nitrogen and magnesium, while chemical fertilizers provided direct access to nutrients and promoted growth. These results are consistent with previous research that emphasizes biochar’s role in increasing crop yield and quality. The synergy between biochar’s soil-improving effects (such as increased cation exchange capacity) and the nutrient supply from chemical fertilizers significantly enhanced sesame performance. Since the highest seed yield was obtained at the highest fertilizer level used, further research is recommended to determine the optimal fertilizer level. ConclusionThe use of biochar and chemical fertilizers markedly enhanced sesame’s morphophysiological and agronomic responses. Biochar improved soil conditions and minimized nutrient leaching, while chemical fertilizers supplied essential nutrients, resulting in higher seed yields and better growth metrics. This approach demonstrates potential for reducing chemical fertilizer use and advancing sustainable agriculture. Future studies should explore optimal application rates and long-term impacts.
Introduction[1]The escalating demand for food, driven by global population growth, poses a significant threat to environmental sustainability. Conventional monoculture agricultural systems, while often profitable in the short term, are increasingly recognized as major contributors to soil degradation, biodiversity loss, and heightened vulnerability to climate change and economic fluctuations. In response, integrated agricultural systems, such as agroforestry, which synergistically combine crops, livestock, poultry, and trees, have emerged as a promising pathway toward sustainable intensification. These systems are theorized to enhance ecological resilience through increased biodiversity, improve soil health, and offer greater economic stability by diversifying income sources and reducing dependency on external inputs. This study was therefore designed to conduct a comprehensive evaluation of sustainability and economic productivity indicators, comparing mono-dimensional and integrated agricultural systems in two distinct villages within Meshginshahr County, Iran, with a specific focus on ecological health, economic viability, and the critical metric of local food security. Materials and MethodsThis survey-analytical research was conducted in 2023 in two purposively selected villages—Arjaq and Jabdaraq—located in Meshginshahr County, Ardabil Province, Iran. Data collection integrated field observations, in-person interviews with local farmers, and official agricultural census data. To quantitatively assess sustainability, a novel Composite Agricultural Diversity Index (ADI) was constructed, comprising five weighted components: Biodiversity (Shannon-Wiener Index), Functional Diversity, Spatial Diversity, Temporal Diversity, and Resilience (assessed through farmer surveys on system recovery from disturbances). Economic analysis was performed by calculating total costs, income, profit, and profit percentage for each documented agricultural system. Food self-sufficiency was evaluated by comparing the annual production of key food groups within each village against established per capita consumption requirements. Additionally, new indices for land-based and population-based self-sufficiency were developed and calculated to provide a holistic view of local food security. Results and DiscussionThe findings revealed a pronounced superiority of integrated agricultural systems across all evaluated metrics. Ecologically, the most complex system (Arable + Gardening + Livestock + Poultry) achieved the highest Composite Agricultural Diversity Index in both Arjaq (4.718) and Jabdaraq (4.181), far exceeding scores for single-activity systems like sole gardening (1.170) or livestock (0.865). This high ADI signifies greater biodiversity, functional redundancy, and spatial complexity, which directly contribute to enhanced ecosystem resilience against environmental stresses such as pests and drought. Soil quality analysis corroborated these findings, showing superior organic matter content and nutrient levels (e.g., nitrogen, phosphorus) in systems incorporating trees and diverse plant cover compared to monoculture arable lands. Economically, the integrated systems demonstrated robust performance. While individual components like poultry sometimes showed high profit percentages, the combined systems (e.g., Arable+Gardening+Livestock) generated significantly higher total absolute profits (e.g., 270.97 million Rials in Arjaq) due to synergistic effects. These synergies included using livestock manure as organic fertilizer, thereby reducing costs for chemical inputs, and utilizing crop residues as animal feed. This resource recycling not only lowered operational expenses but also distributed economic risk across multiple revenue streams, insulating farmers from market or crop-specific failures. The most striking outcome was the disparity in food self-sufficiency. Jabdaraq, with its highly diversified production, achieved complete self-sufficiency, producing surpluses in crucial categories like poultry meat (175% of need), cereals (187%), and garden products (a remarkable 1714%). In stark contrast, Arjaq, despite its focus on lucrative grape production and greater access to irrigation, exhibited significant deficits in animal protein, meeting only 38% of its poultry, 44% of its egg, and 0% of its fish requirements. Its massive surplus in garden products (1589%) was insufficient to compensate for these core nutritional shortfalls, highlighting the risks of over-specialization. Consequently, the composite self-sufficiency index for Jabdaraq (5.08) was more than double that of Arjaq (2.3), underscoring that diversification, rather than mere land or water availability, is the cornerstone of sustainable food security. ConclusionIn general, multi-dimensional, integrated agricultural systems deliver enhanced ecological sustainability through greater biodiversity and soil health, improved economic profitability and risk mitigation through synergistic resource use, and, most importantly, ensure genuine local food self-sufficiency. the presence of diverse agricultural systems in an area leads to increased economic sustainability and food security, and to some extent compensates for limited access to water. It also reduces the need for external and chemical inputs, which results in greater economic and environmental productivity.
