[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3798":3,"related-3798":81},{"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":18,"tags":20,"primary_topic":9,"secondary_topics":25,"classification":26,"search_phrases":55,"slug":58,"view_count":59,"doi":60,"paper":61,"created_at":80},3798,"Debris Flow Susceptibility Mapping Using Explainable Deep Learning in Eastern Hindukush Pakistan","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fesp.70419","ABSTRACT Debris flows are among the most destructive geomorphological hazards in mountainous regions, causing damage to human settlements, infrastructure and ecosystems. The Eastern Hindu Kush region of Pakistan is particularly vulnerable due to steep topography, intense monsoonal precipitation, active tectonics and increasing anthropogenic disturbance. This study develops an integrated debris flow susceptibility assessment framework by combining convolutional neural networks (CNN) with SHapley Additive exPlanations (SHAP). A total of 13 conditioning factors representing topographic, hydrological, geological, environmental and anthropogenic characteristics were prepared using GIS and remote sensing datasets at a spatial resolution of 30 × 30 m. The CNN model demonstrated strong predictive performance, achieving an area under the curve (AUC) of 0.94, overall accuracy (ACC) of 0.86, precision of 0.84, recall of 0.88, an F1‐score of 0.86 and a Kappa coefficient of 0.71. The resulting susceptibility map identified approximately 26.3% of the study area as high to very high susceptibility zones, predominantly concentrated along steep river valleys and highly dissected mountainous terrain. The susceptibility map was further validated by debris flow density analysis, which showed hazard density increasing from 0 events\u002Fkm 2 in very low zones to 0.048 events\u002Fkm 2 in very high zones, with most historical debris flow events concentrated within the very high susceptibility class. SHAP analysis identified slope, NDVI, rainfall, distance to roads and distance to streams as the most influential conditioning factors controlling debris flow occurrence. The proposed CNN–SHAP framework provides a robust and interpretable approach for regional‐scale debris flow susceptibility assessment, with applicability to similar mountainous environments. These findings provide valuable information for hazard mitigation, infrastructure planning and land‐use management in data‐scarce mountain regions.","泥石流是山区最具破坏性的地貌灾害之一，会对人类聚居地、基础设施和生态系统造成损害。巴基斯坦东兴都库什地区由于地形陡峭、季风降水强烈、构造活动活跃以及人为干扰日益加剧，尤为脆弱。本研究通过将卷积神经网络（CNN）与SHapley加法解释（SHAP）相结合，构建了一个综合性的泥石流易发性评估框架。利用GIS和遥感数据集，以30×30 m的空间分辨率制备了代表地形、水文、地质、环境和人为特征的13个 conditioning factors（孕灾因子）。CNN模型表现出较强的预测性能，曲线下面积（AUC）达到0.94，总体精度（ACC）为0.86，精确率为0.84，召回率为0.88，F1分数为0.86，Kappa系数为0.71。所得易发性图识别出约26.3%的研究区域为高至极高易发性区，主要集中于陡峭的河谷和高度切割的山地地形。易发性图进一步通过泥石流密度分析得到验证，结果显示灾害密度从极低区的0 events\u002Fkm²增加到极高区的0.048 events\u002Fkm²，且大多数历史泥石流事件集中在极高易发性类别内。SHAP分析识别出坡度、NDVI、降雨量、距道路距离和距河流距离是控制泥石流发生的最具影响力的孕灾因子。所提出的CNN–SHAP框架为区域尺度泥石流易发性评估提供了一种稳健且可解释的方法，适用于类似的山区环境。