[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3804":3,"related-3804":117},{"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":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":50,"search_phrases":94,"slug":97,"view_count":98,"doi":99,"paper":100,"created_at":116},3804,"Evaluating Reference Evapotranspiration and Soil Moisture as Predictors for Machine Learning-Based Actual Evapotranspiration Estimation: Model Performance and Explainability","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fatmos17100941","Accurate estimation of actual evapotranspiration (ETa) is essential for sustainable water resources management and agricultural planning. This study investigated how the availability of reference evapotranspiration (ET0) and soil moisture (SM) affects ETa prediction performance and predictor importance using Random Forest (RF), Bagging Trees (BT), Least Squares Boosting (LSBoost), Generalized Additive Models (GAM), and Multiple Linear Regression (MLR). Global solar radiation (Rs), land surface temperature (LST), normalized difference vegetation index (NDVI), and SM were evaluated under two primary scenarios, with and without ET0. Models were developed using 80% of the data, with five-fold cross-validation conducted within the training subset, and final performance was evaluated on an independent 20% test subset. Model interpretability was assessed using SHAP, Permutation Feature Importance (PFI), Partial Dependence Plot (PDP), and temporal signed-SHAP analyses, while an additional SM-ablation experiment quantified the incremental predictive contribution of soil moisture. In Scenario I, ET0 was the dominant predictor, and RF and BT achieved the highest independent-test performance (R2 = 0.875; RMSE = 0.398–0.399 mm day−1). Excluding ET0 reduced predictive performance, with RF, LSBoost, and BT achieving R2 values of approximately 0.80 in Scenario II, while the predictor-importance structure shifted primarily toward Rs, followed by SM, LST, and NDVI. Removal of SM further reduced performance in both scenarios, with substantially greater deterioration when ET0 was unavailable: R2 decreased by 0.025–0.044 in Scenario I and by 0.051–0.099 in Scenario II. Under the SM-excluded Scenario I configuration, which more closely aligned the predictor information with previous ANN- and SAFER-based studies, R2 values ranged from 0.820 to 0.832, indicating that differences in ETa prediction performance cannot be attributed solely to model structure but also depend strongly on predictor information content. Overall, ET0 provides substantial atmospheric-demand information for ETa prediction, whereas Rs assumes the dominant predictive role, and SM provides particularly important complementary information when ET0 is unavailable. The combined performance, ablation, and explainability analyses demonstrate the importance of considering predictor composition together with model structure when developing and comparing ETa estimation approaches.","准确估算实际蒸散发（ETa）对于可持续水资源管理和农业规划至关重要。本研究探讨了参考蒸散发（ET0）和土壤水分（SM）的可用性如何影响ETa预测性能及预测因子重要性，采用了随机森林（RF）、Bagging Trees（BT）、最小二乘提升（LSBoost）、广义加性模型（GAM）和多元线性回归（MLR）方法。在全球太阳辐射（Rs）、地表温度（LST）、归一化差异植被指数（NDVI）和SM的条件下，评估了包含和不包含ET0两种主要情景。模型使用80%的数据进行开发，在训练子集内进行五折交叉验证，最终性能在独立的20%测试子集上评估。模型可解释性通过SHAP、排列特征重要性（PFI）、偏依赖图（PDP）和时间符号SHAP分析进行评估，同时通过额外的SM消融实验量化了土壤水分的增量预测贡献。在情景I中，ET0是主导预测因子，RF和BT取得了最高的独立测试性能（R2 = 0.875；RMSE = 0.398–0.399 mm day−1）。排除ET0降低了预测性能，在情景II中RF、LSBoost和BT的R2值约为0.80，同时预测因子重要性结构主要转向Rs，其次是SM、LST和NDVI。去除SM进一步降低了两种情景下的性能，且在ET0不可用时性能下降幅度更大：情景I中R2下降了0.025–0.044，情景II中下降了0.051–0.099。