[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-373":3,"related-373":68},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":63,"slug":66,"view_count":52,"doi":8,"paper":8,"created_at":67},373,"基于多模态时空对齐与因果利润建模的农业投入优化(MAION)","https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994","中国农业大学付正捷、张誉恒等于Sensors发表针对智慧农业投入优化的多模态网络MAION。该框架构建统一的'地块-时间窗'农业状态表示,通过跨模态时空对齐模块解决田间图像、气象环境、土壤状态和田间管理记录之间采样频率不一致、语义尺度异构问题;通过投入-产出因果利润建模模块评估不同投入行为对产量、成本和净利润的潜在影响;并以利润驱动的强化学习生成面向长期净收益最大化的投入策略。在产量、成本和净利润预测上RMSE分别为0.587、0.531和0.648,R2达0.914\u002F0.891\u002F0.883;经济决策中净收益改善17.68%,投入产出比1.71,显著优于随机森林、XGBoost、LSTM、GRU和Transformer等基线。",null,"## 1. Introduction\n\nWith the continuous advancement of smart agriculture, agricultural production is shifting from experience-dependent judgment toward integrated management supported by data, models, and intelligent decision-making [[1](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B1-sensors-26-04994)]. Internet of Things sensors, unmanned aerial vehicle remote sensing, field image acquisition devices, meteorological monitoring systems, and agricultural management platforms have been increasingly deployed in farmland and orchard production scenarios, enabling continuous recording of soil moisture, temperature and humidity, light intensity, rainfall, crop growth status, pest and disease conditions, irrigation and fertilization records, and pesticide application information [[2](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B2-sensors-26-04994)]. These data provide a fine-grained perception basis for precision agriculture and allow crop growth processes and farmland environmental changes to be understood more comprehensively [[3](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B3-sensors-26-04994)]. However, data availability does not necessarily mean that collected data can be directly transformed into effective decisions [[4](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B4-sensors-26-04994)]. In practical production, managers are usually concerned not only with the accurate prediction of a single indicator, but also with how fertilization, irrigation, and pesticide application should be arranged under current crop status, meteorological conditions, and soil background so that input costs can be controlled while yield and quality are maintained [[5](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B5-sensors-26-04994)]. With increasing production costs, tightening resource constraints, and intensifying climate variability, simply pursuing yield maximization is no longer sufficient for modern agricultural management. A more reasonable balance among yield, cost, resource utilization, and net profit has therefore become an important issue in smart agricultural decision-making research [[6](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B6-sensors-26-04994)].\n\nTraditional agricultural management usually relies on farmer experience, expert rules, and statistical analysis models [[7](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B7-sensors-26-04994)]. Experience-driven methods are widely used because of their direct operation and low implementation cost, but their effectiveness depends heavily on personal experience and shows limited adaptability to climate variation, plot heterogeneity, and crop growth-stage changes [[8](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B8-sensors-26-04994)]. Expert systems can provide recommendations for irrigation, fertilization, and pest or disease control according to predefined rules; however, their rule structures are usually fixed and may lack flexibility when complex coupling relationships exist among environmental variables, crop states, and input behaviors. Statistical models and production function models can analyze relationships between agricultural inputs and outputs, but they often rely on linear or static assumptions and are insufficient for describing nonlinear responses, time-lag effects, and stage-dependent differences in agricultural systems [[9](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B9-sensors-26-04994)]. Moreover, many traditional methods still focus on a single production indicator, such as yield, disease incidence, or soil moisture, while the joint relationships among crop status, environmental conditions, input behavior, and economic return are rarely considered. Therefore, traditional methods remain inadequate for multi-source data fusion, dynamic input optimization, and profit-oriented intelligent decision-making [[10](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B10-sensors-26-04994)].\n\nDeep learning has provided a new technical pathway for smart agriculture and has been widely applied to crop recognition, pest and disease detection, yield prediction, quality assessment, and environmental monitoring [[11](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B11-sensors-26-04994)]. Convolutional neural networks can extract crop growth, canopy structure, and disease features from field images and unmanned aerial vehicle remote sensing images, while recurrent neural networks, long short-term memory networks, and Transformer models can process meteorological, soil, and crop growth time-series data. Multimodal learning methods have further attempted to integrate images, sensor data, and management records to improve agricultural state perception and yield prediction [[12](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B12-sensors-26-04994)]. These studies have promoted the transition from manual observation to automated analysis, but limitations remain in input optimization. Several recent studies have explored causal modeling, reinforcement learning, and multimodal learning for agricultural or related complex decision-making tasks. Zhang et al. [[13](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B13-sensors-26-04994)] proposed the CMRL causal meta-reinforcement learning framework, integrating reinforcement learning feedback, causal intervention, and meta-learning optimization for multimodal remote sensing classification, with overall accuracies of\n\n$86.27 \\%$\n,\n\n$95.51 \\%$\n, and\n\n$99.41 \\%$\non the MUUFL, Houston, and Trento datasets, respectively. Liu et al. [[14](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B14-sensors-26-04994)] proposed the ASGO-PAPIS framework, which combined deep learning and causal inference for multidimensional dairy production cost analysis and improved Precision, NDCG, and MAP by up to approximately 5 percentage points. Zhang et al. [[15](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B15-sensors-26-04994)] developed a cross-modal attention and PPO reinforcement learning framework for pesticide application optimization by fusing unmanned aerial vehicle hyperspectral data, soil meteorological data, and pest monitoring data, achieving an RMSE of\n\n$0.162$\n, a spraying accuracy of\n\n$88.3 \\%$\n, an\n\n$18.3 \\%$\nreduction in pesticide usage, and a pest suppression effect of\n\n$77.9 \\%$\n.