这些发现为数据稀缺山区的灾害减缓、基础设施规划和土地利用管理提供了有价值的信息。",null,"Earth Surface Processes and Landforms","2026-09-27T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"泥石流易发性遥感与深度学习研究，属地质灾害领域，与三农、农业信息化无直接关联，不建议进入每日精选。",[19],{"name":10,"url":6},[21,22,23,24],"深度学习","SHAP","遥感监测","地质灾害",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":30},"needs_review","2026-10-22.2","rules",{"candidates":31,"agricultural_evidence":14,"reason":54},[32,39,47],{"code":33,"score":13,"supported":34,"title":35,"abstract":37,"tags":38},"I2",true,[36],"deep learning",[],[22,21],{"code":40,"score":41,"supported":34,"title":42,"abstract":43,"tags":46},"I3",7,[],[44,45],"遥感","remote sensing",[23],{"code":48,"score":49,"supported":34,"title":50,"abstract":51,"tags":53},"I4",3,[],[52],"GIS",[],"农业相关性需要复核",[56,57],"东兴都库什 泥石流 易发性","CNN SHAP 泥石流","东兴都库什泥石流易发性-3798",4,"10.1002\u002Fesp.70419",{"doi":60,"openalex_id":62,"authors":63,"venue":10,"cited_by_count":15,"oa_url":72,"card":73,"direction":77,"ingested_from":79},"W7214538761",[64,67,69],{"name":65,"orcid":66},"Kashif Ullah","https:\u002F\u002Forcid.org\u002F0000-0003-2880-0977",{"name":68,"orcid":9},"Xi Chen",{"name":70,"orcid":71},"Tie Liu","https:\u002F\u002Forcid.org\u002F0000-0002-6879-4818","https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fpdfdirect\u002F10.1002\u002Fesp.70419",{"tldr":74,"method":75,"finding":76,"direction":77,"opportunity":78},"用CNN结合SHAP绘制巴基斯坦东兴都库什泥石流易发性图并解释关键因子。","CNN模型+SHAP，基于GIS与遥感13个30米条件因子。","高易发区占26.3%，坡度、NDVI、降雨、道路与河流距离最关键。","农业遥感与作物表型","可将CNN-SHAP框架迁移至山区农业灾害风险与耕地安全评估，弥补数据稀缺区研究空白。","openalex","2026-09-29T23:30:30.418175Z",{"total":82,"page":83,"page_size":82,"items":84},6,1,[85,151,208,268,353,402],{"id":86,"title":87,"url":88,"summary":89,"summary_zh":90,"content":9,"source_name":91,"source_url":88,"published_at":92,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":93,"sources":95,"tags":97,"primary_topic":9,"secondary_topics":99,"classification":100,"search_phrases":120,"slug":123,"view_count":15,"doi":124,"paper":125,"created_at":150},4908,"Morphological characteristics and spatial distribution of shallow landslides in the Qinling-Daba Mountains, China","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffeart.2026.1858890","Shallow landslides dominate the hazard inventory of the Qinba Mountains, China, yet their regional-scale characteristics and controlling factors remain poorly understood. Based on 4,315 historical shallow landslides (1998–2022), this study integrates field measurements, GIS-based spatial analysis, and statistical methods to investigate landslide morphology, spatial distribution, and conditioning factors. Methodologically, we used variable-specific correlation analyses (Spearman, Cramér’s V , Kruskal–Wallis H tests) and multi-buffer processing for linear features (faults, rivers, roads). Results reveal: (1) Power law scaling in area-volume ( V = 2.27 A 1.034 ) and size-frequency distribution (exponent 2.27), confirming self-organized criticality of the landslide system. (2) Regional differentiation: the Hanjiang River basin shows a gradient from high-density, small failures upstream to lower-density, larger failures downstream; the Jialingjiang and the Hanjiang tributary basins are dominated by larger landslides due to competent lithologies and higher relief. (3) Key controlling factors: epimetamorphic rocks, elevation \u003C1,000 m, slope \u003C30°, relief \u003C200 m, annual precipitation 800–1,100 mm, NDVI 0.5–0.7, population density >10 persons\u002Fkm 2 , and distance to roads (\u003C500 m), rivers (\u003C1,800 m) and faults (\u003C6,000 m). In general, macro-topography, regional tectonics, and climate collaboratively define the potential locations of landslides, whereas micro-topography, lithology, and