在排除SM的情景I配置下（该配置使预测因子信息更接近此前的ANN和SAFER研究），R2值范围为0.820至0.832，表明ETa预测性能的差异不能仅归因于模型结构，还强烈依赖于预测因子信息含量。总体而言，ET0为ETa预测提供了大量大气需求信息，而Rs承担了主导预测作用，SM在ET0不可用时提供了特别重要的补充信息。综合性能、消融和可解释性分析表明，在开发和比较ETa估算方法时，需将预测因子组成与模型结构一并考虑。",null,"Atmosphere","2026-09-27T00:00:00Z","论文",10,false,73,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,22,18,13,8,1,"方法对比与可解释性分析扎实，对农业水资源管理和灌溉决策有参考价值，但属专业论文，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业遥感","机器学习","土壤墒情","蒸散发估算",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[39,44],{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":51,"locked":14,"version":52,"method":53,"evidence":54},"classified","2026-10-22.2","rules",{"candidates":55,"agricultural_evidence":58},[56,65,71,77,84,89],{"code":33,"score":57,"supported":58,"title":59,"abstract":61,"tags":64},17,true,[60],"evapotranspiration",[62,63,60],"水资源","蒸散发",[],{"code":40,"score":66,"supported":58,"title":67,"abstract":68,"tags":70},15,[41],[69,41],"土壤",[30],{"code":45,"score":72,"supported":58,"title":73,"abstract":75,"tags":76},9,[74],"machine learning",[],[29],{"code":78,"score":79,"supported":58,"title":80,"abstract":81,"tags":83},"J1",3,[],[82],"农业规划",[],{"code":85,"score":22,"supported":14,"title":86,"abstract":87,"tags":88},"I1",[],[],[27],{"code":90,"score":22,"supported":14,"title":91,"abstract":92,"tags":93},"I3",[],[],[28],[95,96],"参考蒸散发 土壤水分 机器学习","ET0 实际蒸散发 随机森林","参考蒸散发土壤水分机器学习-3804",2,"10.3390\u002Fatmos17100941",{"doi":99,"openalex_id":101,"authors":102,"venue":10,"cited_by_count":108,"oa_url":6,"card":109,"direction":113,"ingested_from":115},"W7214588993",[103,106],{"name":104,"orcid":105},"Halil Karahan","https:\u002F\u002Forcid.org\u002F0000-0001-5346-5686",{"name":107,"orcid":9},"Devrim Alkaya",0,{"tldr":110,"method":111,"finding":112,"direction":113,"opportunity":114},"评估ET0与土壤湿度对机器学习估算实际蒸散的影响及可解释性。","用RF、BT、LSBoost、GAM、MLR结合SHAP、PFI、PDP及SM消","ET0主导预测，缺失时Rs主导且SM补充价值显著增大。","农业人工智能与决策模型","可探索缺ET0条件下融合遥感与土壤湿度的可解释ETa估算框架。","openalex","2026-09-29T23:30:57.729880Z",{"total":118,"page":22,"page_size":118,"items":119},6,[120,187,270,350,405,455],{"id":121,"title":122,"url":123,"summary":124,"summary_zh":125,"content":9,"source_name":126,"source_url":123,"published_at":127,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":128,"score_detail":129,"sources":132,"tags":134,"primary_topic":137,"secondary_topics":138,"classification":141,"search_phrases":163,"slug":166,"view_count":22,"doi":167,"paper":168,"created_at":186},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":20,"substance":130,"depth":57,"authority":20,"freshness":21,"relevant":22,"comment":131},21,"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。",[133],{"name":126,"url":123},[27,135,29,136,30],"农业人工智能","精准灌溉",{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},[139,140],{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":51,"locked":14,"version":52,"method":53,"evidence":142},{"candidates":143,"agricultural_evidence":58},[144,149,153,158],{"code":45,"score":145,"supported":58,"title":146,"abstract":147,"tags":148},16,[74],[29,74],[135,29],{"code":40,"score":66,"supported":58,"title":150,"abstract":151,"tags":152},[41],[69,41],[30],{"code":33,"score":13,"supported":58,"title":154,"abstract":155,"tags":157},[],[156,63,34,60],"灌溉",[136],{"code":85,"score":72,"supported":58,"title":159,"abstract":161,"tags":162},[160],"precision agriculture",[],[27],[164,165],"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":167,"openalex_id":169,"authors":170,"venue":126,"cited_by_count":108,"oa_url":9,"card":181,"direction":113,"ingested_from":115},"W7213181547",[171,174,177,179],{"name":172,"orcid":173},"Fayzul