\n\nAlthough multimodal learning, causal inference, and reinforcement learning have each demonstrated considerable potential for intelligent agricultural management, they address different stages of the decision-making process and therefore exhibit complementary strengths as well as inherent limitations. Multimodal fusion effectively integrates heterogeneous information from crop images, environmental observations, soil conditions, and management records, enabling comprehensive agricultural state perception [[16](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B16-sensors-26-04994)]. However, it primarily models statistical correlations and cannot reliably determine how changes in irrigation, fertilization, or pesticide application causally affect agricultural productivity and economic returns. Causal inference alleviates confounding effects caused by weather variability, soil heterogeneity, and management differences, providing more reliable estimates of intervention effects. Nevertheless, existing causal approaches mainly focus on effect estimation rather than generating optimal sequential management strategies throughout an entire growing season [[17](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B17-sensors-26-04994)]. Reinforcement learning is naturally suitable for optimizing long-term agricultural decisions, yet its performance strongly depends on accurate state representations and reliable reward signals. Inaccurate perception or biased intervention estimation may consequently result in unstable or economically suboptimal policies. Therefore, these three paradigms should be regarded as complementary rather than competing approaches. A unified framework integrating multimodal perception, causal reasoning, and reinforcement learning can simultaneously achieve comprehensive agricultural state representation, reliable intervention effect estimation, and long-term profit-oriented decision optimization.\n\nAccordingly, a multimodal causal reinforcement learning framework for agricultural input–profit optimization, namely the Multimodal Agricultural Input–Output Optimization Network, abbreviated as MAION, is proposed in this study. Visual data, environmental data, soil data, and agricultural management records are used as inputs, while yield, cost, net profit, and optimal input strategies are taken as outputs. An end-to-end modeling method from multi-source agricultural perception to economically optimal decision-making is thereby constructed. Unlike models that focus only on yield prediction or state recognition, MAION incorporates agricultural input behavior, production cost, and economic return into a unified learning objective. Through cross-modal spatiotemporal alignment, causal input–profit modeling, and profit-driven reinforcement learning decision-making, agricultural intelligent perception is connected with practical production decisions, thereby providing an executable modeling strategy for precision input, cost control, and net profit improvement. The main contributions of this study are summarized as follows:\n\n*   To address the lack of unified agricultural state representation caused by heterogeneous data sources with inconsistent temporal and semantic characteristics, a unified multimodal agricultural input–output modeling framework is developed to support profit-oriented decision making.\n\n*   To address the spatiotemporal inconsistency among crop images, environmental observations, soil measurements, and management records, a cross-modal spatiotemporal alignment strategy is introduced to establish consistent multimodal agricultural representations.\n\n*   To address the inability of existing predictive models to distinguish causal intervention effects from statistical correlations, a causal-aware input–profit modeling mechanism is developed to provide more reliable estimation of the economic effects of agricultural management actions.\n\n*   To address the limitation of conventional optimization methods in achieving long-term economic management, a profit-driven reinforcement learning strategy is designed to optimize sequential agricultural input decisions under long-term profit objectives.\n\n*   To address the challenge of robust deployment in practical agricultural environments, comprehensive cross-plot, cross-year, and missing-modality experiments are conducted to validate the generalization capability and practical effectiveness of the proposed framework.\n\n## 2. Related Work\n\n### 2.1. Multimodal Perception Methods in Smart Agriculture\n\nMultimodal perception in smart agriculture refers to the continuous observation and integrated representation of agricultural production systems using heterogeneous data sources, including images, sensors, remote sensing, and management records [[18](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B18-sensors-26-04994)]. Although these data differ in acquisition frequency, spatial coverage, and semantic level, they jointly provide important information for agricultural state perception [[19](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B19-sensors-26-04994)]. Therefore, multimodal perception is valuable not only because more data types are introduced, but also because complementary information from different sources can be used to identify crop growth status, environmental changes, and production risks more reliably [[20](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B20-sensors-26-04994)]. Image-based agricultural perception methods