Crop Yield Research Articles

A harmonized dataset relating alternative farmer management practices to crop yield, soil organic carbon stock, nitrous oxide emissions, and nitrate leaching generated using IPCC methodologies and meta-analyses.

Farming practices such as soil tillage, organic/mineral fertilization, irrigation, crop selection and residues management influence multiple ecosystem services provided by agricultural systems. These practices exhibit complex, non-linear interrelationships that affect crop productivity, water quality, and non-carbon dioxide greenhouse gases (GHG) emissions, possibly offsetting their benefits regarding soil organic carbon (SOC) sequestration. Current methodologies from the Intergovernmental Panel on Climate Change (IPCC) for assessing the impacts of alternative farming practices on GHG emissions rely on global or country-specific coefficients. However, these methods often do not explicitly account for the combined effects of management practices on carbon and nitrogen cycles or productivity, as this is not required for national GHG inventories. Here we present a new dataset featuring 1.8 Mln of agronomic case scenarios, i.e., unique combinations of farming practices and pedoclimatic conditions, which have been associated with values of SOC changes, nitrous oxide emissions, nitrate-nitrogen leaching, and crop yield. To synthesize trade-offs and synergies between farming practices, each case scenario has been ranked with a ∑ommit index (∑i) value, a fuzzy-based measure ranging from 0 (bad) to 1 (good). The four trade-off components have been estimated by combining available information from i) the 2019 Refinement to the 2006 IPCC Guidelines for National Greenhouse Gas Inventories, ii) the guidelines for Green Water Footprint Accounting, iii) the Italian National Institute of Statistics, iv) and other international meta-analytic studies. The dataset presents four ∑i series, corresponding to alternative perceptions of sustainability from three potential stakeholder categories (young farmers' cooperative, agrochemical company, public agricultural policy agency) plus one equally weighted option. By providing a harmonized data source and an innovative metric, this dataset allows users to explore trade-offs associated with alternative management practices across four key agricultural components and assess their impact on perceived agroecosystem sustainability.

WRKY45 positively regulates salinity and osmotic stress responses in Arabidopsis.

Salt damage is a major issue that causes a decline in crop yield. WRKY transcription factors (TFs) extensively regulate plant biotic and abiotic stress responses, growth, and development. WRKY45 is crucial in regulating leaf senescence, low phosphorus responses, and cadmium stress response in Arabidopsis. However, the involvement of WRKY45 in salinity and osmotic stress responses is unclear. Here, we report that WRKY45 plays a vital role in responding to salinity and osmotic stress. NaCl and sorbitol treatments upregulate WRKY45 expression. Furthermore, the overexpression of WRKY45 (WRKY45-OXs) may enhance the tolerance of Arabidopsis to salinity and osmotic stress. Moreover, the root length, fresh weight, chlorophyll, and proline content were significantly higher in WRKY45-OXs than in the wide type (WT) Col-0 plants after salt or PEG treatment, whereas malondialdehyde and reactive oxygen species (ROS) levels were significantly lower than in the WT plants. Correspondingly, the overexpression of WRKY45 modulated the expression of stress-responsive genes. Dual luciferase assay and electrophoretic mobility shift assay further confirmed that WRKY45 can activate the promoter of RD29A by directly binding to specific W-box cis-acting elements. Overall, our experimental evidence suggesting that WRKY45 mainly acts as a key regulator coordinating the response to high salinity and osmotic stress through mechanisms dependent on ABA signaling along with enhanced antioxidant capacity.

Solid-state fermentation of green waste for the production of biostimulants to enhance lettuce (Lactuca sativa L.) cultivation under water stress: Closing the organic waste cycle.