Pasha","https:\u002F\u002Forcid.org\u002F0000-0002-8295-0602",{"name":175,"orcid":176},"Ashok Inturi","https:\u002F\u002Forcid.org\u002F0009-0004-1934-4310",{"name":178,"orcid":9},"Kinnoree R. Pasha",{"name":180,"orcid":9},"Dilruba Yeasmin",{"tldr":182,"method":183,"finding":184,"direction":113,"opportunity":185},"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":188,"title":189,"url":190,"summary":191,"summary_zh":192,"content":9,"source_name":193,"source_url":190,"published_at":194,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":195,"score_detail":196,"sources":198,"tags":200,"primary_topic":203,"secondary_topics":209,"classification":212,"search_phrases":245,"slug":248,"view_count":108,"doi":249,"paper":250,"created_at":269},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","2026-10-21T00:00:00Z",77,{"impact":145,"substance":130,"depth":57,"authority":20,"freshness":13,"relevant":22,"comment":197},"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。",[199],{"name":193,"url":190},[27,29,201,30,202],"遥感监测","冬小麦",{"code":204,"slug":205,"name":206,"path":207,"parent_code":208},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[210,211],{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},{"status":51,"locked":14,"version":52,"method":53,"evidence":213},{"candidates":214,"agricultural_evidence":58},[215,221,225,229,236,240],{"code":204,"score":216,"supported":58,"title":217,"abstract":219,"tags":220},26,[218,205],"winter wheat",[206,218,205],[202],{"code":40,"score":66,"supported":58,"title":222,"abstract":223,"tags":224},[41],[69,41],[30],{"code":45,"score":66,"supported":58,"title":226,"abstract":227,"tags":228},[74],[29,74],[29],{"code":90,"score":13,"supported":58,"title":230,"abstract":231,"tags":235},[],[232,233,234],"遥感","remote sensing","multispectral",[201],{"code":33,"score":118,"supported":58,"title":237,"abstract":238,"tags":239},[],[156,34],[],{"code":85,"score":241,"supported":58,"title":242,"abstract":243,"tags":244},4,[],[27],[27],[246,247],"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":249,"openalex_id":251,"authors":252,"venue":193,"cited_by_count":108,"oa_url":190,"card":262,"direction":268,"ingested_from":115},"W7223156204",[253,256,258,260],{"name":254,"orcid":255},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":257,"orcid":9},"Yi Zhang",{"name":259,"orcid":9},"WEI Lei",{"name":261,"orcid":9},"Chengcai Zhang",{"tldr":263,"method":264,"finding":265,"direction":266,"opportunity":267},"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":271,"title":272,"url":273,"summary":274,"summary_zh":275,"content":9,"source_name":276,"source_url":273,"published_at":277,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":278,"score_detail":279,"sources":281,"tags":283,"primary_topic":287,"secondary_topics":288,"classification":294,"search_phrases":321,"slug":324,"view_count":108,"doi":325,"paper":326,"created_at":349},4898,"An Interpretable Deep Learning Framework for Spatial Prediction of Soil Salinity Using Multi-Source Remote Sensing and Environmental Data: A Case Study of Cangzhou, Hebei Province, China","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fs26206465","Soil salinity poses a significant challenge to agricultural productivity and sustainable land management in coastal and semi-arid regions. Soil salinity in coastal agricultural regions is controlled by complex interactions among surface conditions, groundwater processes, soil properties, and terrain characteristics. Accurate spatial prediction requires integrating remote