have been widely studied [[21](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B21-sensors-26-04994)]. Convolutional neural networks can automatically extract texture, color, edge, and morphological features from crop images, and have been applied to disease recognition, fruit detection, weed identification, and quality grading [[22](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B22-sensors-26-04994)]. Vision Transformers further improve the representation of long-range regional dependencies and complex background information, thereby enhancing adaptability under occlusion, illumination variation, and scale differences in field environments [[23](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B23-sensors-26-04994)]. Sensor-based time-series data are also important for greenhouse control, soil moisture monitoring, and crop growth trend analysis, where continuous environmental variables need to be modeled dynamically [[24](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B24-sensors-26-04994)]. Long short term memory (LSTM), gated recurrent unit (GRU), and Transformer models have been adopted to capture long-term dependencies among meteorological variables, soil variables, and growth indicators [[25](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B25-sensors-26-04994)]. Remote sensing methods are more commonly used for regional growth estimation, drought monitoring, and yield assessment through spectral features, vegetation indices, and spatial textures [[26](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B26-sensors-26-04994)]. Despite these advances, most existing studies remain centered on a single modality or a single task [[27](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B27-sensors-26-04994)]. Image models usually focus on disease categories, fruit numbers, or phenotypic traits; sensor models are mainly used for environmental trend prediction or soil state estimation; and remote sensing models emphasize regional crop growth variation [[28](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B28-sensors-26-04994)]. Such fragmented strategies are effective for specific tasks, but they are insufficient for describing the coupled relationships among crops, environments, soils, and management behaviors [[29](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B29-sensors-26-04994)]. For agricultural input–profit optimization, crop growth status or environmental risk alone is not enough; it is also necessary to understand how these states influence fertilization, irrigation, and pesticide application, and how such behaviors are ultimately reflected in yield, cost, and net profit [[30](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B30-sensors-26-04994)]. Accordingly, limitations remain in cross-modal spatiotemporal alignment, unified state representation, and feature fusion oriented toward economic decision-making [[31](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B31-sensors-26-04994),[32](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B32-sensors-26-04994)].\n\n### 2.2. Agricultural Yield Prediction and Input Modeling Methods\n\nAgricultural yield prediction and input modeling aim to estimate crop production by modeling the relationships among environmental conditions, soil properties, management practices, and historical crop growth states [[33](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B33-sensors-26-04994)]. Early studies mainly relied on statistical regression, crop growth models, and production function models to quantify the effects of climate, soil, irrigation, and fertilization on yield [[34](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B34-sensors-26-04994),[35](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B35-sensors-26-04994)]. Although these methods are interpretable, they have limited ability to capture the nonlinear and dynamic interactions among meteorological conditions, soil characteristics, crop varieties, pests, and management practices that jointly determine agricultural production [[36](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B36-sensors-26-04994)]. Recent studies have introduced machine learning and deep learning methods to improve yield modeling [[37](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B37-sensors-26-04994)]. Tree-based models such as Random Forest and XGBoost, together with support vector machines, have demonstrated robust performance on structured agricultural data [[38](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B38-sensors-26-04994)], while sequential models including LSTM, GRU, and Transformer further improve the modeling of temporal dependencies and long-term environmental effects from multi-source observations [[39](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B39-sensors-26-04994),[40](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B40-sensors-26-04994)]. These advances have substantially improved prediction accuracy for agricultural production. However, existing studies remain primarily prediction-oriented. Most methods optimize yield without explicitly considering production costs or economic returns, despite the fact that maximizing yield does not necessarily maximize profit [[41](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B41-sensors-26-04994),[42](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B42-sensors-26-04994)]. In addition, current models generally learn statistical correlations between agricultural inputs and outputs rather than identifying the underlying causal relationships, making them vulnerable to confounding factors such as weather, soil conditions, and management differences [[43](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B43-sensors-26-04994)]. Consequently, they provide limited support for reliable input optimization [[44](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B44-sensors-26-04994)]. To address these limitations, the proposed causal-aware input–profit modeling module treats fertilization, irrigation, and pesticide application as intervenable variables, jointly estimating their effects on yield, cost, and profit from multimodal agricultural state representations, thereby extending agricultural modeling from prediction toward interpretable decision-oriented optimization [[45](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B45-sensors-26-04994)].