[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1328":3,"related-1328":108},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":30,"secondary_topics":36,"classification":43,"search_phrases":85,"slug":88,"view_count":89,"doi":90,"paper":91,"created_at":107},1328,"Explainable Machine Learning for Simultaneous Prediction of Soil Texture and Gravimetric Water Content: A SHAP-Driven Multi-Model Framework","https:\u002F\u002Fdoi.org\u002F10.70917\u002Fijcisim-2026-5335","Soil texture and gravimetric water content (GWC) are important properties which need to be determined accurately for proper irrigation and sustainable land management. Although machine learning (ML) has enhanced the ability to predict pedometrics, many of the high performing algorithms have been described as a \"black-box\" and practitioners have been reluctant to trust the model and connect the model output with soil physics. Furthermore, the existing approaches mostly assume independence between the attributes to be predicted and do not take into account their physical relationships. The present study aims to fill these voids by proposing a robust multi-model approach for simultaneous prediction of soil texture and GWC. A variety of data was used to assess state-of-the-art algorithms, such as XGBoost, CatBoost, and Random Forest. However, to achieve local and global interpretability, we integrated Shapley Additive Explanations (SHAP). This XAI-based approach filled the gap between computational intelligence and soil physics, allowing a fine-grained diagnosis of the contribution of the different features. The results show that the Random Forest framework outperformed in terms of concurrent performance with R2 value of 0.908, accuracy of 90.8% and Cohen's Kappa of 0.82 for soil texture and R2 value of 0.798 for GWC. Two features, Cation Exchange Capacity (CEC) and Organic Matter Percentage (OMP), were identified as the most influential using SHAP analysis, and they were found to exert the greatest influence on the moisture retention thresholds, with CEC being the most discriminative feature between the Clayey and Sandy texture classes, which aligns with the model's validity in light of the known pedology. This transparency and simultaneous monitoring of key soil properties makes it an appealing solution for precision agriculture and for resource management in the context of climate change.","土壤质地与重量含水量（GWC）是精准灌溉和可持续土地管理中需精确测定的重要属性。尽管机器学习（ML）增强了预测土壤计量学（pedometrics）的能力，但许多高性能算法被描述为“黑箱”，实践者往往不愿信任模型，也难以将模型输出与土壤物理学联系起来。此外，现有方法大多假设待预测属性之间相互独立，未考虑其物理关系。本研究旨在通过提出一种稳健的多模型方法，同时预测土壤质地和GWC，以填补这些空白。研究使用了多种数据评估先进算法，如XGBoost、CatBoost和随机森林（Random Forest）。然而，为实现局部和全局可解释性，我们整合了Shapley加法解释（SHAP）。这种基于可解释人工智能（XAI）的方法弥合了计算智能与土壤物理学之间的鸿沟，能够对不同特征的贡献进行细粒度诊断。结果表明，随机森林框架在并发性能上表现优异，土壤质地的R²值为0.908，准确率为90.8%，Cohen's Kappa系数为0.82，GWC的R²值为0.798。通过SHAP分析，阳离子交换量（CEC）和有机质百分比（OMP）被识别为最具影响力的两个特征，且它们对水分保持阈值的影响最大，其中CEC是区分黏土和砂土质地类别的最具判别力的特征，这与已知土壤学知识下模型的效度相吻合。这种对关键土壤属性的透明性和同步监测，使其成为精准农业及气候变化背景下资源管理的理想解决方案。",null,"International Journal of Computer Information Systems and Industrial Management Applications","2026-08-30T00:00:00Z","论文",10,false,73,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,12,3,1,"研究提出可解释的机器学习框架，同时预测土壤质地与含水量，提升模型透明度，对精准农业有实质贡献。",[24],{"name":10,"url":6},[26,27,28,29],"智慧农业","农业人工智能","机器学习","土壤监测",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[37],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":44,"locked":14,"version":45,"method":46,"evidence":47},"classified","2026-10-22.2","rules",{"candidates":48,"agricultural_evidence":51},[49,56,62,70,78],{"code":31,"score":50,"supported":51,"title":52,"abstract":54,"tags":55},16,true,[53],"machine