sensing observations with environmental information that represents these processes. This study presents a multi-source deep learning framework that integrates Sentinel-2-derived spectral indices with environmental covariates for regional soil salinity spatial prediction under the environmental conditions of the 2024 sampling period. SHapley Additive exPlanations (SHAP) is employed to quantify the contribution of environmental variables within the prediction framework and improve model interpretability. A convolutional neural network (CNN) incorporating a squeeze-and-excitation (SE) attention mechanism is developed as a nonlinear feature representation framework for integrating heterogeneous predictors, while the Crested Porcupine Optimizer (CPO) is used to optimize model hyperparameters. The proposed framework achieved the highest predictive performance among the benchmark models, with an R2 of 0.785, an RMSE of 0.928, and an MAE of 0.720. Integrating environmental covariates with spectral features further improves the prediction performance, increasing the R2 from 0.701 to 0.785. The results indicate the potential of integrating multi-source environmental information with interpretable deep learning for spatial prediction of near-surface soil salinity under similar coastal agricultural conditions.","土壤盐渍化对沿海和半干旱地区的农业生产力和可持续土地管理构成了重大挑战。沿海农业区域的土壤盐渍化受地表条件、地下水过程、土壤属性和地形特征之间复杂相互作用的控制。准确的空间预测需要将遥感观测与表征这些过程的环境信息相结合。本研究提出了一种多源深度学习框架，该框架将Sentinel-2衍生的光谱指数与环境协变量相结合，用于2024年采样期环境条件下的区域土壤盐渍化空间预测。采用SHapley加法解释（SHAP）方法量化预测框架中环境变量的贡献并提高模型可解释性。开发了一种融合压缩-激励（SE）注意力机制的卷积神经网络（CNN）作为非线性特征表示框架，用于整合异质性预测因子，同时使用冠豪猪优化器（CPO）优化模型超参数。所提出的框架在基准模型中取得了最高的预测性能，R²为0.785，RMSE为0.928，MAE为0.720。将环境协变量与光谱特征相结合进一步提高了预测性能，R²从0.701提升至0.785。结果表明，在类似的沿海农业条件下，将多源环境信息与可解释深度学习相结合用于近地表土壤盐渍化空间预测具有潜力。","Sensors","2026-10-13T00:00:00Z",75,{"impact":145,"substance":130,"depth":57,"authority":20,"freshness":21,"relevant":22,"comment":280},"方法新颖、指标可靠，将多源遥感与可解释深度学习结合用于盐渍化空间预测，对沿海农业区土壤治理有参考价值。",[282],{"name":276,"url":273},[27,28,284,285,286],"可解释AI","深度学习","土壤盐渍化",{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},[289,293],{"code":90,"slug":290,"name":291,"path":292,"parent_code":49},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},{"status":51,"locked":14,"version":52,"method":53,"evidence":295},{"candidates":296,"agricultural_evidence":58},[297,302,306,311,317],{"code":45,"score":145,"supported":58,"title":298,"abstract":300,"tags":301},[299],"deep learning",[285,299],[284,285],{"code":90,"score":66,"supported":58,"title":303,"abstract":304,"tags":305},[233],[232,233],[28],{"code":40,"score":307,"supported":58,"title":308,"abstract":309,"tags":310},14,[41],[69,41],[],{"code":312,"score":79,"supported":58,"title":313,"abstract":314,"tags":316},"H7",[],[315],"干旱",[],{"code":85,"score":22,"supported":14,"title":318,"abstract":319,"tags":320},[],[],[27],[322,323],"沧州 土壤盐渍化 遥感","Sentinel-2 土壤盐分 预测","沧州土壤盐渍化遥感-4898","10.3390\u002Fs26206465",{"doi":325,"openalex_id":327,"authors":328,"venue":276,"cited_by_count":108,"oa_url":273,"card":344,"direction":266,"ingested_from":115},"W7221715654",[329,332,335,337,340,342],{"name":330,"orcid":331},"Mingyuan Ye","https:\u002F\u002Forcid.org\u002F0009-0001-6434-5505",{"name":333,"orcid":334},"Peng Chen","https:\u002F\u002Forcid.org\u002F0000-0002-2549-6765",{"name":336,"orcid":9},"Junchi Ma",{"name":338,"orcid":339},"Bingxia Liu","https:\u002F\u002Forcid.org\u002F0000-0001-7958-7112",{"name":341,"orcid":9},"Jiahao Qi",{"name":343,"orcid":9},"Yuan