\n\n### 2.3. Agricultural Economic Optimization and Intelligent Decision-Making Methods\n\nAgricultural economic optimization aims to allocate land, water, fertilizer, pesticides, labor, and other production resources to balance yield, quality, cost, and profit under resource constraints [[46](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B46-sensors-26-04994)]. Traditional approaches mainly rely on production functions, cost–benefit analysis, and input–output efficiency evaluation to quantify the economic effects of agricultural inputs and support production planning [[47](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B47-sensors-26-04994),[48](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B48-sensors-26-04994)]. Although these methods provide clear economic interpretations, they generally assume relatively stable environmental conditions and fixed input–output relationships, making them difficult to apply to real agricultural systems where weather, market conditions, and crop responses vary continuously across growth stages [[49](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B49-sensors-26-04994)]. Consequently, agricultural input optimization is increasingly regarded as a dynamic sequential decision-making problem rather than a static optimization task [[50](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B50-sensors-26-04994)]. Reinforcement learning (RL) provides an effective framework for learning long-term agricultural management strategies by optimizing cumulative rewards through continuous interactions with the environment [[51](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B51-sensors-26-04994),[52](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B52-sensors-26-04994)]. Existing studies formulate crop status, soil conditions, meteorological observations, and historical management records as states [[53](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B53-sensors-26-04994)], while irrigation, fertilization, and pesticide application are treated as actions, enabling optimization of long-term objectives such as yield, quality, resource consumption, and economic return [[54](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B54-sensors-26-04994)]. Compared with prediction-based approaches, RL is better suited to sta","Sensors 2026-08-06","2026-08-06T00:00:00Z","论文",10,false,67,{"impact":17,"substance":18,"depth":19,"authority":17,"freshness":20,"relevant":21,"comment":22},12,20,18,5,1,"论文提出多模态时空对齐与因果利润建模的农业投入优化方法，具有创新性，但影响范围限于学术研究，时效性一般。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","中国农业大学","多模态","强化学习","Sensors",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":47},[44,51,57],{"code":45,"score":46,"supported":47,"title":48,"abstract":49,"tags":50},"I1",4,true,[],[26],[26],{"code":32,"score":52,"supported":47,"title":53,"abstract":54,"tags":56},3,[],[55],"土壤",[],{"code":58,"score":59,"supported":14,"title":60,"abstract":61,"tags":62},"I2",2,[],[],[28,29],[64,65],"中国农业大学 强化学习 智慧农业 多模态","中国农业大学 强化学习","中国农业大学强化学习智慧农业多模态-373","2026-08-10T23:54:46.189166Z",{"total":69,"page":21,"page_size":69,"items":70},6,[71,142,234,304,414,497],{"id":72,"title":73,"url":74,"summary":75,"summary_zh":76,"content":8,"source_name":77,"source_url":74,"published_at":78,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":79,"score_detail":80,"sources":85,"tags":87,"primary_topic":92,"secondary_topics":93,"classification":99,"search_phrases":119,"slug":122,"view_count":123,"doi":124,"paper":125,"created_at":141},5583,"Active-Labeling Evaluation for Computer Agriculture Nematode-Cyst Detection Under Sparse Soil-Sample Ground Truth: An Artificial Intelligence Annotation-Efficiency Bound","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544145","Active learning promises to reduce the annotation burden of training nematode-cyst detection models for precision agriculture, but the size of that reduction is not known when ground truth comes from sparse soil samples rather than exhaustive visual inspection. the present analysis derives an annotation-efficiency bound for pool-based active learning under sparse soil-sample ground truth. The detection task is formalised as a two-stage process in which a classifier selects candidate cysts from soil imagery and a laboratory assay confirms a small labelled subset. Under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64, the bound is evaluated across a design grid of 8, 16, 24 and 32 clusters and effect sizes of 3, 5 and 8 percentage points, with 2000 replications per cell. The annotation-efficiency gain is bounded by the ratio of label noise to cluster-level variance, and that 52 clusters are required to detect a 5-percentage-point improvement at 80% power. The bound provides a design rule for allocating annotation effort between active selection and confirmatory soil sampling.","主动学习有望减轻精准农业中训练线虫囊检测模型所需的标注负担，但当真实标签来自稀疏土壤样本而非详尽的视觉检查时，这种负担减轻的幅度尚不清楚。本分析推导了在稀疏土壤样本真实标签下基于池的主动学习的标注效率界限。检测任务被形式化为两阶段过程：分类器从土壤图像中筛选候选线虫囊，实验室检测确认一个小的已标注子集。在设定的方差结构下——组间标准差为6.0、残差标准差为4.5、组内相关系数为0.64——该界限在8、16、24和32个簇的设计网格以及3、5和8个百分点的效应量下进行评估，每个单元格重复2000次。标注效率增益受标签噪声与簇级方差之比的约束，并且在80%检验功效下检测5个百分点的改进需要52个簇。该界限为在主动选择与验证性土壤采样之间分配标注工作量提供了设计规则。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",64,{"impact":81,"substance":18,"depth":82,"authority":83,"freshness":13,"relevant":21,"comment":84},8,17,9,"该研究给出稀疏土壤样本下主动学习标注效率的理论边界与聚类设计规则，方法新颖、结论具体，但属细分方法学研究，产业影响有限，适合作为专业精选而非头条。",[86],{"name":77,"url":74},[26,88,89,90,91],"农业人工智能","主动学习","线虫检测","土壤采样",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[94],{"code":58,"slug":95,"name":96,"path":97,"parent_code":98},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":39,"locked":14,"version":40,"method":41,"evidence":100},{"candidates":101,"agricultural_evidence":47},[102,107,112],{"code":32,"score":103,"supported":47,"title":104,"abstract":105,"tags":106},14,[33],[55,33],[],{"code":58,"score":83,"supported":47,"title":108,"abstract":110,"tags":111},[109],"artificial intelligence",[],[88],{"code":45,"score":113,"supported":47,"title":114,"abstract":115,"tags":118},7,[],[116,117],"精准农业","precision agriculture",[26],[120,121],"线虫孢囊 检测 