learning",[28,53],[27,28],{"code":38,"score":57,"supported":51,"title":58,"abstract":59,"tags":61},14,[39],[60,39],"土壤",[],{"code":63,"score":64,"supported":51,"title":65,"abstract":66,"tags":69},"I1",7,[],[67,68],"精准农业","precision agriculture",[26],{"code":71,"score":72,"supported":51,"title":73,"abstract":74,"tags":77},"H3",6,[],[75,76],"灌溉","irrigation",[],{"code":79,"score":72,"supported":51,"title":80,"abstract":81,"tags":84},"H7",[],[82,83],"气候变化","climate change",[],[86,87],"农业人工智能 土壤监测 智慧农业 机器学习","农业人工智能 土壤监测","农业人工智能土壤监测智慧农业机器学习-1328",2,"10.70917\u002Fijcisim-2026-5335",{"doi":90,"openalex_id":92,"authors":93,"venue":10,"cited_by_count":98,"oa_url":6,"card":99,"direction":105,"ingested_from":106},"W7204858035",[94,96],{"name":95,"orcid":9},"Chetana Shivanagi",{"name":97,"orcid":9},"Shivayogi  Ullagaddi",0,{"tldr":100,"method":101,"finding":102,"direction":103,"opportunity":104},"提出可解释机器学习框架，同时预测土壤质地和含水量，提升模型透明度和可信度。","使用XGBoost、CatBoost、随机森林，结合SHAP进行局部和全局解释。","随机森林表现最佳，CEC和有机质是关键特征，与土壤物理规律一致。","智慧农业 \u002F 农业物联网","可探索将SHAP解释与因果推断结合，或扩展到其他土壤属性及动态预测，增强模型泛化性。","农业人工智能与决策模型","openalex","2026-09-01T23:30:40.247344Z",{"total":72,"page":21,"page_size":72,"items":109},[110,164,237,316,372,451],{"id":111,"title":112,"url":113,"summary":114,"summary_zh":9,"content":9,"source_name":115,"source_url":9,"published_at":116,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":117,"score_detail":118,"sources":120,"tags":122,"primary_topic":124,"secondary_topics":125,"classification":127,"search_phrases":151,"slug":154,"view_count":143,"doi":9,"paper":155,"created_at":163},4286,"Applications of Artificial Intelligence in Soil Characterization and Agriculture: A Systematic Review","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37386408","Navarro Rubio等系统综述2018-2026年196项AI土壤特性与农业应用研究，遵循PRISMA 2020框架。综述发现研究明显向数据驱动方法转变，机器学习和深度学习模型主导近期研究；随机森林、支持向量机、梯度提升方法、人工神经网络、卷积神经网络、长短期记忆架构最常被报告；主要数据源包括原位传感、实验室测量、遥感影像和环境协变量，常通过多源数据融合框架集成；树集成模型在不同土壤特性上提供稳健性能。","Agronomy 2026 16(13):1241 DOI:10.3390\u002Fagronomy16131241","2026-10-02T00:00:00Z",78,{"impact":17,"substance":18,"depth":17,"authority":57,"freshness":72,"relevant":21,"comment":119},"PRISMA框架下196项研究的系统综述，方法学扎实、结论可靠，对农业AI土壤应用具较高参考价值。",[121],{"name":115,"url":113},[26,27,28,123,29],"遥感",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[126],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":128},{"candidates":129,"agricultural_evidence":51},[130,136,141,147],{"code":31,"score":50,"supported":51,"title":131,"abstract":133,"tags":135},[132],"artificial intelligence",[134,28],"深度学习",[27,28],{"code":38,"score":137,"supported":51,"title":138,"abstract":139,"tags":140},11,[39],[60],[],{"code":142,"score":143,"supported":51,"title":144,"abstract":145,"tags":146},"I3",4,[],[123],[123],{"code":63,"score":21,"supported":14,"title":148,"abstract":149,"tags":150},[],[],[26],[152,153],"AI 土壤特性 系统综述","机器学习 土壤 遥感","AI土壤特性系统综述-4286",{"doi":9,"openalex_id":9,"authors":156,"venue":9,"cited_by_count":98,"oa_url":9,"card":157,"direction":105,"ingested_from":162},[],{"tldr":158,"method":159,"finding":160,"direction":105,"opportunity":161},"系统综述2018-2026年196项AI用于土壤特性与农业的研究。","PRISMA 