Food production faces important challenges such as water scarcity and the overall need of novel sustainable strategies. This study assesses the effect of the biostimulant produced through solid-state fermentation (SSF) of green waste (wood chips and grass residues) inoculated with Trichoderma harzianum with and without l-tryptophan as a precursor for indole-3-acetic acid (IAA) production, a well-known plant hormone. The fermented solid demonstrated significant positive effects on the growth of lettuce (Lactuca sativa L.) under different irrigation conditions. Substantial enhancements were observed in growth parameters such as fresh weight, plant height, leaf area and leaf quantity, along with chemical parameters including total phenol content, chlorophylls, carotenoids, and antioxidant activity (DPPH). The results also showed a positive impact on the nutritional quality of lettuce, particularly under normal irrigation conditions. In conclusion, this study highlights the biostimulant potential to improve the yield and nutritional quality of lettuce crops by reusing plant residues. Additionally, it poses the relevance of applying circular economy principles in sustainable agriculture and organic waste management.

Agrivoltaics development progresses: From the perspective of photovoltaic impact on crops, soil ecology and climate.

Agrivoltaics, the simultaneous use of land for both agriculture and photovoltaic (PV) energy production, has gained significant attention as a sustainable land-use strategy. This review investigates the progress of agrivoltaics from the perspective of its impacts on crops, soil ecology, and climate. First, the impacts of agrivoltaic systems on solar radiation were assessed, including soil humidity and, temperature dynamics, while considering the potential for changes in soil microbial communities. Second, how PV panels influence crop growth, yield, and quality through the modification of light distribution, temperature regulation, and soil humidity were explored. Lastly, the challenges and propose recommendations for optimizing the integration of agriculture and PV systems were addressed. This review aims to highlight the benefits and trade-offs of agrivoltaics, offering a roadmap for future research and implementation strategies to enhance the synergy between renewable energy production and sustainable agriculture.

An objective methodology for waterlogging risk assessment based on the entropy weighting method and machine learning

Waterlogging disasters are one of the most severe and widespread agricultural meteorological disasters. They affect about 15% of land surface globally, causing a significant reduction in crop growth and yields. This paper presents an objective methodology for assessing waterlogging risk, primarily in non-urban, predominantly agricultural areas. The waterlogging risk was assessed by evaluating vulnerability and hazard based on key environmental, anthropogenic, and climatic factors. The weights of factors affecting the waterlogging vulnerability were determined using the entropy weight method (EWM), assuring the objectivity of the overall evaluation results. The obtained waterlogging risk map was validated by comparing it with observed and detected waterlogged sites using Sentinel-2 imagery and Random Forest classification. The key novelties of this study are the use of the entropy weight method to objectively determine the relative importance of factors influencing waterlogging vulnerability, and a two-step validation process which includes field-based comparison and remote sensing validation. The presented methodology was demonstrated in the Vojvodina region, Serbia. The following waterlogging vulnerability factors were used: soil properties, geomorphology, surface depressions, average phreatic water table depth, and land cover. The EWM shows that surface depressions and soil properties have the most significant influence on waterlogging vulnerability. The highest waterlogging hazard classes occur in about 31% of the analyzed territory. The waterlogging hazard was estimated based on water balance for the non-vegetation season and maximum daily precipitation in spring, both modeled using the Generalize Extreme Value distribution function. The highest waterlogging hazard classes occur in about 31% of the analyzed territory. The final risk map shows that the high waterlogging risk occurs in about 11% of the territory. Those are mainly areas in the central, eastern, and southeastern parts of the Vojvodina region, usually along the main watercourses. High agreement between the detected waterlogged areas and the produced waterlogging risk map was achieved, validating the proposed methodology. The presented waterlogging risk assessment methodology is valuable for planning and policy-making for various water management and environmental activities. Although it is demonstrated in Vojvodina, by selecting the appropriate factors of vulnerability and hazard, it can be applied to any other region.