Jing",{"tldr":345,"method":346,"finding":347,"direction":266,"opportunity":348},"构建融合多源遥感与环境变量的可解释深度学习框架，预测沧州土壤盐分空间分布。","Sentinel-2光谱指数+环境协变量，CNN-SE注意力，CPO优化超参数，","环境协变量与光谱特征结合将R²从0.701提升至0.785，模型性能最优。","可迁移至其他滨海盐渍区，并探索时序动态预测与多深度土壤盐分协同反演。","2026-10-14T23:30:27.313838Z",{"id":351,"title":352,"url":353,"summary":354,"summary_zh":355,"content":9,"source_name":356,"source_url":353,"published_at":357,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":358,"score_detail":359,"sources":362,"tags":364,"primary_topic":367,"secondary_topics":368,"classification":370,"search_phrases":387,"slug":390,"view_count":108,"doi":391,"paper":392,"created_at":404},4498,"SMART CROP SELECTION MODEL USING SOIL PH VALUE, TEMPERATURE, HUMIDITY, AND RAINFALL PREDICTION","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23211381","Crop suitability with soil and climatic conditions plays a vital role in increasing productivity of agriculture. This study proposes a smart crop selection model which recommends the suitable crop based on the machine learning techniques with the input parameters of soil pH, soil temperature, soil humidity and rainfall. The data set consisted of 1000 observations and 8 different crop classes and missing values were handled, crop labels were encoded and numerical features were selected. Five-fold cross validation was used to compare the performance of the three classifiers: Random Forest, XGBoost and Support Vector Machine (SVM). Finally, a Gradient-Boosted classification model was trained and evaluated with test-set accuracy, classification metrics, Multiclass ROC analysis and feature importance. The results of the application were 93.60% of the final test accuracy and the model comparison was used to compare the three classification methods. The contribution of four environmental parameters to the crop classification was analyzed by feature-importance analysis. To facilitate practical accessibility, the entire process was carried out using an interactive dashboard developed with Streamlit, allowing for the upload of datasets, evaluation of models, selection of parameters and the generation of predictions in real time for the crops of interest. The developed system is an example of how machine learning can be integrated with an interactive decision support interface to develop a data-driven, crop selection system, relying on simple soil and weather parameters.","作物适宜性与土壤及气候条件对提高农业生产率至关重要。本研究提出了一种智能作物选择模型，该模型基于机器学习技术，以土壤pH值、土壤温度、土壤湿度和降雨量为输入参数，推荐适宜的作物。数据集包含1000个观测值和8个不同作物类别，对缺失值进行了处理，对作物标签进行了编码，并筛选了数值特征。采用五折交叉验证比较了三种分类器——随机森林（Random Forest）、XGBoost和支持向量机（Support Vector Machine, SVM）的性能。最终，训练了一个梯度提升分类模型，并通过测试集准确率、分类指标、多类ROC分析和特征重要性进行了评估。应用结果为最终测试准确率93.60%，并通过模型比较对三种分类方法进行了对比。通过特征重要性分析，探讨了四个环境参数对作物分类的贡献。为便于实际应用，整个流程通过使用Streamlit开发的交互式仪表板实现，支持数据集上传、模型评估、参数选择以及针对感兴趣作物的实时预测生成。所开发的系统展示了如何将机器学习与交互式决策支持界面相结合，构建一个数据驱动的作物选择系统，且仅依赖于简单的土壤和气象参数。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-07T00:00:00Z",69,{"impact":17,"substance":360,"depth":145,"authority":20,"freshness":21,"relevant":22,"comment":361},20,"基于土壤pH、温湿度与降雨的机器学习选种模型，含93.6%测试精度与Streamlit交互看板，方法完整但属常规应用型研究，产业影响有限。",[363],{"name":356,"url":353},[27,135,365,30,366],"决策支持系统","作物选择",{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},[369],{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},{"status":51,"locked":14,"version":52,"method":53,"evidence":371},{"candidates":372,"agricultural_evidence":58},[373,377,383],{"code":40,"score":66,"supported":58,"title":374,"abstract":375,"tags":376},[41],[69,41],[30],{"code":45,"score":378,"supported":58,"title":379,"abstract":380,"tags":382},11,[],[29,74,381],"decision