vegetation cover govern their scale and type; Human activities change the dominant geometry of landslides to a certain extent. (4) The spatial pattern of landslide in continuous variables is analyzed at a 36 km distance threshold, with mean annual precipitation exhibiting the strongest positive spatial autocorrelation (Moran’s I = 0.93), and LISA maps show High-High clusters of precipitation and coefficient of elevation variation in Ankang, while elevation shows an opposite pattern. These findings provide a scientific basis for hazard mitigation and land-use planning in the Qinba Mountains and offer a methodological framework for landslide susceptibility studies in other geologically similar regions.","浅层滑坡是秦巴山区灾害清单中的主要类型，但其区域尺度特征及控制因素仍缺乏系统认识。基于1998—2022年间4 315处历史浅层滑坡数据，本研究综合野外实测、基于GIS的空间分析与统计方法，探讨了滑坡形态、空间分布及孕灾因素。方法上，采用变量特异性相关分析（Spearman、Cramér's V、Kruskal–Wallis H检验）以及针对线性要素（断层、河流、道路）的多缓冲带处理。结果表明：（1）面积—体积关系（V = 2.27 A^1.034）与规模—频率分布（指数2.27）均呈幂律标度，证实了滑坡系统的自组织临界性。（2）区域分异显著：汉江流域表现为从上游高密度小规模滑坡向下游低密度大规模滑坡的梯度变化；嘉陵江及汉江支流流域因岩性坚硬、地形起伏较大，以较大规模滑坡为主。（3）关键控制因素包括：浅变质岩、海拔\u003C1 000 m、坡度\u003C30°、地形起伏\u003C200 m、年降水量800~1 100 mm、NDVI 0.5~0.7、人口密度>10人\u002Fkm²，以及距道路\u003C500 m、距河流\u003C1 800 m、距断层\u003C6 000 m。总体而言，宏观地形、区域构造与气候共同决定了滑坡的潜在发生位置，而微观地形、岩性与植被覆盖控制其规模与类型；人类活动在一定程度上改变了滑坡的优势几何形态。（4）在36 km距离阈值下分析连续变量的滑坡空间格局，年均降水量表现出最强的正空间自相关（Moran's I = 0.93），LISA图显示安康地区降水量与高程变异系数呈高—高聚集，而高程则呈相反格局。上述发现为秦巴山区灾害减缓与土地利用规划提供了科学依据，并为其他地质条件类似区域的滑坡易发性研究提供了方法框架。","Frontiers in Earth Science","2026-10-13T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":94},"该论文研究秦巴山区浅层滑坡形态与空间分布，属地质灾害与自然地理领域，与三农、农业信息化、智慧农业主题无直接关联，不建议进入每日精选。",[96],{"name":91,"url":88},[23,98,24],"滑坡灾害",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":101},{"candidates":102,"agricultural_evidence":14,"reason":54},[103,110,116],{"code":48,"score":104,"supported":34,"title":105,"abstract":106,"tags":109},9,[],[107,52,108],"空间分析","spatial analysis",[],{"code":111,"score":49,"supported":34,"title":112,"abstract":113,"tags":115},"I7",[],[114],"methodological framework",[],{"code":40,"score":83,"supported":14,"title":117,"abstract":118,"tags":119},[],[],[23],[121,122],"秦岭大巴山 浅层滑坡","秦巴山区 滑坡分布","秦岭大巴山浅层滑坡-4908","10.3389\u002Ffeart.2026.1858890",{"doi":124,"openalex_id":126,"authors":127,"venue":91,"cited_by_count":15,"oa_url":143,"card":144,"direction":149,"ingested_from":79},"W7221663082",[128,130,132,134,136,139,141],{"name":129,"orcid":9},"Dingchao Qi",{"name":131,"orcid":9},"Wen Fan",{"name":133,"orcid":9},"Deng Longsheng",{"name":135,"orcid":9},"Yufei Song",{"name":137,"orcid":138},"Jun Li","https:\u002F\u002Forcid.org\u002F0000-0001-9198-0945",{"name":140,"orcid":9},"Yanbo Cao",{"name":142,"orcid":9},"Yiwei Ji","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fearth-science\u002Farticles\u002F10.3389\u002Ffeart.2026.1858890\u002Fpdf",{"tldr":145,"method":146,"finding":147,"direction":77,"opportunity":148},"基于4315个浅层滑坡数据，分析秦巴山区滑坡形态、空间分布及控制因素。","GIS空间分析、Spearman\u002FCramér's V\u002FKruskal-Wall","滑坡面积-体积呈幂律关系，宏观地形构造气候定位置，微观岩性植被定规模。","可结合遥感与机器学习构建滑坡易发性动态模型，并探究农业活动对滑坡的驱动机制。","农业人工智能与决策模型","2026-10-14T23:30:47.340224Z",{"id":152,"title":153,"url":154,"summary":155,"summary_zh":156,"content":9,"source_name":157,"source_url":154,"published_at":158,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":159,"sources":161,"tags":163,"primary_topic":9,"secondary_topics":165,"classification":166,"search_phrases":178,"slug":181,"view_count":49,"doi":182,"paper":183,"created_at":207},4231,"CrossCD-Eval: a unified framework with domain-aware feature normalization for cross-domain remote sensing change detection","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-70914-7","Abstract Change detection (CD) in remote sensing imagery is essential for monitoring urban growth, land-use transformation, and environmental dynamics. However, cross-domain change detection remains challenging due to distribution shifts caused by differences in geographic regions, spatial resolutions, sensor\u002Facquisition conditions, temporal periods, and annotation protocols. This paper introduces CrossCD-Eval, a unified framework for evaluating the generalization of deep learning-based change detection models under in-domain, cross-domain, and few-shot domain adaptation settings. Five recent models, namely GLAFormer 1 , Change-Mamba 2 , EHCTNet 3 , ELGC-Net 4 , and STNet 5 , are evaluated using CLCD, HRSCD, and LEVIR-CD. To reduce representation-level domain mismatch, we propose a Domain-Aware Feature Normalization (DAFN) module that aligns source and target feature statistics as a lightweight feature-level adaptation component. Experimental results show that all models achieve strong in-domain performance but degrade under cross-domain transfer, confirming the impact of domain shift. DAFN improves cross-domain and few-shot adaptation performance, with larger gains observed under more challenging source–target shifts. Repeated 10-shot experiments over five random target-sample selections further show that DAFN improves adaptation stability, reducing IoU standard deviation by up to 22.7%. An additional ablation and baseline-comparison study demonstrates that the observed gains are not solely due to preprocessing. Compared with full preprocessing, AdaBN, adversarial feature alignment, and the instance-normalization-based CrossCDNet baseline, DAFN provides additional feature-level adaptation benefits, especially when combined with strong backbones such as STNet.","摘要 遥感影像中的变化检测（CD）对于监测城市扩张、土地利用转变和环境动态至关重要。然而，由于地理区域、空间分辨率、传感器\u002F采集条件、时间段和标注协议差异所导致的分布偏移，跨域变化检测仍然具有挑战性。本文提出CrossCD-Eval，一个用于评估基于深度学习的变化检测模型在域内、跨域和少样本域适应设置下泛化能力的统一框架。使用CLCD、HRSCD和LEVIR-CD对五个近期模型进行了评估，即GLAFormer 1、Change-Mamba 2、EHCTNet 3、ELGC-Net 4和STNet 5。为减少表示层面的域不匹配，我们提出域感知特征归一化（DAFN）模块，作为轻量级特征级适应组件，对齐源域和目标域的特征统计量。实验结果表明，所有模型均取得较强的域内性能，但在跨域迁移时性能下降，证实了域偏移的影响。DAFN提升了跨域和少样本适应性能，在更具挑战性的源-目标偏移下增益更大。在五次随机目标样本选择上重复进行的10-shot实验进一步表明，DAFN提升了适应稳定性，将IoU标准差最多降低22.7%。额外的消融和基线对比研究表明，所观察到的增益并非仅由预处理所致。与完整预处理、AdaBN、对抗特征对齐以及基于实例归一化的CrossCDNet基线相比，DAFN提供了额外的特征级适应收益，尤其是与STNet等强骨干网络结合时。","Scientific Reports","2026-10-03T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":160},"属遥感变化检测通用方法研究，未涉及农业场景，与三农及农业信息化主题不相关。",[162],{"name":157,"url":154},[21,23,164],"变化检测",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":167},{"candidates":168,"agricultural_evidence":14,"reason":54},[169,174],{"code":40,"score":170,"supported":34,"title":171,"abstract":172,"tags":173},15,[45],[44,45],[23],{"code":33,"score":41,"supported":34,"title":175,"abstract":176,"tags":177},[],[21,36],[21],[179,180],"CrossCD-Eval 跨域变化检测","遥感变化检测 域自适应","CrossCD-Eval跨域变化检测-4231","10.1038\u002Fs41598-026-70914-7",{"doi":182,"openalex_id":184,"authors":185,"venue":157,"cited_by_count":15,"oa_url":201,"card":202,"direction":77,"ingested_from":79},"W7218559287",[186,189,192,195,198],{"name":187,"orcid":188},"Menna