Robust counting for multi-species plants based on Few-Shot learning

Accurate counting of plant organs at various growth stages is crucial for crop growth monitoring, phenotypic assessment, and yield prediction. Traditional plant counting models, typically designed for specific plant types, often exhibit poor generalization capabilities. In this research, an improved model, Field-CounTR, was proposed to accurately count multiple plant organs. The Field-Count dataset, utilizing a Few-Shot method, was introduced to enhance accuracy in plant counting. Additionally, a mixed salient module was developed to improve the feature fusion capability of sample images by exploiting their high similarity in Few-Shot counting tasks. During the downsampling process, Shuffle Attention was integrated to reduce redundant information in the feature fusion process. Furthermore, a hybrid convolution module combining Do-Conv and dilated convolutions was developed to increase the speed of convolutional inference and expand the receptive field through over-parameterized and dilation operations. To assess the effectiveness of the proposed approach, tests were conducted using the Field-Count dataset, which includes Sorghum, Wheat, Maize, and Rice. The results demonstrated a mean absolute error (MAE) of 14.49 and a root mean square error (RMSE) of 21.14. Compared with the CounTR model, the Field-CounTR model reduced the MAE and RMSE by 2.01 and 1.33, respectively. The enhanced Field-CounTR model exhibited superior feature extraction performance, high detection accuracy, and excellent generalization capabilities. This model can accurately count multiple plant types in complex field or orchard conditions and offers a wide range of applications.

Predicting photovoltaic greenhouse irradiance at low-latitudes of plateau based on ultra-short-term time series

Accurate and reliable ultra-short-term prediction of solar irradiance in photovoltaic (PV) greenhouses at low-latitude plateau is essential to precisely control electricity consumption of greenhouse equipment and ensure high quality crop yields. However, the irradiance in the low-latitude plateau has problems such as poor data quality, limited short-term prediction accuracy, and insufficient ability to capture nonlinear characteristics. Therefore, in order to achieve efficient utilization of photovoltaic resources, this study proposed a new hybrid integrated model TTAO-CNN-BiGRU-Attention framework to predict ultra-short-term photovoltaic greenhouse irradiance in the region. Monthly and seasonal characteristics of irradiance in low-latitude plateau areas were analyzed by statistical methods. The performance of the proposed model was verified using 9 different models for 5 different data volumes and 4 different seasons. Comprehensive analysis results show that Total radiant instantaneous(TRI) demonstrates a seasonal trend, generally low in spring, high in summer and autumn, relatively stable in autumn and winter. The monthly trend initially increases and then decreases, reaching the highest value of the year in September. The scheme proposed in this paper makes full use of the advantages of CNN, BiGRU, Attention and TTAO, greatly improving the comprehensive prediction ability of the model. In predicting different data amounts, 1 year prediction performance was the best, with RMSE, MAE, MAPE and R2 reaching 70.61 W/m2, 31 W/m2, 9.3% and 95.84%, respectively. With regard to different seasons, autumn prediction performance was the best, with RMSE, MAE, MAPE and R2 reaching 66.27 W/m2, 31.02 W/m2, 8.37% and 95.87%, respectively. The TRI prediction curve of the proposed model was closer to the actual value than other comparison models. The study found that the TTAO-CNN-BiGRU-Attention model is more accurate and stable than many traditional models in predicting ultra-short-term TRI in low-latitude plateau photovoltaic greenhouses, which can provide a reference for the comprehensive performance of PV greenhouse irradiance prediction models and precise regulation of energy supply in the future.

Effects of agricultural plastic films on crop growth and soil health in tobacco fields: A comparative study

