Global agriculture is facing severe challenges, including increasing crop yields, addressing climate change, and coping with resource shortages. Accurate prediction of crop growth is crucial for sustainable agricultural development. Traditional prediction methods have limitations in data processing capacity and forecasting accuracy, while the introduction of artificial intelligence (AI) offers new opportunities for optimizing prediction models. This paper systematically reviews the key technologies and applications of AI in crop growth prediction, covering machine learning, deep learning, and ensemble learning methods under various crop and climate conditions. It further explores the decisive impact of data quality and quantity on AI model performance and analyzes pressing challenges such as model interpretability, data privacy, and security. Based on existing research, this paper proposes future research directions and application strategies for AI-driven intelligent agriculture, aiming to provide theoretical support and practical guidance for precision and smart farming.

抄録全体を表示

With the intensification of global water scarcity and soil salinization, sustainable agricultural development faces escalating challenges, prompting growing interest in the efficient utilization of saline water resources and the cultivation of salt-tolerant crops. In recent years, advances in artificial intelligence (AI) and big data technologies have opened new avenues for addressing key technical bottlenecks in saline water desalination, salt recovery, and salt-tolerant crop breeding. These technologies enable high-throughput data processing and intelligent analysis, thereby enhancing the efficiency of desalination processes, improving the recovery and recycling of salt resources, and accelerating the identification of salt-tolerant genes and precision breeding of resilient crop varieties. Furthermore, the integration of real-time monitoring and dynamic control systems in both water treatment and agricultural management contributes to the enhanced reliability, adaptability, and cost-effectiveness of saline agriculture. This paper systematically examines the current state of research and major technical challenges in saline water utilization and salt-tolerant crop development. It further elucidates the transformative potential of AI- and data-driven innovations in promoting sustainable land reclamation and agricultural productivity on saline-alkali soils. The paper aims to provide a theoretical foundation and practical guidance for future research and technological innovation in the context of climate-resilient and resource-efficient agriculture.

抄録全体を表示

Global population growth and climate change pose significant challenges to agricultural production, making the improvement of crop yield and quality a central task for sustainable global agriculture. Modern agrarian biotechnology offers innovative approaches to achieve this goal through microbiome regulation, biofertilizer application, and gene editing. This paper first reviews the composition and function of the plant microbiome and its crucial role in enhancing crop disease resistance and optimizing nutrient uptake. It then examines the applications and effectiveness of biofertilizers in enhancing soil fertility, promoting plant growth, and promoting agricultural sustainability. Finally, it evaluates recent advances in gene editing technologies for crop improvement, with a focus on their potential to enhance stress resistance and nutrient use efficiency. By systematically integrating and analyzing current research findings, this paper aims to provide scientific evidence and technical guidance for agricultural research and practice, contributing to global food security and sustainable agricultural development.

抄録全体を表示

Amidst escalating global climate change and environmental degradation, ecological protection of vegetation has emerged as a critical strategy for enhancing ecosystem resilience and safeguarding biodiversity. In parallel, the rapid advancement of artificial intelligence (AI) technologies has opened new frontiers for ecological research and conservation practice. This review systematically examines recent progress in the application of AI to vegetation ecological protection, elucidating its current capabilities and future potential. First, it investigates AI-assisted vegetation monitoring, emphasizing the integration of remote sensing, image recognition, and machine learning algorithms for health assessment, species classification, and spatiotemporal dynamics analysis. Second, it explores AI-driven approaches in ecosystem management, including vegetation restoration, disaster impact assessment, and predictive ecological modeling. Third, the role of AI in biodiversity conservation is analyzed, particularly in optimizing habitat suitability assessments and enhancing decision support for conservation planning. Moreover, the paper highlights the synergies between AI and sustainable development goals, discussing how AI contributes to evidence-based policymaking and participatory ecological governance. Drawing on representative case studies, the review synthesizes the current effectiveness of AI applications and delineates key technological innovations and implementation challenges. Ultimately, it identifies critical research gaps and outlines future directions to promote interdisciplinary collaboration and inform the strategic deployment of AI in ecological protection. The overarching aim is to provide a comprehensive theoretical foundation and actionable insights for researchers, practitioners, and policymakers engaged in promoting sustainable ecological outcomes through intelligent technologies.

抄録全体を表示

Against the backdrop of the continuous expansion of salinized soils worldwide, the development of salt-tolerant crops has become a key strategy to enhance agricultural stability and sustainability. This study aims to elucidate the genetic regulatory mechanisms underlying the uptake of micronutrients such as iron, zinc, and manganese by salt-tolerant crops under saline-alkaline conditions, and systematically evaluates the roles of key functional genes in micronutrient utilization. Through the integration of big data and multi-omics analyses—including genomics, transcriptomics, and epigenetics—the physiological response patterns of crops under various salinity conditions and their underlying genetic networks were revealed. In parallel, the synergistic effects of traditional breeding approaches and advanced gene editing technologies in improving salt-tolerant crop varieties are discussed, along with strategies for leveraging intelligent algorithms to optimize breeding parameters and construct integrated, precision-oriented breeding models. The findings offer new insights into the molecular basis of micronutrient uptake in salt-tolerant crops and provide theoretical and technical support for the sustainable development of agriculture on saline-alkaline soils globally.