主动学习","稀疏土壤样本 标注效率","线虫孢囊检测主动学习-5583",0,"10.5281\u002Fzenodo.23544145",{"doi":124,"openalex_id":126,"authors":127,"venue":77,"cited_by_count":123,"oa_url":74,"card":134,"direction":138,"ingested_from":140},"W7223082195",[128,130,132],{"name":129,"orcid":8},"Amine Ben Salah",{"name":131,"orcid":8},"Ines Trabelsi",{"name":133,"orcid":8},"Mohamed Aziz Khelifi",{"tldr":135,"method":136,"finding":137,"direction":138,"opportunity":139},"推导稀疏土壤样本真值下主动学习标注效率的理论上界。","基于方差结构与设计网格的统计模拟，2000次重复。","标注效率增益受标签噪声与簇间方差之比限制，检测5个百分点提升需52簇。","农业人工智能与决策模型","可将该上界推广到其他稀疏真值农业检测任务，并探索主动选择与确认采样的最优分配策略。","openalex","2026-10-22T11:20:58.901747Z",{"id":143,"title":144,"url":145,"summary":146,"summary_zh":147,"content":8,"source_name":148,"source_url":145,"published_at":78,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":149,"score_detail":150,"sources":155,"tags":157,"primary_topic":162,"secondary_topics":168,"classification":171,"search_phrases":209,"slug":212,"view_count":123,"doi":213,"paper":214,"created_at":233},5558,"Estimation of Soil Water Content in Winter Wheat Field at Jointing Stage Using Multi-Source Features and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202071","Accurate and timely monitoring of soil water content (SWC) plays an essential supporting role in crop irrigation management and smart agricultural practice. Remote sensing technology provides rapid and convenient approaches to large-scale farmland SWC estimation or inversion. However, existing mechanistic modeling methods are limited by parameter localization and land surface heterogeneity, while machine learning data-driven methods lack quite good physical interpretability. To address deficiencies in single data-driven methods and single vegetation microwave scattering models, and explore the estimation effect of different feature variables in machine learning. This study proposes an innovative estimation model that integrates machine learning strategies and multi-source features, including spectral indices and features derived from the classic water cloud model (WCM). The novelty of the proposed model lies in balancing physical interpretability and data-driven accuracy, namely extracting relevant soil backscattering parameters through WCM, which are then used as input features in the machine learning. A combination of field-measured data and unmanned aerial vehicle (UAV) multi-source remote sensing data, including multispectral and synthetic aperture radar (SAR) data, was acquired synchronously at the jointing stage of winter wheat. Through extracting variables such as the SAR microwave backscattering coefficient and the optical vegetation index, and conducting feature screening and parameter sensitivity analysis, we optimized the input variable sets of models based on back-propagation (BP) neural network, support vector regression (SVR) and random forest (RF) algorithms. The study results showed that the established estimation model had excellent estimation performance, especially for the RF algorithm, with the highest R2 of 0.855, lowest MAE of 0.0212 cm3\u002Fcm3, and lowest RMSE of 0.0253 cm3\u002Fcm3. It was also shown that different feature input schemes have obvious effects on SWC estimation performance. On the whole, RF had the best estimation accuracy, followed by SVR and then BPNN. This study demonstrated that models integrating multi-source remote sensing data and machine learning could enhance SWC estimation ability for winter wheat fields, and could also serve as a promising approach for SWC monitoring in winter wheat fields in the North China Plain.","准确、及时地监测土壤含水量（SWC）对作物灌溉管理和智慧农业实践具有重要的支撑作用。遥感技术为大规模农田土壤含水量估算或反演提供了快速便捷的手段。然而，现有机理建模方法受参数本地化和地表异质性限制，机器学习数据驱动方法则缺乏良好的物理解释性。针对单一数据驱动方法和单一植被微波散射模型的不足，并探究不同特征变量在机器学习中的估算效果，本研究提出了一种融合机器学习策略与多源特征的创新估算模型，所采用特征包括光谱指数和经典水云模型（WCM）衍生的特征。该模型的新颖性在于平衡物理解释性与数据驱动精度，即通过WCM提取相关土壤后向散射参数，再将其作为机器学习的输入特征。研究在冬小麦拔节期同步获取了田间实测数据与无人机（UAV）多源遥感数据，包括多光谱和合成孔径雷达（SAR）数据。通过提取SAR微波后向散射系数和光学植被指数等变量，并进行特征筛选和参数敏感性分析，优化了基于反向传播（BP）神经网络、支持向量回归（SVR）和随机森林（RF）算法的模型输入变量集。研究结果表明，所建立的估算模型具有优良的估算性能，尤其是RF算法，最高R²为0.855，最低MAE为0.0212 cm³\u002Fcm³，最低RMSE为0.0253 cm³\u002Fcm³。研究还表明，不同特征输入方案对土壤含水量估算性能有明显影响。总体而言，RF估算精度最佳，SVR次之，BPNN再次之。本研究证明，融合多源遥感数据与机器学习的模型能够提升冬小麦田土壤含水量估算能力，也可为华北平原冬小麦田土壤含水量监测提供一种有前景的方法。","Agronomy",77,{"impact":151,"substance":152,"depth":82,"authority":153,"freshness":13,"relevant":21,"comment":154},16,21,13,"该研究融合多源遥感与机器学习估算冬小麦拔节期土壤含水量，方法有创新、结论可靠，对智慧灌溉有参考价值，但属细分领域论文，影响范围有限。",[156],{"name":148,"url":145},[26,158,159,160,161],"机器学习","遥感监测","土壤墒情","冬小麦",{"code":163,"slug":164,"name":165,"path":166,"parent_code":167},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[169,170],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":58,"slug":95,"name":96,"path":97,"parent_code":98},{"status":39,"locked":14,"version":40,"method":41,"evidence":172},{"candidates":173,"agricultural_evidence":47},[174,180,185,190,198,205],{"code":163,"score":175,"supported":47,"title":176,"abstract":178,"tags":179},26,[177,164],"winter wheat",[165,177,164],[161],{"code":32,"score":181,"supported":47,"title":182,"abstract":183,"tags":184},15,[33],[55,33],[160],{"code":58,"score":181,"supported":47,"title":186,"abstract":188,"tags":189},[187],"machine learning",[158,187],[158],{"code":191,"score":13,"supported":47,"title":192,"abstract":193,"tags":197},"I3",[],[194,195,196],"遥感","remote sensing","multispectral",[159],{"code":199,"score":69,"supported":47,"title":200,"abstract":201,"tags":204},"H3",[],[202,203],"灌溉","irrigation",[],{"code":45,"score":46,"supported":47,"title":206,"abstract":207,"tags":208},[],[26],[26],[210,211],"冬小麦 土壤含水量 遥感","多源遥感 机器学习 墒情","冬小麦土壤含水量遥感-5558","10.3390\u002Fagronomy16202071",{"doi":213,"openalex_id":215,"authors":216,"venue":148,"cited_by_count":123,"oa_url":145,"card":226,"direction":232,"ingested_from":140},"W7223156204",[217,220,222,224],{"name":218,"orcid":219},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":221,"orcid":8},"Yi Zhang",{"name":223,"orcid":8},"WEI Lei",{"name":225,"orcid":8},"Chengcai Zhang",{"tldr":227,"method":228,"finding":229,"direction":230,"opportunity":231},"融合WCM物理特征与多源遥感，用机器学习估算冬小麦拔节期土壤含水量。","无人机多光谱与SAR数据，WCM参数+光谱指数，BP\u002FSVR\u002FRF建模。","RF最优，R²达0.855，RMSE为0.0253 cm³\u002Fcm³，特征方案影响显著。","农业遥感与作物表型","可探索物理约束与深度学习耦合，并迁移至多生育期、多作物及不同土壤质地验证。