2020框架，分析机器学习与深度学习模型及多源数据融合。","研究转向数据驱动，树集成模型在不同土壤特性上表现稳健。","可探索可解释AI与多源数据融合在土壤特性预测中的泛化能力。","agent","2026-10-06T00:05:04.976398Z",{"id":165,"title":166,"url":167,"summary":168,"summary_zh":169,"content":9,"source_name":170,"source_url":167,"published_at":171,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":172,"score_detail":173,"sources":179,"tags":181,"primary_topic":184,"secondary_topics":185,"classification":190,"search_phrases":213,"slug":216,"view_count":21,"doi":217,"paper":218,"created_at":236},2543,"Effects of Noise on the Accuracy of Estimating Rootzone Total Soil Moisture Using a Non‐Linear Autoregressive Exogenous Machine Learning Model for Precision Agriculture","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fird.70226","ABSTRACT Widely used evapotranspiration (ET)–based irrigation methods contain many uncertainties that can affect irrigation quantity. To reduce these uncertainties, an alternative approach is the use of soil moisture (SM) data to estimate plant water uptake (PWU). If rootzone SM dynamics are understood, a surrogate machine learning (ML) model to predict the behaviour of SM dynamics can be developed to estimate PWU. Given the time and external variable dependency of SM, the non‐linear autoregressive exogenous (NARX) algorithm can be a better ML model for this purpose. However, the effect of measurement errors can affect prediction quality and hence the full deployment of data collection technology and computational algorithms. This paper presents a methodology consisting of analysing real‐world data, developing a generalized hypothetical SM curve, simulating measurement errors to develop noisy datasets and developing an ML model. The results show that the prediction accuracy is inversely proportional to the noise level. Up to a 10% measurement error, the NARX model can capture the SM dynamics with relatively high accuracy. However, the prediction quality decreases significantly as the noise level increases to 20%. For noise levels within 5%, the model prediction accuracy is significantly high, with correlation coefficients higher than 0.90 for all sets.","摘要 广泛使用的基于蒸散发（ET）的灌溉方法存在许多不确定性，可能影响灌溉量。为减少这些不确定性，一种替代方法是利用土壤水分（SM）数据估算植物吸水量（PWU）。如果理解了根区土壤水分动态，就可以开发一个替代性机器学习（ML）模型来预测土壤水分动态行为，从而估算植物吸水量。鉴于土壤水分对时间和外部变量的依赖性，非线性自回归外生（NARX）算法可能是更适合此目的的机器学习模型。然而，测量误差的影响可能影响预测质量，进而影响数据采集技术和计算算法的全面部署。本文提出了一套方法，包括分析真实世界数据、建立广义假设土壤水分曲线、模拟测量误差以生成含噪数据集，以及开发机器学习模型。结果表明，预测精度与噪声水平成反比。在测量误差不超过10%时，NARX模型能够以较高精度捕捉土壤水分动态。然而，当噪声水平增至20%时，预测质量显著下降。对于5%以内的噪声水平，模型预测精度显著较高，所有数据集的决定系数均高于0.90。","Irrigation and Drainage","2026-09-14T00:00:00Z",72,{"impact":174,"substance":175,"depth":176,"authority":174,"freshness":177,"relevant":21,"comment":178},13,21,17,8,"核心期刊论文，量化了测量噪声对NARX土壤水分预测精度的影响，为精准灌溉传感器布设与数据质量控制提供参考，但属细分方法研究，公共影响有限。",[180],{"name":170,"url":167},[26,27,28,182,183],"精准灌溉","土壤墒情",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[186,187],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":71,"slug":76,"name":188,"path":189,"parent_code":42},"水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",{"status":44,"locked":14,"version":45,"method":46,"evidence":191},{"candidates":192,"agricultural_evidence":51},[193,197,202,208],{"code":31,"score":50,"supported":51,"title":194,"abstract":195,"tags":196},[53],[28,53],[27,28],{"code":38,"score":198,"supported":51,"title":199,"abstract":200,"tags":201},15,[39],[60,39],[183],{"code":71,"score":13,"supported":51,"title":203,"abstract":204,"tags":207},[],[75,205,76,206],"蒸散发","evapotranspiration",[182],{"code":63,"score":209,"supported":51,"title":210,"abstract":211,"tags":212},9,[68],[],[26],[214,215],"农业人工智能 土壤墒情 智慧农业 机器学习","农业人工智能 