抄録全体を表示

Soil microbial communities, as key factors in regulating crop disease resistance, have a profound impact on crop health and agricultural productivity due to their complex structures and diverse functions. This study establishes a multidimensional analytical framework based on big data analysis and artificial intelligence (AI) technologies to systematically explore the association between soil microbial communities and crop disease resistance. Firstly, by deeply analyzing the co-regulation mechanisms between soil microbial communities and crop gene expression, the role of specific key microbes in enhancing crop immunity is elucidated. Secondly, the study compares microbial community diversity under different soil environments and investigates their differential effects on disease resistance regulation. Through machine learning models and big data processing methods, the study achieves accurate prediction of microbial effects on crop disease resistance, providing a theoretical basis for optimizing disease-resistant breeding and biological control strategies. Finally, typical case studies demonstrate the practical application of big data and AI technologies in this field of research. This study aims to uncover the intrinsic mechanisms of soil microbial communities in regulating crop disease resistance, offering new insights for the development of microbe-based precision agriculture and disease-resistant breeding technologies, and exploring innovative pathways for sustainable agricultural development.

抄録全体を表示

Potatoes are a globally significant staple crop, with starch as its primary economic product, widely utilized across the food, pharmaceutical, and industrial sectors. Enhancing both the yield and quality of potato starch is a critical goal in modern agriculture. This paper provides a comprehensive analysis of the interactions between environmental factors—such as soil characteristics, temperature, and humidity—and key genes involved in starch biosynthesis, including GBSS, SBE, and AGPase. Particular attention is given to how environmental conditions modulate gene expression and enzyme activity through complex gene regulatory networks, thereby influencing starch synthesis and structural optimization. The paper also explores the integration of big data analytics and artificial intelligence, especially machine learning and deep learning techniques, in decoding environment-gene interactions. These technologies facilitate large-scale data analysis, the optimization of cultivation conditions, and the implementation of precision agriculture strategies. Case studies demonstrate that precision management based on environment–gene interaction analysis can substantially improve potato starch productivity and quality. This paper ultimately aims to establish a theoretical and technical foundation for intelligent, data-driven agricultural practices, offering actionable insights for optimizing potato cultivation systems.

抄録全体を表示

With the continuous advancement of agricultural modernization, the application of big data technologies and gene editing methods in rice breeding and nitrogen fertilizer management has increasingly become a research focus. This study proposes a synergistic optimization strategy that integrates multi-source data analysis, gene editing technologies (such as CRISPR-Cas9), and machine learning and deep learning algorithms to achieve an organic integration of rice variety improvement and nitrogen fertilizer management. Based on whole-genome data of rice, dynamic monitoring information of soil nitrogen, and environmental conditions such as climate and soil properties, a collaborative optimization model was developed to enhance nitrogen uptake efficiency, optimize breeding strategies, and enable precise and intelligent fertilization control. The goal is to maximize nitrogen use efficiency, increase rice yield, and reduce environmental burdens. Empirical analysis and case studies demonstrate that the proposed strategy offers significant advantages in improving crop productivity and promoting sustainable agriculture. The findings provide valuable insights for the future application of smart agricultural technologies.

抄録全体を表示

Genome-wide association studies (GWAS) serve as essential tools for elucidating the genetic architecture of complex traits through systematic analysis of genome-wide genotype-phenotype relationships. The exponential growth of high-throughput sequencing technologies has generated unprecedented volumes of genetic variation data, including single-nucleotide polymorphisms, creating substantial computational challenges for data processing and analysis. This review examines the application of big data technologies in GWAS, encompassing four critical domains: (1) scalable data storage and management systems, (2) high-performance computing frameworks, (3) dimensionality reduction and feature extraction methodologies for large-scale datasets, and (4) machine learning and artificial intelligence algorithms for identifying and predicting genetic variation patterns. Through comprehensive analysis of current big data approaches in GWAS, we address the computational complexity inherent in massive genomic datasets, focusing on methods for detecting epistatic interactions and strategies for multi-dimensional data integration. Furthermore, we explore the transformative potential of AI technologies in precision breeding applications, particularly their implications for crop improvement and personalized agriculture. The primary objective of this work is to advance complex trait genetics research by systematically evaluating big data processing methods and AI technologies in GWAS contexts, ultimately providing novel technical frameworks and methodologies for efficient functional gene identification.

抄録全体を表示

With the increasing significance of microorganisms in agriculture, environmental protection, and biotechnology, accurately deciphering the functions of individual strains has become a core issue in both fundamental and applied research. Traditional experimental and statistical approaches face limitations in terms of data scale, complexity, and accuracy. In contrast, artificial intelligence (AI) technologies—including intense learning and machine learning—have substantially improved the precision and efficiency of function prediction by effectively analyzing genomic information and integrating multi-omics data, such as transcriptomics and metabolomics. This study systematically outlines the AI-based technological framework for strain function prediction, detailing key methods and workflows in genomic data analysis, functional annotation, and the integration of multi-omics data. Taking agricultural applications such as salt-alkali-tolerant crops as examples, it further explores the potential advantages of AI-driven strain selection in accelerating crop improvement. The study also provides an in-depth analysis of current technical challenges, including data quality control, model generalization, and coordinated processing of multi-omics data, and proposes future research directions and improvement strategies. This study aims to offer theoretical support and practical guidance for advancing microbial function prediction technologies and promoting the development of intelligent and precision agriculture.

抄録全体を表示

The screening of agricultural microbial strains plays a crucial role in enhancing crop stress resistance, promoting growth, and improving agricultural productivity, particularly in the cultivation of salt- and alkali-tolerant crops. However, traditional screening methods often suffer from limitations, including lengthy processing cycles, low efficiency, and inadequate environmental adaptability. In recent years, the rapid development of artificial intelligence (AI) technologies has brought unprecedented opportunities to the field of agricultural microbiology. This paper provides a comprehensive review of recent advances in AI-based screening and optimization of agricultural microbial strains, with a focus on the integration of genomics, metabolomics, and multi-omics data for strain function prediction and underlying mechanisms. It also examines specific applications of AI in the study of salt-alkali-tolerant crops, such as utilizing soil and crop growth data to optimize strain selection and application conditions, thereby enhancing the plant growth-promoting effects. In addition, the paper discusses technical frameworks for multi-strain combination optimization and highlights the unique advantages of AI in environmental adaptability simulation and functional prediction of microbial strains. This paper aims to clarify the vital role of AI technologies in microbial strain screening and optimization, reveal their application potential in the field of salt-alkali-tolerant crops, and provide references and prospects for future theoretical research and practical applications.