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:18.887301Z",{"id":235,"title":236,"url":237,"summary":238,"summary_zh":239,"content":8,"source_name":240,"source_url":237,"published_at":241,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":242,"score_detail":243,"sources":245,"tags":247,"primary_topic":252,"secondary_topics":253,"classification":254,"search_phrases":281,"slug":284,"view_count":123,"doi":285,"paper":286,"created_at":303},5389,"A Wideband Flexible Waterproof Antenna for Internet of Underground Things: Design, Characterization, and Field Validation","https:\u002F\u002Fdoi.org\u002F10.3390\u002Felectronics15204815","The Internet of Underground Things (IoUT) is seen as a new technology that could revolutionize soil management, improving irrigation efficiency, soil and plant health, and food safety using reliable and resilient wireless connectivity. Rapid deployment of IoUT in precision agriculture requires flexible, waterproof antennas specifically designed for operation in soil. This study introduces a methodology for the design and characterization of waterproof, flexible antennas that maintain robust performance in soil across varying gravimetric water contents (GWC). Applying this methodology, a wideband, waterproof, and flexible antenna was designed and fabricated. Its parameters and characteristics were evaluated numerically and experimentally in soils with different GWCs to determine its suitability for IoUT applications. Within the GWC range of 10% to 20%, which is optimal for supporting plant health and water use, the antenna demonstrates a wide bandwidth of 0.6 to 1.8 GHz (|S11| \u003C −10 dB) and radiation efficiency ranging from 3.56% to 0.15% at 868 MHz. Experimental results obtained in free space, dry sand, and garden soil agree reasonably well with simulation predictions, showing that the proposed antenna is suitable for IoUT applications. Field validation demonstrated that the antenna prototype maintained its impedance response after two months of in-soil operation, indicating stable performance over the evaluated period.","地下物联网（Internet of Underground Things, IoUT）被视为一项可能彻底改变土壤管理的新技术，通过可靠且具有韧性的无线连接提升灌溉效率、土壤与植物健康以及食品安全。在精准农业中快速部署IoUT需要专为土壤环境运行而设计的柔性防水天线。本研究提出了一种防水柔性天线的设计与表征方法，使天线在不同重量含水率（gravimetric water content, GWC）的土壤中保持稳健性能。应用该方法，设计并制作了一款宽带防水柔性天线。在不同GWC的土壤中对其参数与特性进行了数值仿真与实验评估，以确定其用于IoUT应用的适用性。在10%至20%的GWC范围内（该范围最有利于维持植物健康与水分利用），天线在868 MHz处展现出0.6至1.8 GHz的宽带宽（|S11| \u003C −10 dB）以及3.56%至0.15%的辐射效率。在自由空间、干沙和花园土壤中获得的实验结果与仿真预测吻合良好，表明所提出的天线适用于IoUT应用。现场验证表明，天线原型在土壤中运行两个月后仍保持其阻抗响应，表明在所评估时段内性能稳定。","Electronics","2026-10-19T00:00:00Z",70,{"impact":17,"substance":18,"depth":82,"authority":153,"freshness":81,"relevant":21,"comment":244},"面向地下物联网的柔性防水天线设计与田间验证，方法新颖、数据扎实，对精准农业无线感知有参考价值，但属细分技术进展，公共影响有限。",[246],{"name":240,"url":237},[26,248,249,250,251],"物联网","土壤水分","地下物联网","柔性天线",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":255},{"candidates":256,"agricultural_evidence":47},[257,261,265,272,276],{"code":32,"score":113,"supported":47,"title":258,"abstract":259,"tags":260},[],[55,33],[249],{"code":45,"score":113,"supported":47,"title":262,"abstract":263,"tags":264},[],[116,117],[26],{"code":266,"score":69,"supported":47,"title":267,"abstract":268,"tags":271},"E4",[],[269,270],"食品安全","food safety",[],{"code":199,"score":69,"supported":47,"title":273,"abstract":274,"tags":275},[],[202,203],[],{"code":277,"score":46,"supported":47,"title":278,"abstract":279,"tags":280},"I5",[],[248],[248],[282,283],"IoUT 柔性防水天线","地下物联网 土壤水分","IoUT柔性防水天线-5389","10.3390\u002Felectronics15204815",{"doi":285,"openalex_id":287,"authors":288,"venue":240,"cited_by_count":123,"oa_url":237,"card":298,"direction":232,"ingested_from":140},"W7222978032",[289,292,295],{"name":290,"orcid":291},"Nikolay Todorov Atanasov","https:\u002F\u002Forcid.org\u002F0000-0002-7707-0133",{"name":293,"orcid":294},"Blagovest Nikolaev Atanasov","https:\u002F\u002Forcid.org\u002F0009-0001-0145-5619",{"name":296,"orcid":297},"Gabriela Lachezarova Atanasova","https:\u002F\u002Forcid.org\u002F0000-0002-7177-8317",{"tldr":299,"method":300,"finding":301,"direction":232,"opportunity":302},"设计并验证了一款用于地下物联网的宽带柔性防水天线。","采用数值仿真与实验测试，在不同含水率土壤中评估天线性能。","在10%-20%含水率下带宽0.6-1.8GHz，埋土两个月阻抗响应稳定。","可探索天线辐射效率随土壤含水率下降的补偿机制，或结合土壤传感节点做长期田间组网验证。","2026-10-20T23:30:13.823825Z",{"id":305,"title":306,"url":307,"summary":308,"summary_zh":309,"content":8,"source_name":310,"source_url":307,"published_at":311,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":312,"score_detail":313,"sources":315,"tags":317,"primary_topic":322,"secondary_topics":323,"classification":324,"search_phrases":385,"slug":388,"view_count":52,"doi":389,"paper":390,"created_at":413},5081,"Nanobubble-Driven Precision Aeration: Deciphering Abiotic Hypoxia Responses via Multi-Omics for Next-Generation Smart Agriculture","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fantiox15101332","Soil salinity and drought can restrict oxygen availability in the root zone, adding hypoxic stress to the ionic, osmotic, and hydraulic constraints experienced by crops. Nanobubble (NB) water offers a chemical-free approach for delivering highly dispersed oxygen and sustaining dissolved oxygen during irrigation. This review connects the physicochemical behavior of NBs with plant responses to salinity- and drought-associated hypoxia. It examines restoration of aerobic respiration and ATP homeostasis, modulation of ethylene response factor group VII and hypoxia-responsive gene signaling, recovery of ion transport and aquaporin function, redox regulation, hormonal cross-talk, and rhizosphere microbiome responses. Evidence from rice, maize, wheat, cotton, and controlled-environment systems is evaluated alongside opportunities for nanoparticle co-delivery, nanofertilizers, seed priming, and sensor-guided irrigation. The review also outlines how transcriptomics, proteomics, metabolomics, epigenomics, ionomics, and phenomics can resolve NB-mediated mechanisms across the plant–soil continuum. Current evidence supports NB irrigation as a promising precision-aeration platform, but field-scale validation, standardized NB characterization, dose–response studies, energy and cost assessments, and long-term environmental safety analyses remain necessary before broad agricultural deployment.","土壤盐渍化和干旱会限制根区氧气供应，在作物已承受的离子、渗透和水力胁迫之外，进一步叠加低氧胁迫。