In recent years, the impact of microplastics on soil microorganisms and crop growth has gained significant attention. However, the effects of agricultural plastic films on crop growth and soil health in tobacco fields are not clear. In our study, we conducted field experiments to investigate the effects of six types of agricultural film treatments on soil fertility, soil microbial community, and plant growth. Compositions of study treatments were as follows: T1: farmhouse film; T2: photodegradation film; T3: black film (6 μm); T4: black film (8 μm); T5: transparent film (6 μm); T6: transparent film (8 μm). Our results showed that photodegradable film treatment was beneficial for promoting crop growth and root development. The fresh stem biomass, dry root biomass, and dry stem biomass were significantly increased by 14.58 %, 68.70 %, and 18.27 %, respectively, under the T2 treatment, when compared to the T1 treatment. In addition, our results showed that photodegradation film treatment maintained soil pH value, compared with other agricultural film treatments. The application of photodegradation film treatment offered advantageous effects in the preservation of soil moisture and temperature. In addition, the diversity of soil microorganisms improved with photodegradable film. Compared to T1 treatment, the number of OTUs of bacteria and fungi improved by 1.94–7.64 % and 7.39–30.08 % under other treatments, respectively. Furthermore, our study showed that pH emerged as the paramount environmental determinant. The number of subnetworks treated with photodegradable film significantly increased, indicating a more complex and stable functional diversity of soil microbial communities. Additionally, compared to bacteria, fungal communities exhibited greater adaptability and stability. The results of this study support the view that photodegradable film can be employed, as it can to enhance crop yield, improve soil quality, maintain a favorable ecological environment, and mitigate the adverse environmental impact of microplastics.

Seasonal auto-regressive integrated moving average with bidirectional long short-term memory for coconut yield prediction

Crop yield prediction helps farmers make informed decisions regarding the optimal timing for crop cultivation, taking into account environmental factors to enhance predictive accuracy and maximize yields. The existing methods require a massive amount of data, which is complex to acquire. To overcome this issue, this paper proposed a seasonal auto-regressive integrated moving average-bidirectional long short-term memory (SARIMA-BiLSTM) for coconut yield prediction. The collected dataset is preprocessed through a label encoder and min-max normalization is employed to change non-numeric features into numerical features and enhance model performance. The preprocessed features are selected through an adaptive strategy-based whale optimization algorithm (AS-WOA) to avoid local optima issues. Then, the selected features are given to the SARIMA-BiLSTM to predict the coconut yields. The proposed SARIMA-BiLSTM is adaptable to handling a widespread of various seasonal patterns and captures spatial features. The SARIMA-BiLSTM performance is estimated through the coefficient of determination (R2), mean absolute error (MAE), mean squared error (MSE), and root mean square error (RMSE). SARIMA-BiLSTM attains 0.84 of R2, 0.056 of MAE, 0.081 of MSE, and 0.907 of RMSE which is better when compared to existing techniques like multilayer stacked ensemble, convolutional neural network and deep neural network (CNN-DNN) and autoregressive moving average (ARIMA).

Phenotypic traits of sunflower varieties depend on the composition of cover crops

ContextIntroducing cover crop (CC) mixtures is a promising approach to enhance the multifunctionality of ecosystem services provided by CCs. However, CC mixtures have contrasting effects on subsequent crop yield, depending on multiple factors such as the type of subsequent crop and the mixture composition. In the context of climate change, sunflower (Helianthus annuus L.), which is adapted to environments with low nitrogen (N) and water requirements, has multiple varieties with different drought-tolerance strategies. However, little is known about how drought-tolerant sunflower varieties differ in their response to CCs in low-input systems. ObjectiveThis study aimed to characterize CC ecosystem services related mainly to N and water and to investigate how CC ecosystem services influence the responses of sunflower varieties that differ in drought sensitivity. MethodsCCs and sunflower varieties were organized in a randomized non-complete block design with a split-plot arrangement in 2021–2022 and 2022–2023. CC treatments consisted of a pure grass CC (rye), a mixture of legume CCs (purple vetch/fodder pea), three mixtures of legume and non-legume CCs (faba bean/Indian mustard/phacelia; fodder pea/rye/purple vetch and fodder radish/hairy vetch/white mustard) and a relay CC treatment (fodder sorghum then faba bean). Sunflower varieties exhibited different drought-tolerance strategies for leaf expansion and transpiration. Establishment, development, growth, N status and productivity were evaluated for the sunflower varieties preceded by CCs through low- and high-throughput phenotyping. Multiple variables of growth and development were assessed by applying image-processing tools to unmanned aerial vehicle (UAV) RGB images. ResultsThe results indicate that CCs influenced early and late N-release uptake by sunflower, thereby extending the seed-filling period. Optimizing the CC chosen allows for yields equivalent to those of intensively tilled bare soil, while increasing the amount of carbon returned to the soil and weed control in low-input cropping systems. Furthermore, in addition to the CC chosen, optimizing the sunflower varieties chosen can improve sunflower growth during dry years. ImplicationsThese results can inform decisions about CCs, sunflower variety and management in low-input systems to better match the nitrogen released from CC residues to subsequent cash crop responses during vegetative and post-flowering phases.