抄録全体を表示

To elucidate the regulatory mechanisms of starch accumulation and key enzyme activities in rice grains under different cultivation methods in arid regions, this study selected four representative rice varieties and established three typical planting patterns: water-conserving dry direct seeding (W1), dry seeding followed by irrigation (W2), and traditional transplanting (W3). The yield components, grain starch content, and activities of key enzymes involved in starch synthesis, including AGP, GBSS, and SSS, were systematically analyzed. The results showed that, compared with W3, both W1 and W2 treatments slightly reduced total yield but significantly improved 1,000-grain weight and seed setting rate, and markedly increased total starch and amylose content in the grains, with the most pronounced effects observed under W1 treatment. Enzyme activity assays indicated that W1 and W2 significantly enhanced SSS activity, while W3 maintained higher AGP and GBSS activity. Significant varietal differences were observed in response to cultivation methods, with variety B performing best across multiple key traits. Further correlation analysis revealed significant positive relationships between starch synthase activity and starch accumulation, indicating that cultivation methods can influence starch composition and accumulation by modulating the expression and activity of related enzymes. This study reveals the physiological effects of different rice cultivation models on starch synthesis in arid regions, providing theoretical and practical guidance for optimizing dry direct seeding techniques and improving rice quality.

抄録全体を表示

In the context of global climate change, the increasing frequency of extreme precipitation events poses a significant threat to the yield stability and security of major food crops, such as sweet potatoes (Ipomoea batatas L.). To systematically elucidate the physiological response mechanisms of sweet potato to waterlogging stress at different growth stages and their effects on yield formation, this study used the cultivar WY18 and applied three waterlogging treatments: during the vine elongation stage, the storage root expansion stage, and the entire growth period. Changes in morphological traits, physiological and biochemical indicators, and yield components were comprehensively analyzed. The results showed that waterlogging significantly reduced the root-to-shoot ratio and relative leaf water content, induced the accumulation of proline and soluble sugars, and markedly enhanced the activities of antioxidant enzymes such as catalase, peroxidase, and superoxide dismutase, indicating that the plant activated its antioxidant defense system to alleviate oxidative damage caused by stress. In terms of yield, waterlogging during the storage root expansion stage resulted in a greater yield reduction than during vine elongation. At the same time, the whole-period stress caused the most severe yield loss, suggesting that the storage root expansion stage is the most sensitive period to waterlogging. Correlation analysis revealed that yield decline was closely associated with plant water imbalance and the intensity of antioxidant responses. The novelty of this study lies in its systematic comparison of sensitivity differences across sweet potato growth stages to waterlogging stress, identification of key mechanisms—such as assimilate allocation shifts and metabolic disorders—that limit yield formation, and determination of the critical sensitive period.

抄録全体を表示

To systematically elucidate the synergistic regulatory mechanisms of nitrogen management and spatial configuration on crop growth dynamics and yield formation in soybean-maize strip intercropping systems, this study employed two nitrogen application levels (no nitrogen and nitrogen application) and four interspecific spacing treatments (30, 45, 60, and 75 cm), with corresponding sole cropping systems as controls. Key parameters, including crop growth rate, dry matter accumulation and distribution, yield components, and land equivalent ratio, were monitored and analyzed. The results demonstrated significant interactive effects between crops under intercropping conditions, with a suitable interspecific spacing of 60 cm optimizing interspecific resource competition and complementarity, thereby markedly enhancing dry matter accumulation and grain yield. Nitrogen application not only improved yield but also reshaped the pattern of dry matter distribution, reinforcing intra-system synergy and resource use efficiency. All intercropping combinations outperformed sole cropping in land use efficiency, with the nitrogen-applied 60 cm spacing treatment achieving the best performance, reflecting strong crop complementarity and yield potential. This study proposes a dual-factor synergistic regulation strategy, combining “nitrogen application + optimized interspecific spacing,” and highlights the pivotal role of dry matter accumulation and distribution in yield formation. It provides theoretical and practical guidance for high-yield and efficient management of soybean-maize strip intercropping systems.

抄録全体を表示

Against the backdrop of increasingly severe water shortages in arid irrigated regions of Northwest China, elucidating the root adaptive mechanisms of spring wheat under drip irrigation in response to staged drought-rewatering stress holds significant theoretical and practical value for promoting water-saving and efficient agriculture. This study selected spring wheat cultivars with contrasting drought tolerance and employed soil column cultivation combined with precise drip irrigation control. Mild and moderate drought treatments were applied during the tillering and jointing stages to systematically evaluate the dynamic responses of key physiological and ecological indicators, including root morphological development, antioxidant enzyme activity, osmotic adjustment substance content, and yield formation. The results showed that mild drought promoted root growth in the 20–60 cm soil layer, enhanced root activity and antioxidant capacity, and induced a pronounced physiological compensation effect after rewatering, thereby contributing to yield stability or improvement. Significant differences were observed between drought-tolerant and drought-sensitive cultivars in terms of root regulation pathways, stress resistance strategies, and the intensity of physiological responses. By coupling precise water regulation under drip irrigation with staged drought stress, this study proposes a regulation pathway of “moderate stress–timely rewatering” to optimize root development and achieve yield compensation, offering scientific insights and technical support for efficient water-saving cultivation and precision irrigation strategies for spring wheat in arid irrigated areas.