土壤墒情","农业人工智能土壤墒情智慧农业机器学习-2543","10.1002\u002Fird.70226",{"doi":217,"openalex_id":219,"authors":220,"venue":170,"cited_by_count":98,"oa_url":9,"card":231,"direction":105,"ingested_from":106},"W7213181547",[221,224,227,229],{"name":222,"orcid":223},"Fayzul Pasha","https:\u002F\u002Forcid.org\u002F0000-0002-8295-0602",{"name":225,"orcid":226},"Ashok Inturi","https:\u002F\u002Forcid.org\u002F0009-0004-1934-4310",{"name":228,"orcid":9},"Kinnoree R. Pasha",{"name":230,"orcid":9},"Dilruba Yeasmin",{"tldr":232,"method":233,"finding":234,"direction":105,"opportunity":235},"该论文评估了测量噪声对NARX机器学习模型估算根区土壤水分动态精度的影响。","使用NARX模型，基于真实数据、广义假设曲线和模拟噪声数据集。","预测精度与噪声水平成反比；噪声≤10%时精度较高，≤5%时相关系数>0.90，20%时显著下降。","可研究自适应去噪或鲁棒NARX模型，以在20%以上噪声下维持土壤水分预测精度。","2026-09-15T23:30:38.023164Z",{"id":238,"title":239,"url":240,"summary":241,"summary_zh":242,"content":9,"source_name":243,"source_url":240,"published_at":244,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":245,"score_detail":246,"sources":248,"tags":250,"primary_topic":253,"secondary_topics":254,"classification":256,"search_phrases":290,"slug":293,"view_count":20,"doi":294,"paper":295,"created_at":315},1910,"APPLICATION OF ARTIFICIAL INTELLIGENCE IN SOIL FERTILITY ASSESSMENT AND CROP YIELD PREDICTION IN SOUTHWEST NIGERIA: A STATISTICAL APPROACH","https:\u002F\u002Fdoi.org\u002F10.70382\u002Ftijsrat.v13i9.090","This study investigates the application of Artificial Intelligence (AI) techniques in soil fertility assessment and crop yield prediction in Southwest Nigeria. Traditional soil analysis methods are often time-consuming, expensive, and limited in predictive capability. This research integrates machine learning models to analyse soil parameters such as pH, nitrogen, phosphorus, potassium, and organic matter content to predict crop yield outcomes. Data were obtained from selected agricultural zones in Osun and Oyo States. Supervised learning algorithms including Linear Regression, Random Forest, and Support Vector Machines were employed. The results indicate that AI-based models significantly improve prediction accuracy compared to conventional statistical approaches, with Random Forest outperforming other models. The study demonstrates that AI can enhance decision-making in precision agriculture, optimize fertilizer application, and improve food security. It is recommended that stakeholders adopt AI-driven soil analysis systems to boost agricultural productivity in Nigeria.","本研究探讨了人工智能（AI）技术在尼日利亚西南部土壤肥力评估与作物产量预测中的应用。传统土壤分析方法往往耗时、成本高昂，且预测能力有限。本研究整合机器学习模型，分析土壤参数如pH值、氮、磷、钾及有机质含量，以预测作物产量结果。数据来源于奥孙州和奥约州选定的农业区域。采用了包括线性回归、随机森林和支持向量机在内的监督学习算法。结果表明，与传统统计方法相比，基于AI的模型显著提高了预测准确性，其中随机森林模型表现最优。研究证明，AI能够增强精准农业中的决策能力，优化肥料施用，并提升粮食安全水平。建议利益相关方采用AI驱动的土壤分析系统，以提高尼日利亚的农业生产率。","International Journal of Science Research and Technology","2026-09-07T00:00:00Z",56,{"impact":19,"substance":17,"depth":198,"authority":177,"freshness":20,"relevant":21,"comment":247},"研究AI在尼日利亚土壤评估与产量预测中的应用，方法常规但数据具体，对非洲农业智能化有参考价值。",[249],{"name":243,"url":240},[26,27,28,251,252],"作物产量预测","土壤肥力",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[255],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":257},{"candidates":258,"agricultural_evidence":51},[259,264,268,272,279,286],{"code":31,"score":260,"supported":51,"title":261,"abstract":262,"tags":263},19,[132],[28,53,132],[27,28],{"code":38,"score":198,"supported":51,"title":265,"abstract":266,"tags":267},[39],[60,39],[252],{"code":63,"score":64,"supported":51,"title":269,"abstract":270,"tags":271},[],[67,68],[26],{"code":273,"score":72,"supported":51,"title":274,"abstract":275,"tags":278},"A8",[],[276,277],"粮食安全","food