support",[135,365],{"code":85,"score":22,"supported":14,"title":384,"abstract":385,"tags":386},[],[],[27],[388,389],"土壤pH 降雨量 作物选择模型","机器学习 作物推荐 智慧农业","土壤pH降雨量作物选择模型-4498","10.5281\u002Fzenodo.23211381",{"doi":391,"openalex_id":393,"authors":394,"venue":356,"cited_by_count":108,"oa_url":353,"card":399,"direction":268,"ingested_from":115},"W7220991946",[395,397],{"name":396,"orcid":9},"C. SAI KUMAR",{"name":398,"orcid":9},"Prof. G SREENIVASULU",{"tldr":400,"method":401,"finding":402,"direction":113,"opportunity":403},"基于土壤pH、温湿度和降雨，用机器学习构建智能选种模型并开发交互式仪表板。","1000条8类作物数据，五折交叉验证比较RF、XGBoost、SVM，最终用梯度","梯度提升模型测试准确率达93.60%，特征重要性揭示四参数对选种的贡献。","可引入时序气象与多源土壤数据，提升模型泛化性并适配不同区域作物推荐。","2026-10-09T23:30:12.285129Z",{"id":406,"title":407,"url":408,"summary":409,"summary_zh":9,"content":9,"source_name":410,"source_url":9,"published_at":411,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":412,"score_detail":413,"sources":415,"tags":417,"primary_topic":419,"secondary_topics":420,"classification":422,"search_phrases":442,"slug":445,"view_count":241,"doi":9,"paper":446,"created_at":454},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":19,"substance":18,"depth":19,"authority":307,"freshness":118,"relevant":22,"comment":414},"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。",[416],{"name":410,"url":408},[27,135,29,232,418],"土壤监测",{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},[421],{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},{"status":51,"locked":14,"version":52,"method":53,"evidence":423},{"candidates":424,"agricultural_evidence":58},[425,430,434,438],{"code":45,"score":145,"supported":58,"title":426,"abstract":428,"tags":429},[427],"artificial intelligence",[285,29],[135,29],{"code":40,"score":378,"supported":58,"title":431,"abstract":432,"tags":433},[41],[69],[],{"code":90,"score":241,"supported":58,"title":435,"abstract":436,"tags":437},[],[232],[232],{"code":85,"score":22,"supported":14,"title":439,"abstract":440,"tags":441},[],[],[27],[443,444],"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":447,"venue":9,"cited_by_count":108,"oa_url":9,"card":448,"direction":113,"ingested_from":453},[],{"tldr":449,"method":450,"finding":451,"direction":113,"opportunity":452},"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":456,"title":457,"url":458,"summary":459,"summary_zh":460,"content":9,"source_name":461,"source_url":458,"published_at":462,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":278,"score_detail":463,"sources":465,"tags":467,"primary_topic":469,"secondary_topics":474,"classification":477,"search_phrases":512,"slug":515,"view_count":241,"doi":9,"paper":516,"created_at":530},4076,"Automated System for Plant Health Monitoring and Stress Diagnosis Using IoT and Machine Learning","https:\u002F\u002Fwajes.isroset.org\u002Findex.php\u002Fj\u002Farticle\u002Fview\u002F208","Irrigation decisions on smallholder farms are still taken subjectively, and both root-zone dehydration and over-saturation measurably depress yield, making low-cost automated plant-stress diagnosis an urgent requirement in water-scarce agricultural regions. This study designs, implements and validates a decentralized system that closes the control loop between field sensing and irrigation actuation by combining Internet of Things (IoT) hardware with a cloud-hosted predictive Machine Learning (ML) model. The edge node is built on an ESP32 system-on-chip integrated with a calibrated capacitive soil-moisture probe and a DHT22 temperature and humidity array. Serialized telemetry is transmitted over a non-blocking, encrypted wireless channel to a Flask web service, where a 