纳米气泡（NB）水提供了一种无需化学添加的方式，可输送高度分散的氧气并在灌溉过程中维持溶解氧水平。本文综述将纳米气泡的物理化学行为与植物对盐渍化和干旱相关低氧的响应联系起来，考察有氧呼吸和ATP稳态的恢复、乙烯响应因子第VII组及低氧响应基因信号的调控、离子转运和水通道蛋白功能的恢复、氧化还原调节、激素互作以及根际微生物组响应。文章评估了来自水稻、玉米、小麦、棉花及受控环境系统的证据，并探讨了纳米颗粒共递送、纳米肥料、种子引发和传感器引导灌溉的应用机会。综述还概述了转录组学、蛋白质组学、代谢组学、表观基因组学、离子组学和表型组学如何解析纳米气泡在植物–土壤连续体中的介导机制。当前证据支持纳米气泡灌溉作为一种有前景的精准增氧平台，但在广泛农业应用之前，仍需进行田间规模验证、标准化纳米气泡表征、剂量–响应研究、能耗与成本评估以及长期环境安全性分析。","Antioxidants","2026-10-15T00:00:00Z",80,{"impact":19,"substance":152,"depth":19,"authority":103,"freshness":83,"relevant":21,"comment":314},"综述系统梳理纳米气泡增氧缓解盐旱缺氧胁迫的机制与多组学解析路径，学术价值高但尚处田间验证前阶段，属细分领域前沿进展。",[316],{"name":310,"url":307},[26,318,319,320,321],"精准灌溉","多组学","土壤盐渍化","纳米气泡",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":325},{"candidates":326,"agricultural_evidence":47},[327,333,338,342,349,353,360,367,374,380],{"code":32,"score":83,"supported":47,"title":328,"abstract":329,"tags":332},[],[55,330,33,331],"根际","rhizosphere",[],{"code":45,"score":83,"supported":47,"title":334,"abstract":336,"tags":337},[335],"smart agriculture",[],[26],{"code":199,"score":113,"supported":47,"title":339,"abstract":340,"tags":341},[],[202,203],[318],{"code":343,"score":69,"supported":47,"title":344,"abstract":345,"tags":348},"A1",[],[346,347],"水稻","rice",[],{"code":163,"score":69,"supported":47,"title":350,"abstract":351,"tags":352},[],[165,164],[],{"code":354,"score":69,"supported":47,"title":355,"abstract":356,"tags":359},"A3",[],[357,358],"玉米","maize",[],{"code":361,"score":69,"supported":47,"title":362,"abstract":363,"tags":366},"A6",[],[364,365],"棉花","cotton",[],{"code":368,"score":69,"supported":47,"title":369,"abstract":370,"tags":373},"H7",[],[371,372],"干旱","drought",[],{"code":375,"score":52,"supported":47,"title":376,"abstract":377,"tags":379},"F3",[],[378],"肥料",[],{"code":381,"score":21,"supported":14,"title":382,"abstract":383,"tags":384},"F2",[],[],[319],[386,387],"纳米气泡 灌溉 增氧","盐碱地 缺氧 多组学","纳米气泡灌溉增氧-5081","10.3390\u002Fantiox15101332",{"doi":389,"openalex_id":391,"authors":392,"venue":310,"cited_by_count":123,"oa_url":307,"card":408,"direction":232,"ingested_from":140},"W7222342675",[393,396,399,402,405],{"name":394,"orcid":395},"Hafiz Abdul Kareem","https:\u002F\u002Forcid.org\u002F0000-0002-8209-0446",{"name":397,"orcid":398},"Sana Saleem","https:\u002F\u002Forcid.org\u002F0000-0001-9836-2744",{"name":400,"orcid":401},"Muhammad Bilal Hafeez","https:\u002F\u002Forcid.org\u002F0000-0001-6719-6667",{"name":403,"orcid":404},"Naeem Ahmad","https:\u002F\u002Forcid.org\u002F0000-0002-5023-8362",{"name":406,"orcid":407},"Da‐Chuan Yin","https:\u002F\u002Forcid.org\u002F0000-0003-2161-5867",{"tldr":409,"method":410,"finding":411,"direction":232,"opportunity":412},"综述纳米气泡灌溉缓解盐旱根区缺氧的机制，并展望多组学与智能农业应用。","综述多组学（转录\u002F蛋白\u002F代谢\u002F表型等）与纳米气泡水灌溉证据。","纳米气泡灌溉可恢复呼吸与离子稳态，但田间验证与标准仍缺乏。","可研究纳米气泡剂量-响应与传感器引导灌溉闭环，结合多组学解析根际机制。","2026-10-16T23:30:09.487745Z",{"id":415,"title":416,"url":417,"summary":418,"summary_zh":419,"content":8,"source_name":420,"source_url":417,"published_at":421,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":422,"score_detail":423,"sources":425,"tags":427,"primary_topic":430,"secondary_topics":434,"classification":441,"search_phrases":482,"slug":485,"view_count":59,"doi":8,"paper":486,"created_at":496},5013,"REMOTE SENSING AND GIS-BASED ASSESSMENT OF SOIL SALINITY IN IRRIGATED LANDS: METHODS, CHALLENGES AND PROSPECTS FOR PRECISION AGRICULTURE","http:\u002F\u002Fwww.arabianjournalofscience.com\u002Findex.php\u002Findex\u002Farticle\u002Fview\u002F1223","Soil salinization is a major land degradation process affecting the sustainability of irrigated agriculture, particularly in arid and semi-arid regions. Conventional soil sampling provides essential information about salinity levels but may be insufficient for continuous monitoring of large agricultural territories because of spatial variability, sampling costs, and temporal limitations. Remote sensing (RS) and geographic information systems (GIS) offer complementary approaches for identifying spatial patterns of salinity, monitoring land conditions, and supporting agricultural management. This article examines the scientific and methodological foundations of integrating multispectral satellite imagery, spectral indices, geospatial analysis, and machine learning for soil salinity assessment in irrigated lands. Particular attention is given to Landsat and Sentinel-2 imagery, the interpretation of vegetation and soil reflectance indicators, the role of electrical conductivity measurements in model calibration, and the limitations associated with vegetation cover, soil moisture, and seasonal variability. The analysis indicates that reliable salinity assessment requires the integration of satellite observations with field measurements and environmental variables rather than the isolated application of spectral indices. The article proposes a methodological framework for developing spatially explicit salinity assessment systems applicable to irrigated agricultural landscapes, including those of Central Asia. The framework provides a basis for improving monitoring strategies and supporting evidence-based land management without assuming unverified local measurement results.","土壤盐渍化是影响灌溉农业可持续性的主要土地退化过程，在干旱和半干旱地区尤为突出。传统土壤采样可提供盐分水平的基本信息，但由于空间变异性、采样成本和时间限制，可能不足以对大面积农业区域进行持续监测。遥感（RS）和地理信息系统（GIS）为识别盐渍化空间格局、监测土地状况和支持农业管理提供了互补性方法。本文探讨了整合多光谱卫星影像、光谱指数、地理空间分析和机器学习进行灌溉土地土壤盐渍化评估的科学与方法学基础。文章特别关注Landsat和Sentinel-2影像、植被与土壤反射率指标的解译、电导率测量在模型校准中的作用，以及与植被覆盖、土壤湿度和季节变异性相关的局限性。分析表明，可靠的盐渍化评估需要将卫星观测与野外测量和环境变量相结合，而非孤立地应用光谱指数。本文提出了一个方法学框架，用于开发适用于灌溉农业景观（包括中亚地区）的空间显式盐渍化评估系统。