security",[],{"code":280,"score":72,"supported":51,"title":281,"abstract":282,"tags":285},"F3",[],[283,284],"肥料","fertilizer",[],{"code":142,"score":21,"supported":14,"title":287,"abstract":288,"tags":289},[],[],[251],[291,292],"作物产量预测 农业人工智能 土壤肥力 智慧农业","作物产量预测 农业人工智能","作物产量预测农业人工智能土壤肥力智慧农业-1910","10.70382\u002Ftijsrat.v13i9.090",{"doi":294,"openalex_id":296,"authors":297,"venue":243,"cited_by_count":98,"oa_url":240,"card":310,"direction":105,"ingested_from":106},"W7211915991",[298,300,302,304,306,308],{"name":299,"orcid":9},"AJALA S. A.",{"name":301,"orcid":9},"OYEDEPO A. O.",{"name":303,"orcid":9},"OLOWOLAGBA M. A.",{"name":305,"orcid":9},"OGUNOLA Z. A.",{"name":307,"orcid":9},"BAKARE S. A.",{"name":309,"orcid":9},"SULU A. B.",{"tldr":311,"method":312,"finding":313,"direction":105,"opportunity":314},"研究AI在尼日利亚西南部土壤肥力评估和作物产量预测中的应用，发现随机森林模型表现最佳。","使用线性回归、随机森林和支持向量机等监督学习算法分析土壤参数预测作物产量。","AI模型显著提高预测精度，随机森林优于其他模型，可优化施肥和提升农业生产力。","可探索将AI土壤分析系统推广至其他地区，或结合遥感数据与实时传感器提升预测精度和实用性。","2026-09-08T23:30:32.423857Z",{"id":317,"title":318,"url":319,"summary":320,"summary_zh":321,"content":9,"source_name":322,"source_url":319,"published_at":323,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":324,"score_detail":325,"sources":328,"tags":330,"primary_topic":334,"secondary_topics":335,"classification":337,"search_phrases":352,"slug":355,"view_count":98,"doi":356,"paper":357,"created_at":371},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":177,"substance":326,"depth":176,"authority":209,"freshness":13,"relevant":21,"comment":327},20,"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。",[329],{"name":322,"url":319},[26,27,331,332,333],"主动学习","线虫检测","土壤采样",{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},[336],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":44,"locked":14,"version":45,"method":46,"evidence":338},{"candidates":339,"agricultural_evidence":51},[340,344,348],{"code":38,"score":57,"supported":51,"title":341,"abstract":342,"tags":343},[39],[60,39],[],{"code":31,"score":209,"supported":51,"title":345,"abstract":346,"tags":347},[132],[],[27],{"code":63,"score":64,"supported":51,"title":349,"abstract":350,"tags":351},[],[67,68],[26],[353,354],"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","10.5281\u002Fzenodo.23544145",{"doi":356,"openalex_id":358,"authors":359,"venue":322,"cited_by_count":98,"oa_url":319,"card":366,"direction":105,"ingested_from":106},"W7223082195",[360,362,364],{"name":361,"orcid":9},"Amine Ben Salah",{"name":363,"orcid":9},"Ines Trabelsi",{"name":365,"orcid":9},"Mohamed Aziz Khelifi",{"tldr":367,"method":368,"finding":369,"direction":105,"opportunity":370},"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。","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。","2026-10-22T11:20:58.901747Z",{"id":373,"title":374,"url":375,"summary":376,"summary_zh":377,"content":9,"source_name":378,"source_url":375,"published_at":323,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":379,"score_detail":380,"sources":382,"tags":384,"primary_topic":387,"secondary_topics":393,"classification":396,"search_phrases":427,"slug":430,"view_count":98,"doi":431,"paper":432,"created_at":450},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":50,"substance":175,"depth":176,"authority":174,"freshness":13,"relevant":21,"comment":381},"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。",[383],{"name":378,"url":375},[26,28,385,183,386],"遥感监测","冬小麦",{"code":388,"slug":389,"name":390,"path":391,"parent_code":392},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[394,395],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":44,"locked":14,"version":45,"method":46,"evidence":397},{"candidates":398,"agricultural_evidence":51},[399,405,409,413,419,423],{"code":388,"score":400,"supported":51,"title":401,"abstract":403,"tags":404},26,[402,389],"winter