Thriving in adversity: Understanding how maize seeds respond to the challenge of combined cold and high humidity stress.

Extreme conditions, such as cold and high humidity in northeast China's high-latitude maize region, can hinder crop yield and stability during the vegetative stage. However, there is a paucity of research examining the effects of simultaneous cold and high humidity stress on plant responses. In this study, we characterized the acclimation of JD558 (cold- and high humidity-sensitive hybrid) and JD441 (cold- and high humidity-tolerant hybrid) to stress at sowing caused by cold (4°C), high humidity (25%), and their combined stress for five days, using physiological measurements and metabolomics during the stress treatments and recovery stages. Cold, high humidity, and their combined stress prolonged seed development and restricted material transport, with high humidity harming seed survival more than cold. Combined stress exhibited a more significant inhibitory effect on growth than individual stress. Individual and combined stress reduced α-amylase activity, disrupted antioxidants levels, increased malondialdehyde content, disturbed the oxidative balance within seeds, and impeded seed growth and development. Most carboxylic acids and their derivatives were downregulated caused by combined stress. In JD558, sucrose, D-glucose, glucose-1-phosphate, and fructose-1,6-bisphosphate were downregulated, while these metabolites were upregulated in JD441, leading to a blockage of glycolysis in JD558. After eliminating stress, JD441 showed greater α-amylase activity and a smaller decrease in MDA levels, resulting in a smaller reduction in root growth and transport rate than JD558. In summary, the different responses of the cold and high humidity sensitive hybrid and the tolerant hybrid to combined stress are related to the recovery ability after stress elimination.

Improving soil quality and crop yield of fluvo-aquic soils through long-term organic-inorganic fertilizer combination: Promoting microbial community optimization and nutrient utilization

Improving soil quality and crop yield of fluvo-aquic soils through long-term organic-inorganic fertilizer combination: Promoting microbial community optimization and nutrient utilization

Shaping resilience: The critical role of plant response regulators in salinity stress.

Salinity stress affects plant growth, development, biomass, yield, as well as their survival. A series of signaling cascade is activated to cope the deleterious effect of salinity stress. Cytokinins are known for their regulatory roles from cell growth and expansion to abiotic stress signaling. Two component system (TCS) are important multistep phosphorelay signal transduction machinery converging cytokinin, ethylene and light signal transduction pathways together. Plant TCS comprises of histidine kinases, phosho-transfer proteins and response regulators. Histidine kinases perceive the signal and relay it to response regulator via histidine containing phosphor-transfer proteins. Response regulators are one of the major and diverse component of TCS system which have been extensively studied for their role in plant growth, development and circadian rhythm. However, knowledge of their regulatory role in abiotic stress signaling is limited. This mini-review specifically focus on role of response regulators in salinity stress signaling. Response regulators is the divergent node of TCS machinery, where cross-talks with other stress-mediated, phytohormone-mediated, as well as, light-mediated signaling pathways ensues. Studies from past few years have established central role of response regulators in salinity stress, however, the detailed mechanism of their actions need to be studied further. Response regulators act as both negative as well as positive regulator of salinity and cytokinin signaling, making it an excellent target to increase crop yield as well as stress tolerance capabilities.