抄録全体を表示

Water scarcity and excessive nitrogen application have become major constraints to the sustainable development of modern agriculture. As an efficient water-saving irrigation technique, drip irrigation offers substantial potential for the precise management of water and nitrogen in crop production. To clarify how water-nitrogen coordination under drip irrigation influences winter wheat performance, a field experiment was conducted in the North China Plain. A randomized block design with varying nitrogen application rates and irrigation levels was used to systematically assess their effects on grain yield formation, photosynthetic characteristics, soil nitrogen dynamics, and water and nitrogen use efficiency. The results demonstrated that appropriate combinations of water and nitrogen significantly enhanced the net photosynthetic rate and grain yield of winter wheat. Optimal treatments not only improved water and nitrogen use efficiency but also reduced residual soil nitrogen and the risk of nitrogen leaching, promoting synergistic and efficient utilization of resources. This study elucidated the regulatory mechanisms of water-nitrogen interactions on key physiological processes during critical growth stages of winter wheat under drip irrigation, and established an optimized water-nitrogen management model aimed at improving yield and resource efficiency. The findings provide scientific guidance for water and nitrogen regulation in winter wheat drip irrigation in similar ecological regions, offering theoretical support and practical strategies to address water scarcity and nitrogen overuse.

抄録全体を表示

To address the critical challenges of low embryogenic induction efficiency and limited system stability in winter wheat microspore culture, this study systematically optimized key technical parameters involved in microspore isolation, induction, and differentiation, while also assessing genotypic responses. Using three winter wheat cultivars as experimental materials, a series of culture trials was conducted under varying pretreatment regimes, isolation solutions, inoculation densities, and differentiation media. The results indicated that an extended period of low-temperature pretreatment notably improved microspore viability and embryogenic competence. Among the tested isolation solutions, one specific formulation yielded the highest proportion of viable microspores. An intermediate inoculation density was found to be optimal for callus induction, significantly enhancing tissue proliferation. Furthermore, a specially formulated differentiation medium substantially promoted organogenesis from callus tissues. Significant to highly significant differences among genotypes were observed during microspore culture, particularly at the stages of callus formation and differentiation. This study established a simplified, efficient, and reproducible microspore culture system with wide genotypic applicability, clarified the major influencing factors and their interactions in microspore embryogenesis, and provided a robust cellular engineering platform for accelerating the breeding process of winter wheat.

抄録全体を表示

Against the backdrop of increasingly scarce water resources in northern China, exploring efficient water-saving irrigation models for summer maize holds significant practical value. Under the condition of equal total irrigation volume, this study systematically compared the effects and underlying mechanisms of four irrigation methods—furrow irrigation (FI), drip irrigation (DI), subsurface drip irrigation (SDI), and micro-irrigation (MI)—on soil water distribution, plant growth and development, water use efficiency, and yield formation in summer maize. The results showed that SDI and MI significantly optimized the vertical distribution of soil moisture within the root zone, reduced surface soil moisture fluctuations, and enhanced moisture retention in deeper layers, thereby promoting deeper root growth and prolonging leaf functional duration. These changes led to improved photosynthetic capacity and dry matter accumulation, ultimately contributing to yield enhancement. Compared with FI, both SDI and MI markedly improved yield performance and water use efficiency, highlighting their strong potential for water conservation. This study innovatively revealed the synergistic physiological mechanisms through which advanced irrigation technologies enhance water use efficiency and delay leaf senescence, while elucidating their advantages in yield formation and water-saving effectiveness. The findings provide scientific evidence and management strategies to support green and efficient summer maize production in arid regions.

抄録全体を表示

The soil nitrogen cycle is a core biogeochemical process in farmland ecosystems, with microorganisms playing a crucial role in nitrogen transformation. With the rapid advancement of high-throughput sequencing technologies and big data analysis methods, researchers can now more accurately analyze the structure and dynamic changes of soil microbial communities, thereby exploring their functional mechanisms in nitrogen transformation. This study outlines the primary processes of nitrogen cycling in agricultural soils, with a focus on the roles of various microbial communities in nitrogen mineralization, nitrification, denitrification, and nitrogen fixation. By integrating high-throughput sequencing with multidimensional environmental data, the application of big data in monitoring microbial activity and constructing models of nitrogen cycling is explored. A nitrogen transformation model based on microbial activity, soil moisture, and organic matter variation is proposed to simulate and predict the effects of different management practices on soil nitrogen use efficiency. Furthermore, by incorporating big data mining and machine learning technologies, the study optimizes fertilizer and water management strategies, proposing precision fertilization and integrated water-nutrient management plans that aim to improve nitrogen use efficiency and promote environmental sustainability. This big data-driven, microbially mediated nitrogen transformation model reveals the dynamic mechanisms of soil nitrogen cycling and provides scientific and technological support for the future implementation of precision agriculture.

抄録全体を表示

With the increasing severity of global climate change and water resource scarcity, the agricultural sector faces a growing demand for efficient water utilization and sustainable management. Intelligent irrigation systems based on artificial intelligence (AI) technologies have emerged as a key solution to address these challenges, thanks to their high efficiency in resource optimization. This paper systematically reviews the core technologies of intelligent irrigation systems, including sensor networks, soil moisture monitoring, nitrogen cycle modeling, and automated control systems, with a particular focus on the application of AI techniques in irrigation strategy optimization. Innovative contributions of machine learning, deep learning, and reinforcement learning algorithms to precise water resource management are highlighted. By analyzing the application of AI in real-time data processing, predictive modeling, resource allocation optimization, and sustainable development management, this paper presents the latest research progress and typical practical cases in the field. Major challenges such as data quality control, model accuracy improvement, and system compatibility issues are also discussed in depth, along with potential technical pathways to address these challenges. Ultimately, the paper envisions the future potential of AI-driven intelligent irrigation systems in enhancing water use efficiency, optimizing nitrogen uptake, and promoting agricultural sustainability, thereby providing a valuable reference for future research and practice.