wheat",[390,402,389],[386],{"code":38,"score":198,"supported":51,"title":406,"abstract":407,"tags":408},[39],[60,39],[183],{"code":31,"score":198,"supported":51,"title":410,"abstract":411,"tags":412},[53],[28,53],[28],{"code":142,"score":13,"supported":51,"title":414,"abstract":415,"tags":418},[],[123,416,417],"remote sensing","multispectral",[385],{"code":71,"score":72,"supported":51,"title":420,"abstract":421,"tags":422},[],[75,76],[],{"code":63,"score":143,"supported":51,"title":424,"abstract":425,"tags":426},[],[26],[26],[428,429],"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":431,"openalex_id":433,"authors":434,"venue":378,"cited_by_count":98,"oa_url":375,"card":444,"direction":103,"ingested_from":106},"W7223156204",[435,438,440,442],{"name":436,"orcid":437},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":439,"orcid":9},"Yi Zhang",{"name":441,"orcid":9},"WEI Lei",{"name":443,"orcid":9},"Chengcai Zhang",{"tldr":445,"method":446,"finding":447,"direction":448,"opportunity":449},"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。","2026-10-22T11:20:18.887301Z",{"id":452,"title":453,"url":454,"summary":455,"summary_zh":456,"content":9,"source_name":457,"source_url":454,"published_at":458,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":172,"score_detail":459,"sources":461,"tags":463,"primary_topic":466,"secondary_topics":470,"classification":473,"search_phrases":498,"slug":501,"view_count":98,"doi":502,"paper":503,"created_at":523},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",{"impact":19,"substance":175,"depth":176,"authority":174,"freshness":209,"relevant":21,"comment":460},"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。",[462],{"name":457,"url":454},[26,27,123,464,465],"土壤盐渍化","新疆农业",{"code":142,"slug":467,"name":468,"path":469,"parent_code":35},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[471,472],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":44,"locked":14,"version":45,"method":46,"evidence":474},{"candidates":475,"agricultural_evidence":51},[476,480,484,489,494],{"code":142,"score":198,"supported":51,"title":477,"abstract":478,"tags":479},[416],[123,416],[123],{"code":38,"score":57,"supported":51,"title":481,"abstract":482,"tags":483},[39],[60,39],[],{"code":31,"score":209,"supported":51,"title":485,"abstract":487,"tags":488},[486],"deep learning",[],[27],{"code":79,"score":20,"supported":51,"title":490,"abstract":491,"tags":493},[],[492],"干旱",[],{"code":63,"score":21,"supported":14,"title":495,"abstract":496,"tags":497},[],[],[26],[499,500],"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":502,"openalex_id":504,"authors":505,"venue":457,"cited_by_count":98,"oa_url":454,"card":518,"direction":448,"ingested_from":106},"W7221816183",[506,508,511,513,515],{"name":507,"orcid":9},"Mingjie Qian",{"name":509,"orcid":510},"Liangjun Wang","https:\u002F\u002Forcid.org\u002F0009-0006-8718-8326",{"name":512,"orcid":9},"Peng Wang",{"name":514,"orcid":9},"Hangyuan Liu",{"name":516,"orcid":517},"Weitao Chen","https:\u002F\u002Forcid.org\u002F0000-0002-6272-1618",{"tldr":519,"method":520,"finding":521,"direction":448,"opportunity":522},"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"]