150-tree Random Forest classifier trained on 5,000 labelled multi-sensor records assigns the plant to one of three physiological states Optimal, Temperature Stress or Dehydration Stress and returns an actuator control bit that drives a micro-irrigation pump. An engineered Evapotranspiration Proxy Index couples ambient temperature and relative humidity into a single transpiration-sensitive feature. Capacitive calibration was validated against the gravimetric standard on ten soil cores, yielding a Pearson correlation coefficient of 0.948. Over a continuous forty-eight-hour open-air evaluation the classifier achieved an overall accuracy of 96.8%, with 98.2% precision and 97.9% recall on the critical Dehydration Stress class, and a mean end-to-end round-trip latency of 1.84 seconds. Deep-sleep duty cycling reduced the mean node current to 0.65 mA, corresponding to an estimated 159 days of unattended operation on a single 2,500 mAh cell. The results demonstrate that a low-cost edge–cloud architecture can deliver dependable, timely and energy-sustainable irrigation control for micro-precision agriculture without server-grade hardware.","小农户的灌溉决策仍依赖主观判断，而根区脱水和过度饱和均会显著降低产量，这使得低成本自动化植物胁迫诊断成为缺水农业地区的迫切需求。本研究设计、实现并验证了一种去中心化系统，通过将物联网（IoT）硬件与云端预测机器学习（ML）模型相结合，闭合了田间传感与灌溉执行之间的控制回路。边缘节点基于ESP32片上系统构建，集成了经过校准的电容式土壤水分探头和DHT22温湿度传感器阵列。序列化遥测数据通过非阻塞加密无线信道传输至Flask Web服务，在此处，一个基于5,000条带标签多传感器记录训练的150棵树的随机森林分类器将植物判定为三种生理状态之一——最优、温度胁迫或脱水胁迫——并返回驱动微灌泵的执行器控制位。所设计的蒸散代理指数将环境温度和相对湿度耦合为单一蒸腾敏感特征。电容校准在十个土芯上与重量法标准进行验证，得到皮尔逊相关系数为0.948。在连续四十八小时的户外评估中，分类器总体准确率达到96.8%，在关键的脱水胁迫类别上精确率为98.2%、召回率为97.9%，平均端到端往返延迟为1.84秒。深度睡眠占空比控制将节点平均电流降至0.65 mA，相当于在单节2,500 mAh电池上估计可无人值守运行159天。结果表明，低成本边缘—云架构无需服务器级硬件即可为微精准农业提供可靠、及时且能源可持续的灌溉控制。","World Academics Journal of Engineering Sciences","2026-09-30T00:00:00Z",{"impact":145,"substance":18,"depth":19,"authority":20,"freshness":118,"relevant":22,"comment":464},"低成本边缘-云架构实现植物胁迫自动诊断与灌溉闭环，数据扎实、结论可靠，对智慧农业节水灌溉有参考价值。",[466],{"name":461,"url":458},[27,135,468,136,30],"农业物联网",{"code":470,"slug":471,"name":472,"path":473,"parent_code":49},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",[475,476],{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":51,"locked":14,"version":52,"method":53,"evidence":478},{"candidates":479,"agricultural_evidence":58},[480,487,491,495,500,505],{"code":470,"score":19,"supported":58,"title":481,"abstract":483,"tags":486},[482],"IoT",[484,485,482],"物联网","internet of things",[468],{"code":45,"score":66,"supported":58,"title":488,"abstract":489,"tags":490},[74],[29,74],[135],{"code":33,"score":13,"supported":58,"title":492,"abstract":493,"tags":494},[],[156,34,60],[136],{"code":40,"score":496,"supported":58,"title":497,"abstract":498,"tags":499},7,[],[69,41],[30],{"code":85,"score":496,"supported":58,"title":501,"abstract":502,"tags":504},[],[503,160],"精准农业",[27],{"code":506,"score":118,"supported":58,"title":507,"abstract":508,"tags":511},"G2",[],[509,510],"小农户","smallholder",[],[513,514],"ESP32 土壤湿度 灌溉 机器学习","随机森林 植物胁迫 诊断","ESP32土壤湿度灌溉机器学习-4076",{"doi":9,"openalex_id":517,"authors":518,"venue":461,"cited_by_count":108,"oa_url":458,"card":525,"direction":268,"ingested_from":115},"W7217836036",[519,521,523],{"name":520,"orcid":9},"Christian Athanas Mwakyusa",{"name":522,"orcid":9},"Allen Deogratius Mwalekwa",{"name":524,"orcid":9},"Gift Geofrey Mushi",{"tldr":526,"method":527,"finding":528,"direction":268,"opportunity":529},"设计并验证了基于ESP32与随机森林的物联网闭环灌溉系统，实现植物胁迫自动诊断。","ESP32、电容式土壤湿度传感器、DHT22、随机森林分类器、Flask云服务。","48小时测试分类准确率96.8%，脱水胁迫召回率97.9%，节点续航约159天。","可探索多作物泛化、极端环境鲁棒性及边缘端轻量化模型部署以降低云依赖。","2026-10-03T23:30:18.857006Z"]