抄録全体を表示

Precision irrigation, as a key technology for improving water resource use efficiency and crop yield, has gradually entered a new era of intelligence and automation, driven by the rapid development of big data technologies. This paper presents a systematic review of precision irrigation technologies based on big data, focusing on key aspects such as data acquisition and processing, irrigation decision model design, and optimization algorithms. First, methods for the integration and processing of multi-source data, including meteorological data, soil moisture data, and crop growth information, are analyzed, and an efficient irrigation decision support framework is proposed by combining machine learning and deep learning techniques. Second, big data-based irrigation models and optimization methods are discussed, with particular emphasis on the soil-plant-atmosphere continuum model and its application in irrigation optimization, along with the role of multi-objective optimization algorithms in enhancing irrigation system performance. Finally, the practical impacts of precision irrigation on water conservation, crop yield improvement, economic benefits, and environmental sustainability are evaluated, and the current challenges and future development directions of the technology are analyzed. This paper aims to provide a comprehensive overview of the current status and progress of precision irrigation technologies, clarify key directions for future research, and offer theoretical foundations and technical support for the design and application of big data-driven precision irrigation systems.

抄録全体を表示

With the increasing global pressure on water resources, accurate assessment and effective management of the agricultural water footprint have become essential for achieving sustainable agricultural development. This paper, based on big data technologies, systematically analyzes the composition and dynamic changes of the agricultural water footprint. By integrating remote sensing, sensor data, meteorological information, and agricultural production data, a multi-source data fusion framework for analyzing agricultural water footprints is proposed. Considering the water demands and environmental dependencies of different crops, the study conducts a differentiated assessment from both spatial and temporal perspectives, revealing the potential impacts of agricultural activities on regional water resources and associated ecological risks. It further explores strategies to reduce water consumption by optimizing agricultural production structures and cropping patterns, with a focus on the application of sustainable farming practices such as smart irrigation, crop rotation, and intercropping. This paper aims to provide a scientific basis and decision-making support for the refined management of agricultural water resources, risk early warning, and sustainable development through a big data-driven water footprint assessment approach.

抄録全体を表示

Farmland soil health forms the foundation for crop productivity and sustainable agriculture, with soil nitrogen dynamics playing a critical role in both aspects. This study develops a comprehensive framework for predicting soil nitrogen dynamics by integrating sensor technologies, remote sensing, and microbial community analysis. Using big data analytics and machine learning algorithms, we identify key factors governing nitrogen transformation, availability, and loss, and establish data-driven prediction models. To support intelligent farmland management, we explore multi-source data fusion for nitrogen optimization and develop decision-support strategies for organic fertilizer application and irrigation management. Case studies across diverse environmental conditions demonstrate model performance and identify implementation challenges. This integrated approach provides a scientific foundation for precision nitrogen management and advances the development of intelligent decision-making systems for sustainable agriculture.

抄録全体を表示

Against the backdrop of increasing global water scarcity, the treatment and resource utilization of agricultural wastewater have become key components in promoting sustainable agricultural development. Agricultural wastewater encompasses farmland drainage, effluents from livestock and poultry farming, and agricultural processing wastewater, all of which are characterized by complex compositions and variable properties that impose high demands on treatment technologies. Currently, widely applied methods include biological treatments, physicochemical treatments, and various integrated approaches, which recover key nutrients such as nitrogen and phosphorus for reuse, thereby alleviating some of the ecological pressures associated with fertilizer use. Additionally, reclaimed water irrigation not only helps boost crop yields but also improves soil structure and the environment, demonstrating significant environmental benefits. However, the application of reclaimed water also poses risks, including heavy metal residues, the spread of pathogenic microorganisms, and potential long-term impacts on soil and crop health. In recent years, the extensive application of modern information technologies—such as sensor systems, the Internet of Things, and artificial intelligence—in wastewater treatment and irrigation management has greatly enhanced processing efficiency and the level of reclaimed water utilization. This paper systematically reviews the current status, technological progress, and typical application cases of agricultural wastewater treatment and resource utilization. It analyzes the application potential of related technologies in sustainable agriculture and explores future research directions and development challenges.

抄録全体を表示

In recent years, with the increasing scarcity of water resources, reclaimed water irrigation has been widely applied in agricultural production as an important measure to alleviate water shortages. However, due to the complex composition of reclaimed water, long-term irrigation may lead to soil physical structure degradation, salt accumulation, nutrient imbalance, and alterations in microbial community composition, thereby posing potential risks to crop growth, quality, and food safety. Based on relevant literature and typical cases from both domestic and international studies, this paper systematically evaluates the mechanisms by which reclaimed water irrigation affects soil structural stability, chemical properties (including salt and nutrient dynamics), and microbial ecosystems, while also examining its impacts on crop physiological growth, quality changes, and heavy metal accumulation risks. Furthermore, it discusses in detail the key technologies, data collection, and analytical methods used in long-term monitoring of soil and crops. This paper aims to provide a theoretical basis and technical support for developing scientific and rational reclaimed water irrigation management strategies, ensuring the safety and sustainability of agricultural production.