M. Elkholy","https:\u002F\u002Forcid.org\u002F0000-0003-4475-5424",{"name":190,"orcid":191},"Hala M. Ebied","https:\u002F\u002Forcid.org\u002F0000-0001-9843-842X",{"name":193,"orcid":194},"Mohamed F. Tolba","https:\u002F\u002Forcid.org\u002F0000-0003-3104-6418",{"name":196,"orcid":197},"Marwa S. Moustafa","https:\u002F\u002Forcid.org\u002F0000-0003-3805-9668",{"name":199,"orcid":200},"Dina Elsayad","https:\u002F\u002Forcid.org\u002F0000-0003-3934-7637","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-70914-7.pdf",{"tldr":203,"method":204,"finding":205,"direction":77,"opportunity":206},"提出统一框架CrossCD-Eval评估跨域遥感变化检测，并设计DAFN模块提升跨域泛化。","在CLCD、HRSCD、LEVIR-CD上评测五种模型，提出域感知特征归一化DA","模型域内表现强但跨域下降，DAFN提升跨域与少样本适应，IoU标准差最多降22.7%。","可将DAFN用于农业跨区域\u002F跨传感器作物变化监测，探索轻量域适应与少样本迁移。","2026-10-05T23:30:25.083737Z",{"id":209,"title":210,"url":211,"summary":212,"summary_zh":213,"content":9,"source_name":157,"source_url":211,"published_at":214,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":215,"sources":217,"tags":219,"primary_topic":9,"secondary_topics":222,"classification":223,"search_phrases":234,"slug":237,"view_count":15,"doi":238,"paper":239,"created_at":267},4088,"Empirically informed AHP-FR modeling for multi-hazard susceptibility mapping in a mountainous transport corridors","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-66468-3","Abstract Mountainous transport corridors are increasingly exposed to interacting natural hazards that intensify infrastructure, socio-economic, and land-use risks. However, most susceptibility assessments for high-mountain corridors still focus on single hazards or rely heavily on expert-based weighting, which can introduce subjectivity into spatial decision-making. This study develops an empirically informed Analytical Hierarchy Process–Frequency Ratio (AHP-FR) framework for integrated landslide, debris-flow, and flood susceptibility mapping along the Barakhan–Gilgit–Juglot section of the northern China–Pakistan Economic Corridor (CPEC). The main methodological contribution is the use of frequency-ratio-derived empirical evidence that was integrated with AHP-derived factor weights to calculate final subclass weights and thereby reducing reliance on purely subjective expert judgment. Field surveys, remote sensing datasets, historical hazard inventories, and 12 conditioning factors were integrated in a GIS environment to generate single-hazard susceptibility maps and an eight-class multi-hazard susceptibility map. Independent ROC-AUC validation showed acceptable to very good predictive performance, with AUC values of 0.803 for landslides, 0.762 for debris flows, and 0.872 for floods. The results indicate that 63% of the corridor is exposed to one or more hazards, including 59% exposed to two or more overlapping hazards; 41% are co-susceptible to landslides and debris flows, while 37% falls within the no\u002Fvery low multi-hazard susceptibility class. The spatial outputs identify major hazard-prone sections, including Attabad, Chalt, and Passu, providing practical guidance for road-maintenance prioritization, slope-stabilization planning, drainage improvement, and emergency preparedness. The added value of this study lies in combining empirical FR-based weighting with AHP and translating separate hazard maps into explicit multi-hazard combination classes, offering a reproducible decision-support framework for resilient planning in mountainous transport corridors.","摘要 山区交通走廊日益暴露于相互作用的自然灾害之下，这些灾害加剧了基础设施、社会经济和土地利用风险。