Controlled release urea combined with normal urea maintains the N balance and improves the environmental and economic benefits in wheat–maize multiple cropping

Controlled release urea combined with normal urea (CRUNU) can potentially improve crop yields and reduce the associated environmental risk. However, the effects of CRUNU on farmland environmental benefits and the agroecosystem nitrogen (N) balance have not been evaluated in the winter wheat–summer maize multiple cropping system in northwest China, and few studies have quantified the impacts of CRUNU on N losses with this cropping system based on life cycle assessment. Therefore, we performed a field experiment for two years during 2020–2022 with two types of N fertilizer (normal urea (NU) and CRUNU) and at three N application rates (low: 135 kg N ha–1, medium: 180 kg N ha–1, and high: 225 kg N ha–1) at Caoxinzhuang experimental farm to comprehensively evaluate the effects of CRUNU on the agronomic, N balance, environmental, and economic benefits in winter wheat–summer maize cropping. Compared with NU, CRUNU helped to synchronize the N supply and demand for wheat and maize, and under all three N application rates, the annual average grain yield and grain N uptake increased with CRUNU, as well as reducing the volatilization of NH3 by 16.69 %, N2O emissions by 25.16 %, and N losses due to nitrate (NO3–) leaching by 44.23–61.65 %, thereby maintaining the total N storage. Considering both the N input and output, CRUNU achieved a lower N surplus than NU and maintained the N balance in the farmland ecosystem. In addition, CRUNU significantly reduced the reactive N losses at the three N application rates to decrease the N footprint (NF) by 25.48–42.85 %, where CRUNU obtained the lowest NF at the medium N application rate. More importantly, the benefits of CRUNU for increasing the grain yield at different N application rates offset the higher agricultural input costs and reduced the environmental costs due to N2O emissions, NH3 volatilization, and NO3– leaching losses, so the net benefits increased by 23.14–29.25 %. Furthermore, the net benefits under CRUNU did not differ significantly at the medium and high N application rates. Therefore, we recommend CRUNU application at the medium rate as an effective strategy for improving the N balance, environmental effects, and economic benefits in wheat–maize multiple cropping systems

Integrated Crop Production Management

Abstract: Integrated Crop Production and Management is an innovative and sustainable approach that combines a variety of farming practices to optimize crop yield, soil health, and environmental sustainability. The approach integrates strategies such as crop rotation, organic fertilization, pest and weed management, water conservation, and soil fertility enhancement into a comprehensive farming system. ICPM would minimize dependency on chemical inputs, promote soil structure, and enhance biodiversity while improving crop tolerance to climatic variability and pests. This paper explores the principles and methodologies behind ICPM, bringing to light how it can promote agricultural productivity and ecological balance at the same time. The paper highlights the potential of IPM, conservation tillage, and agroforestry in promoting farm resilience while reducing environmental degradation. Case studies and field experiments demonstrate the effects of ICPM on crop yield, soil health, and profitability of the farm. The adoption of modern and traditional practices in ICPM not only addresses the immediate needs of crop production but also contributes to long-term sustainability. This research will demonstrate how ICPM can be a viable solution to current challenges in agriculture, such as climate change, food security, and resource depletion, and offer farmers a pathway to more resilient and sustainable agricultural systems.

Ensemble Techniques in Plant Nutrient Deficiency Detection: A Survey

Abstract: Plant nutrient deficiency detection represents a critical challenge in modern agriculture, significantly im- pacting crop health, yield, and sustainable farming practices. This survey paper presents a comprehensive analysis of ensemble learning techniques for automated detection of plant nutrient deficiencies through image analysis. Our research evaluates a hybrid approach combining MobileNet’s efficient feature extraction capabilities with ensemble methods including Random Forest and Gradient Boosting algorithms. The methodology encompasses three key compo- nents: feature extraction using MobileNet’s lightweight architecture for processing plant leaf images, implementation of individual classification models, and development of ensemble techniques that leverage the strengths of multiple clas- sifiers. Through extensive experimentation and comparative analysis, our findings demonstrate that ensemble methods consistently outperform individual models, achieving superior accuracy in detecting nutrient deficiencies across various plant species. The integration of MobileNet with ensemble techniques provides a robust framework that balances com- putational efficiency with prediction accuracy. This research contributes to the advancement of precision agriculture by proposing a scalable, real-time solution for nutrient deficiency detection that can be practically implemented in field conditions, ultimately supporting improved crop management decisions and agricultural productivity..