抄録全体を表示

The water retention performance of farmland soil is a key factor in ensuring crop growth, improving irrigation efficiency, and achieving sustainable agricultural development. In recent years, with the rapid advancement of artificial intelligence technology in the agricultural field, new opportunities have emerged for soil moisture management. Based on a systematic analysis of soil water retention characteristics and their main influencing factors, this study constructs a framework for optimizing soil water retention performance strategies using artificial intelligence, primarily focusing on three key aspects: intelligent monitoring and data mining, deep learning models, and precision irrigation. The framework is then verified through case studies with performance evaluations. By developing a real-time soil moisture monitoring system, the framework enables multi-source data collection and precise analysis; deep learning is used to model historical and real-time data, predict crop irrigation needs, and optimize irrigation control strategies; combined with typical farmland cases, field experiments are conducted to verify the effectiveness of intelligent soil improvement and management plans in enhancing soil water retention performance. This study aims to provide scientific and innovative technological support and practical guidance for farmland water resource management and sustainable agricultural development, promoting the in-depth application of artificial intelligence technology in precision agriculture.

抄録全体を表示

The global challenges of water scarcity and environmental pollution are intensifying. Nutrients such as nitrogen and phosphorus in wastewater not only contribute significantly to water pollution but also represent valuable alternative resources to synthetic fertilizers in agricultural production. Efficient recovery of these nutrients can mitigate environmental pressures and support sustainable agriculture. However, conventional wastewater treatment and nutrient recovery methods often face limitations, including low efficiency, high costs, and operational complexity. In recent years, advances in artificial intelligence (AI)—including intelligent monitoring, deep learning–based modeling, and process optimization—have opened new technological pathways for wastewater nutrient recovery. This paper systematically reviews key technologies and persistent challenges in this field, with particular emphasis on AI applications in real-time monitoring, separation process optimization, and intelligent control. Drawing on practical cases and experimental data, the paper evaluates the performance of AI-driven systems in enhancing recovery efficiency, reducing energy consumption, and improving economic outcomes. It also explores the potential of data-driven decision-support tools and intelligent fertilization recommendation systems in agricultural contexts. Finally, the paper discusses prospects for the deep integration of AI with wastewater resource recovery technologies and the need for supportive policy frameworks, providing a scientific basis and technical reference for advancing intelligent wastewater treatment and nutrient recovery.

抄録全体を表示

Agricultural wastewater contains high concentrations of nutrients such as nitrogen and phosphorus, which, if discharged without proper treatment, can lead to environmental problems, including water eutrophication and soil pollution. These nutrients, however, also have considerable potential for resource utilization. Efficient recovery and conversion into fertilizers can strongly support sustainable agricultural development. In recent years, significant advances have been achieved in nutrient recovery and fertilizer production from agricultural wastewater, encompassing physical, chemical, biological, and combined methods. These technologies have been widely applied in the research and production of slow-release and liquid fertilizers. This paper systematically reviews the fundamental characteristics of nutrients in agricultural wastewater, the principles of various recovery technologies, and their specific applications in fertilizer production. It also examines the environmental and economic benefits of these technologies, as well as their limitations and the challenges encountered in practical implementation. Furthermore, the paper outlines future research directions, aiming to provide a systematic theoretical foundation and technical guidance for the resource utilization of agricultural wastewater, thereby promoting green agriculture and a circular resource economy.

抄録全体を表示

With the rapid development of renewable energy technologies, distributed generation and microgrids—key components of future smart power systems—are exhibiting increasing diversity and complexity in practical applications. Due to the intermittency of energy sources, the distributed nature of control architectures, and uncertainties in operating environments, the stability of microgrid systems has become an increasingly prominent issue. This paper systematically reviews the research progress in the field of distributed generation and microgrid stability, with a focus on the topology, control architecture, and operational modes of microgrids. It categorizes and analyzes major stability assessment methods under both grid-connected and islanded operating conditions. Furthermore, it explores the development trends of critical control technologies such as virtual synchronous generator control, droop control, and adaptive control, and evaluates stability challenges under scenarios involving high penetration of renewable energy, system disturbances, and dynamic mode transitions. The paper also summarizes the application outcomes and research frontiers of emerging technologies—such as big data analytics, artificial intelligence algorithms, and advanced energy storage systems—in enhancing microgrid stability. Finally, it identifies key scientific problems and core technical bottlenecks that need to be addressed, and proposes research pathways for sustainable development and directions for multidimensional technological integration. This paper aims to provide a comprehensive knowledge framework and frontier insights for scholars and engineers engaged in distributed generation and microgrid stability research, contributing to the development of highly stable and resilient new power systems.

抄録全体を表示

With the global shift toward cleaner and low-carbon energy systems, Multi-Energy Systems (MES)—which integrate electricity, heat, gas, and other energy carriers—are emerging as a key foundation of the new energy paradigm. Due to strong physical and control-layer couplings across subsystems, MES stability involves high complexity and dynamic uncertainty, which limits the applicability of conventional power system stability theories and necessitates methodological innovation. This paper reviews recent advances in MES integrated stability from three perspectives. First, it discusses dynamic modeling approaches, including modular, hybrid physical–cyber, and data-driven methods. Second, it summarizes stability analysis techniques such as small-signal and transient stability, along with multi-timescale coupled modeling and solution methods. Third, it examines coordinated control strategies, including hierarchical control, source–load–network coordination, demand-side response, and intelligent control methods such as reinforcement learning. The roles of big data and artificial intelligence in state awareness, stability assessment, and adaptive control are also highlighted. Key challenges are identified in the depth of theoretical modeling, understanding coupling mechanisms, and managing uncertainty. Finally, future directions—such as multi-scale modeling theories, cross-domain coupling characterization, and robustness-oriented control strategies—are outlined to guide the secure and efficient development of next-generation MES.