该框架为改进监测策略和支持基于证据的土地管理提供了基础，且不以未经核实的当地测量结果为假设前提。","Arabian journal of science.","2026-10-13T00:00:00Z",74,{"impact":151,"substance":18,"depth":82,"authority":153,"freshness":81,"relevant":21,"comment":424},"系统综述遥感与GIS在灌溉农田盐渍化评估中的方法框架与挑战，对盐碱地治理和精准农业有参考价值，但属综述性论文，非突破性成果。",[426],{"name":420,"url":417},[26,116,194,428,429],"盐碱地治理","土壤监测",{"code":191,"slug":431,"name":432,"path":433,"parent_code":98},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[435,440],{"code":436,"slug":437,"name":438,"path":439,"parent_code":98},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":442},{"candidates":443,"agricultural_evidence":47},[444,448,456,460,464,468,472,476],{"code":191,"score":19,"supported":47,"title":445,"abstract":446,"tags":447},[195],[194,195,196],[194],{"code":436,"score":82,"supported":47,"title":449,"abstract":451,"tags":455},[450],"GIS",[452,453,450,454],"地理信息","空间分析","geographic information",[],{"code":32,"score":181,"supported":47,"title":457,"abstract":458,"tags":459},[33],[55,33],[428],{"code":45,"score":13,"supported":47,"title":461,"abstract":462,"tags":463},[117],[],[26,116],{"code":58,"score":69,"supported":47,"title":465,"abstract":466,"tags":467},[],[158,187],[],{"code":199,"score":52,"supported":47,"title":469,"abstract":470,"tags":471},[],[202],[],{"code":368,"score":52,"supported":47,"title":473,"abstract":474,"tags":475},[],[371],[],{"code":477,"score":52,"supported":47,"title":478,"abstract":479,"tags":481},"I7",[],[480],"methodological framework",[],[483,484],"遥感 GIS 土壤盐渍化","Landsat Sentinel-2 盐分监测","遥感GIS土壤盐渍化-5013",{"doi":8,"openalex_id":487,"authors":488,"venue":420,"cited_by_count":123,"oa_url":417,"card":491,"direction":230,"ingested_from":140},"W7221843179",[489],{"name":490,"orcid":8},"Sadullayev Sardor Zokirjon o'g'li",{"tldr":492,"method":493,"finding":494,"direction":230,"opportunity":495},"综述遥感与GIS评估灌溉地土壤盐渍化的方法、挑战与前景，并提出空间显式评估框架。","整合多光谱卫星影像、光谱指数、GIS空间分析与机器学习，结合电导率校准。","可靠盐渍化评估需卫星观测与实地测量及环境变量融合，而非孤立使用光谱指数。","可探索多源遥感与机器学习融合的盐渍化动态监测，并验证于中亚等干旱灌区。","2026-10-15T23:30:32.401626Z",{"id":498,"title":499,"url":500,"summary":501,"summary_zh":502,"content":8,"source_name":503,"source_url":500,"published_at":504,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":505,"score_detail":506,"sources":508,"tags":510,"primary_topic":512,"secondary_topics":513,"classification":516,"search_phrases":540,"slug":543,"view_count":123,"doi":544,"paper":545,"created_at":565},5006,"Mapping Soil Salinity in Arid Agricultural Regions Using Multi-Source Remote Sensing and a Long-Range Dependency-Enhanced Deep Learning Framework","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fland15101966","Soil salinity estimation across arid agricultural regions is challenging due to pronounced environmental heterogeneity and complex dependencies among multi-source variables. This study proposes a Long-Range Dependency-Enhanced Network (LRD-Net) for regional-scale soil salinity estimation in multiple agricultural oasis regions using multi-source remote sensing and environmental covariates. A dataset comprising 180 field samples from three agricultural oasis regions in Xinjiang, China, was constructed with 25 covariates derived from spectral, topographic, climatic, and soil property data. LRD-Net consists of three stages: a multi-scale feature fusion backbone based on depthwise separable convolutions and cross-scale interaction; a Long-Range Dependency Enhancement Module (LDEM) with an asymmetric dual-branch architecture that captures forward and reverse-aware dependencies through reverse alignment and cross-directional fusion; and multi-scale attention refinement with a regression head for continuous salinity estimation. Under the region-stratified random-split evaluation, LRD-Net achieved an R2 of 0.905, an RMSE of 1.207 g·kg−1, and an MAE of 0.868 g·kg−1. Performance decreased under more spatially independent validation, with an R2 of 0.874 under spatial cross-validation and LORO test R2 values ranging from 0.739 to 0.801, indicating that prediction across spatially and geographically independent samples is more challenging than region-stratified random-split evaluation. The proposed framework effectively integrates multi-source information and captures complementary long-range dependencies, providing a potential approach for regional-scale soil salinity estimation within the studied arid agricultural oasis environments and supporting soil salinization monitoring and sustainable land management in the study region.","干旱农业区域土壤盐分估算面临显著的环境异质性和多源变量间复杂依赖关系的挑战。本研究提出了一种长程依赖增强网络（LRD-Net），利用多源遥感与环境协变量对多个农业绿洲区域进行区域尺度土壤盐分估算。研究构建了包含中国新疆三个农业绿洲区域180个野外样本的数据集，并衍生出25个协变量，涵盖光谱、地形、气候和土壤属性数据。LRD-Net由三个阶段组成：基于深度可分离卷积和跨尺度交互的多尺度特征融合骨干网络；具有非对称双分支架构的长程依赖增强模块（LDEM），通过反向对齐和跨方向融合捕获前向与反向感知依赖关系；以及多尺度注意力细化与回归头，用于连续盐分估算。在区域分层随机划分评估下，LRD-Net取得了R²为0.905、RMSE为1.207 g·kg⁻¹、MAE为0.868 g·kg⁻¹的性能。在空间独立性更强的验证下性能有所下降，空间交叉验证R²为0.874，留一区域测试R²范围为0.739至0.801，表明跨空间和地理独立样本的预测比区域分层随机划分评估更具挑战性。所提出的框架有效整合了多源信息并捕获了互补的长程依赖关系，为研究区干旱农业绿洲环境下的区域尺度土壤盐分估算提供了潜在方法，并支持研究区土壤盐渍化监测与可持续土地管理。","Land","2026-10-14T00:00:00Z",72,{"impact":17,"substance":152,"depth":82,"authority":153,"freshness":83,"relevant":21,"comment":507},"方法新颖、数据扎实的遥感土壤盐渍化估算研究，对干旱区盐碱地监测与治理有参考价值，但属细分领域学术进展，公共影响有限。",[509],{"name":503,"url":500},[26,88,194,320,511],"新疆农业",{"code":191,"slug":431,"name":432,"path":433,"parent_code":98},[514,515],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":58,"slug":95,"name":96,"path":97,"parent_code":98},{"status":39,"locked":14,"version":40,"method":41,"evidence":517},{"candidates":518,"agricultural_evidence":47},[519,523,527,532,536],{"code":191,"score":181,"supported":47,"title":520,"abstract":521,"tags":522},[195],[194,195],[194],{"code":32,"score":103,"supported":47,"title":524,"abstract":525,"tags":526},[33],[55,33],[],{"code":58,"score":83,"supported":47,"title":528,"abstract":530,"tags":531},[529],"deep learning",[],[88],{"code":368,"score":52,"supported":47,"title":533,"abstract":534,"tags":535},[],[371],[],{"code":45,"score":21,"supported":14,"title":537,"abstract":538,"tags":539},[],[],[26],[541,542],"新疆 农业绿洲 土壤盐渍化 遥感","LRD-Net 土壤盐分 估算","新疆农业绿洲土壤盐渍化遥感-5006","10.3390\u002Fland15101966",{"doi":544,"openalex_id":546,"authors":547,"venue":503,"cited_by_count":123,"oa_url":500,"card":560,"direction":230,"ingested_from":140},"W7221816183",[548,550,553,555,557],{"name":549,"orcid":8},"Mingjie Qian",{"name":551,"orcid":552},"Liangjun Wang","https:\u002F\u002Forcid.org\u002F0009-0006-8718-8326",{"name":554,"orcid":8},"Peng Wang",{"name":556,"orcid":8},"Hangyuan Liu",{"name":558,"orcid":559},"Weitao Chen","https:\u002F\u002Forcid.org\u002F0000-0002-6272-1618",{"tldr":561,"method":562,"finding":563,"direction":230,"opportunity":564},"提出LRD-Net深度学习框架，融合多源遥感与环境协变量，估算新疆干旱绿洲区土壤盐分。","构建180个样点、25个协变量的数据集，设计含长程依赖增强模块的多尺度网络。","区域分层随机划分下R²达0.905，但空间独立验证R²降至0.739-0.874，跨区域预测更难。","可探索跨区域迁移学习与不确定性量化，提升空间独立场景下盐分制图泛化能力。","2026-10-15T23:30:29.667342Z"]