Transformative Approaches to Agricultural Sustainability: Automation, Smart Greenhouses, and AI

Agricultural sustainability is continually undermined by climate change, resource depletion, and the increasing worldwide need for food. Fundamental technologies, including automation, smart greenhouses, and artificial intelligence (AI), are changing modern agricultural methods by providing novel ways to improve sustainability in farming. This review study examines the significance of these technologies in advancing sustainable agricultural systems, particularly their effects on resource optimization, environmental conservation, and economic efficiency. Automation technologies, such as robots, drones, and autonomous vehicles, enhance farm management by enhancing efficiency and minimizing resource waste. Intelligent greenhouses, fitted with IoT sensors and temperature regulation systems, provide precise management of environmental conditions, therefore improving agricultural output while minimizing water and energy use. AI-driven technologies, including machine learning and predictive analytics, enhance crop health monitoring, pest management, and yield prediction, enabling data-informed decision-making. The research analyses the combination of various technologies, focusing their synergies in developing comprehensive smart agricultural systems that promote enduring sustainability. Despite the apparent promise, challenges like substantial initial investment, technological intricacy, and scalability persist. This review continues by addressing future directions, policy implications, and research requirements for promoting the use of these technologies to enhance global agricultural sustainability.

Harnessing Climate Data for Accurate Crop Yield Predictions

Harnessing Climate Data for Accurate Crop Yield Predictions

Optimizing crop yield forecasting with ensemble machine learning techniques

Accurate crop yield prediction is critical for ensuring food security and efficient agricultural management, particu- larly in the face of climate change and rising global populations. Current predictive models often fall short in generalizing across diverse agricultural contexts due to their inability to capture complex interactions between various climatic and soil variables effectively. This study addresses these gaps by proposing a com- prehensive machine-learning framework that integrates ensemble methods to enhance crop yield prediction accuracy. Using a dataset enriched with climatic and agricultural features, we evaluated multiple models, including Linear Regression, Decision Tree, Random Forest, Gradient Boosting, XGBoost, Bagging Regressor, and K-nearest neighbors. The Random Forest model emerged as the top performer, achieving an accuracy of 0.985 and a Mean Squared Error (MSE) of 1.08e+08. At the same time, the Bagging Regressor closely followed with an accuracy of 0.984 and comparable MSE. Gradient Boosting and XGBoost models also demonstrated robust performance, with accuracies ranging from 0.865 to 0.974 and MSE values between 9.60e+08 and 1.89e+08. Our approach includes extensive hyperparameter tuning and k-fold cross-validation to ensure model generalizability and robustness across agricultural scenarios. These findings highlight the effectiveness of ensemble methods in capturing complex data relationships and their superiority over traditional models in predicting crop yields. Our work sets the stage for future research into integrating real-time data and advanced hybrid models, aiming to refine predictive accuracy further and support sustainable agricultural practices.

AI in agriculture: Smart greenhouses and indoor farming systems

This comprehensive article examines the transformative impact of artificial intelligence on modern indoor agriculture, focusing on key technological advancements in smart greenhouse management and controlled environment agriculture. The article explores critical areas, including precision environmental control, nutrient management in hydroponic systems, plant health monitoring and disease management, harvest optimization, quality control, and energy management with sustainability practices. AI-driven solutions have revolutionized traditional farming approaches by integrating deep learning algorithms, computer vision systems, and IoT sensor networks, enabling unprecedented levels of automation, resource efficiency, and crop yield optimization. Implementing these technologies has significantly improved agricultural metrics, from disease detection and prevention to harvest timing and quality assessment, while substantially reducing operational costs and environmental impact.