抄録全体を表示

With the rapid evolution of power systems toward digitalization, networking, and intelligence, their structural complexity and operational dynamics have significantly increased. Traditional methods that rely on analytical physical models are increasingly constrained by difficulties in modeling, limited real-time capabilities, and poor adaptability in stability analysis and control. In recent years, the widespread deployment of phasor measurement units, intelligent terminals, and various sensors has provided high-dimensional and high-timeliness data support for power system operations, fostering a paradigm shift toward data-driven research methods. Artificial intelligence (AI) technologies—particularly machine learning, deep neural networks, and reinforcement learning—have been extensively explored for key tasks such as stability state identification, dynamic risk prediction, control strategy optimization, and adaptive fault response. This paper presents a comprehensive review of recent advances in the application of AI to power system stability, with a focus on data-driven dynamic stability prediction models, AI-integrated coordinated control strategies, and intelligent decision-making frameworks for disturbance detection and self-healing recovery. It further discusses core challenges in current research, including data quality and completeness, model generalization and robustness, algorithm interpretability, and feasibility of engineering deployment. Finally, the paper proposes key future research directions and potential breakthroughs. This paper aims to provide a systematic reference for advancing both theoretical research and practical implementation of AI technologies in power system stability assurance.

抄録全体を表示

With the deep integration of smart grids and information and communication technologies, power system relay protection is undergoing a fundamental transformation from traditional localized, closed architectures to communication-based, distributed, and collaborative intelligent protection systems. The incorporation of communication technologies has significantly enhanced the real-time performance and accuracy of fault detection, information exchange, and coordinated control, leading to substantial improvements in core functions such as response speed, selectivity, and adaptability. This paper provides a comprehensive review of the key applications and technological evolution of communication technologies in the field of relay protection in recent years, with a focus on the integration patterns and performance characteristics of optical fiber communication, fifth-generation mobile communication, phasor measurement units, and software-defined networking. It further explores the collaborative mechanisms within communication-based distributed relay protection architectures, as well as the research progress and application potential of big data and artificial intelligence in fault identification, adaptive setting, and coordinated decision-making control. In addition, this study analyzes the critical challenges faced by relay protection communication systems in terms of reliability assurance, network security, communication latency control, and standardization, while reviewing key research trends and representative engineering practices both domestically and internationally. Finally, the paper envisions future development trends of relay protection systems toward adaptive, self-healing, and pervasively intelligent coordination. This work aims to provide researchers and practitioners with a comprehensive and systematic overview of technologies and cutting-edge research, serving as a technical reference for building a new generation of highly reliable and intelligent power system protection frameworks.

抄録全体を表示

With the increasing frequency of extreme natural disasters, equipment failures, and malicious attacks, the vulnerability of power systems has become increasingly prominent, making system restoration capability and operational resilience critical topics for ensuring energy security and enhancing system robustness. This paper provides a comprehensive review of recent research progress in power system restoration and resilience analysis, focusing on the evolution of key technical approaches and methodologies, and examining their interdisciplinary integration under the trend of intelligent power systems. First, the paper clarifies the fundamental concepts of resilience and restoration in power systems, analyzes mainstream quantitative indicators, assessment frameworks, and modeling methods, and distinguishes their intrinsic connections and essential differences from traditional performance metrics such as stability, reliability, and risk assessment. It then systematically summarizes current research achievements from perspectives such as restoration optimization scheduling, self-healing control strategies, and resilient network topology design, with particular emphasis on the critical roles of distributed energy resources, microgrid architectures, and multi-agent cooperative control technologies in enhancing power system resilience. Furthermore, the paper explores the frontier applications of emerging technologies—including artificial intelligence, digital twins, and power-communication coordinated defense—in building intelligent resilient grids, and identifies major challenges such as the high complexity of system modeling, the incompleteness of operational data, and the lack of standardized evaluation methods and frameworks. Finally, it outlines future research directions, advocating for the development of dynamic adaptive restoration mechanisms. This paper aims to provide systematic insights for resilience research and engineering practice in power systems, promoting the development of next-generation secure, adaptive, and intelligent power grids.

抄録全体を表示

To address the critical challenges of rapid production decline and low recovery efficiency in the development of shale oil reservoirs in the Chang 7 Member of the Ordos Basin, this study proposes an optimization method for single-well huff and puff development that integrates imbibition and stress sensitivity. A multi-scale coupled numerical simulation framework based on the Embedded Discrete Fracture Model was established to systematically analyze the influence of key parameters—including injection timing, injection rate, shut-in duration, and huff and puff cycle—on production performance. The model fully incorporates the imbibition-driven mechanism within complex fracture networks of shale reservoirs and the dynamic regulation of seepage behavior due to stress sensitivity, enabling high-precision prediction and optimization of the injection process. Results demonstrate that rational parameter design can not only effectively replenish reservoir energy but also enhance oil recovery, with oil recovery improving by 5.1% and the oil-water displacement efficiency reaching 6.8% under optimal conditions. The innovation of this study lies in incorporating the coupled imbibition–stress sensitivity mechanism into the optimization of shale oil injection development parameters, significantly improving model adaptability and predictive accuracy, and providing valuable engineering insights for single-well huff and puff development in continental shale oil reservoirs.

抄録全体を表示

This study focuses on the tight oil reservoirs of the S Oilfield and establishes a systematic research framework encompassing geological modeling, numerical simulation, parameter optimization, and performance evaluation. It investigates the mechanisms by which key engineering parameters—such as injection timing, pressure, volume, rate, and shut-in duration—affect oil recovery during CO₂ huff and puff processes. The results show that when the reservoir pressure coefficient declines to a certain level and the injection pressure approaches the minimum miscibility pressure, the contact efficiency and miscibility between CO₂ and crude oil are significantly enhanced, leading to reduced oil viscosity and improved fluidity, thereby increasing recovery. Through sensitivity analysis, the study identifies optimal parameter combinations suitable for tight reservoirs and, based on the evolution of interfacial tension, proposes a theoretical basis for scientifically determining shut-in time. This research innovatively develops a CO₂ huff and puff parameter optimization model tailored to the characteristics of tight oil reservoirs, clarifies key control mechanisms, and provides theoretical support and practical engineering strategies for the efficient development of CO₂-based tight oil resources.

抄録全体を表示

To address the complexity of mechanisms and the limitations of modeling microbial enhanced oil recovery (MEOR) in heterogeneous oil reservoirs, this study develops a reaction kinetics–flow coupling model that integrates key oil displacement mechanisms, including crude oil viscosity reduction, biopolymer-induced mobility control, and reduction of oil–water interfacial tension. The model systematically characterizes the multiscale interactions between microbial activities and the physical processes of oil reservoirs. Considering the heterogeneity of oil reservoir structures and microbial physiological behaviors, a numerical simulation method was established that is suitable for complex oil reservoir environments. Multi-source experimental data were introduced for parameter inversion and model validation to ensure physical reliability and broad applicability. Simulation results reveal that initial microbial concentration, injection rate, and nutrient ratio exert significant and nonlinear impacts on oil recovery. The innovation of this research lies in the first realization of multi-mechanism coupled dynamic modeling for the MEOR process, the proposal of quantitative characterization methods for key physico-chemical interactions, and the construction of a field-adaptive, efficient oil reservoir simulation platform. This study provides systematic and quantitative technical support for mechanistic understanding, sensitivity analysis, and field engineering optimization of MEOR in oil reservoirs.

抄録全体を表示

Natural gas hydrate, characterized by its high energy density, abundant reserves, and widespread distribution, is regarded as a strategic unconventional natural gas resource with significant development potential. Driven by the accelerating transformation of the global energy structure and the “dual carbon” goals, both fundamental research and engineering development of natural gas hydrate have made continuous progress. This paper systematically reviews the physicochemical properties, geological occurrence conditions, and spatial distribution of major hydrate-bearing regions, with a particular focus on recent advances in key technologies such as geophysical exploration, geochemical analysis, and borehole investigations. In terms of extraction technologies, the theoretical mechanisms, experimental results, and engineering practices of mainstream methods—depressurization, thermal stimulation, and chemical injection—are comprehensively analyzed, along with a summary of critical experiences and technical bottlenecks from representative pilot production projects. The study also examines the latest research on environmental risk identification, monitoring, and control technologies related to geomechanical stability, greenhouse gas leakage, and ecological impacts during hydrate exploitation. Finally, in light of current scientific and technological trends, the paper highlights key scientific challenges and technical obstacles that need to be addressed in intelligent exploration and production, digital twin modeling, green and low-carbon development pathways, and the establishment of commercial evaluation systems. The findings aim to provide theoretical guidance and technical references for the efficient, safe, and sustainable development of natural gas hydrate resources.

抄録全体を表示

Deepwater and ultra-deepwater oil and gas resources have become a vital component of the global energy strategy. As onshore and shallow-water reserves are gradually depleting, exploration and development activities are extending into deeper, more remote, and geologically complex marine areas. To address the technical challenges posed by extreme geological conditions such as high pressure, low temperature, and complex structures, deepwater oil and gas technologies have achieved continuous breakthroughs. In recent years, advancements in high-resolution seismic imaging, intelligent drilling and logging, deepwater production system optimization, and the integrated application of subsea production systems have significantly enhanced exploration and development capabilities. Moreover, the integration of cutting-edge technologies such as artificial intelligence, big data analytics, and digital twins has further improved operational precision and efficiency. Despite these advancements, deepwater development still faces formidable challenges, including the risks of oil and gas leakage, equipment corrosion, construction safety, and environmental protection. Additionally, the global “dual carbon” goals have set higher demands on deepwater oil and gas development, promoting a shift toward intelligent, green, and sustainable practices. Against this backdrop, this paper provides a comprehensive review of the geological characteristics of deepwater oil and gas resources, the current status of key technologies, and the main engineering challenges. It also explores frontier research directions such as intelligent oilfield construction, carbon capture, utilization, and storage, and the integrated development of deepwater oil and gas with renewable energy. This paper aims to summarize the research progress and technical bottlenecks in deepwater oil and gas development, anticipate future trends, and offer theoretical and technical references for achieving efficient, safe, and low-carbon utilization of deepwater resources.

抄録全体を表示

Shale oil, as a crucial component of unconventional hydrocarbon resources, is distinguished by its broad distribution and significant potential, yet geological analysis remains constrained by ultra-low porosity and permeability, pronounced heterogeneity, and structural complexity. The emergence of big data technologies has introduced transformative perspectives and tools to address these challenges. This paper systematically reviews multi-source heterogeneous datasets in shale oil exploration and development—including seismic surveys, well logging, core experiments, and production monitoring—while examining their structural features and quality control requirements. On this basis, it highlights key big data-driven approaches such as data integration and governance, feature extraction and pattern recognition, machine learning-based predictive modeling, and real-time processing with dynamic model updating. Practical applications are summarized in sweet spot identification, quantitative reservoir heterogeneity characterization, intelligent fracture interpretation, and integrated geological–engineering analysis. The paper further discusses core challenges, notably multi-source data fusion and interoperability, model interpretability and physical consistency, the effective incorporation of geological prior knowledge, and interdisciplinary collaboration. Finally, it outlines future research directions and provides systematic theoretical and methodological guidance for the integration of big data with shale oil geological analysis. These efforts aim to foster more intelligent, efficient, and refined development of unconventional petroleum geology.

抄録全体を表示