然而，大多数高山走廊的易发性评估仍集中于单一灾害，或严重依赖基于专家经验的权重赋值，这可能在空间决策中引入主观性。本研究开发了一种基于经验数据的层次分析法-频率比（AHP-FR）框架，用于中巴经济走廊（CPEC）北段Barakhan–Gilgit–Juglot沿线滑坡、泥石流和洪水灾害的综合易发性制图。该方法的主要贡献在于利用频率比衍生的经验证据，将其与AHP衍生的因子权重相结合，以计算最终子类权重，从而减少对纯主观专家判断的依赖。研究在GIS环境中整合了野外调查、遥感数据集、历史灾害编目和12个致灾因子，生成了单灾种易发性图和八类多灾种易发性图。独立的ROC-AUC验证显示预测性能处于可接受到很好水平，滑坡AUC值为0.803，泥石流为0.762，洪水为0.872。结果表明，该走廊63%的区域暴露于一种或多种灾害，其中59%暴露于两种或以上重叠灾害；41%同时易受滑坡和泥石流影响，而37%属于无\u002F极低多灾种易发性类别。空间输出结果识别出主要灾害易发路段，包括Attabad、Chalt和Passu，为道路维护优先级排序、边坡稳定规划、排水改善和应急准备提供了实践指导。本研究的增值在于将基于经验FR的权重与AHP相结合，并将各单灾种图转化为明确的多灾种组合类别，为山区交通走廊的韧性规划提供了可重复的决策支持框架。","2026-10-01T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":216},"该论文聚焦山区交通走廊多灾种易发性制图，属地质灾害与遥感领域，与三农、农业信息化、智慧农业主题无关，不建议进入每日精选。",[218],{"name":157,"url":211},[23,24,220,221],"中巴经济走廊","多灾种评估",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":224},{"candidates":225,"agricultural_evidence":14,"reason":54},[226,230],{"code":40,"score":41,"supported":34,"title":227,"abstract":228,"tags":229},[],[44,45],[23],{"code":48,"score":49,"supported":34,"title":231,"abstract":232,"tags":233},[],[52],[],[235,236],"中巴经济走廊 地质灾害","AHP-FR 滑坡 泥石流","中巴经济走廊地质灾害-4088","10.1038\u002Fs41598-026-66468-3",{"doi":238,"openalex_id":240,"authors":241,"venue":157,"cited_by_count":15,"oa_url":261,"card":262,"direction":77,"ingested_from":79},"W7215052453",[242,245,248,250,252,254,256,259],{"name":243,"orcid":244},"Muhammad Awais Hussain","https:\u002F\u002Forcid.org\u002F0000-0001-6223-8020",{"name":246,"orcid":247},"Xinyu Xie","https:\u002F\u002Forcid.org\u002F0000-0002-0750-0599",{"name":249,"orcid":9},"Chenxu Su",{"name":251,"orcid":9},"Fatima Mehvish",{"name":253,"orcid":9},"Muhammad Muneer",{"name":255,"orcid":9},"Muhammad Akbar",{"name":257,"orcid":258},"Ahmed Othman Alanazi","https:\u002F\u002Forcid.org\u002F0009-0002-6500-8903",{"name":260,"orcid":9},"Masamba Pinto¹","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-66468-3_reference.pdf",{"tldr":263,"method":264,"finding":265,"direction":77,"opportunity":266},"提出AHP-FR经验加权框架，绘制中巴经济走廊山区多灾种易发性图。","频率比与AHP结合，GIS整合野外调查、遥感与12个致灾因子。","63%走廊暴露于至少一种灾害，59%面临两种以上重叠灾害。","可将该多灾种易发性框架迁移至农业基础设施与农田受灾风险评估。","2026-10-03T23:30:33.771580Z",{"id":269,"title":270,"url":271,"summary":272,"summary_zh":273,"content":9,"source_name":274,"source_url":271,"published_at":275,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":276,"score_detail":277,"sources":284,"tags":286,"primary_topic":9,"secondary_topics":290,"classification":291,"search_phrases":326,"slug":329,"view_count":49,"doi":330,"paper":331,"created_at":352},3479,"Artificial Intelligence-Enabled Mangrove Ecosystem Monitoring Using Remote Sensing and Environmental Data","https:\u002F\u002Fdoi.org\u002F10.68012\u002Fair.v1i2.252","Mangrove ecosystems play a critical role in coastal protection, carbon sequestration, biodiversity conservation, and climate change mitigation; however, increasing anthropogenic pressures and environmental changes have accelerated mangrove degradation, creating an urgent need for efficient and scalable monitoring approaches. This study aims to develop an Artificial Intelligence-Enabled framework for monitoring mangrove ecosystem conditions by integrating remote sensing imagery with environmental datasets to improve the accuracy and timeliness of ecosystem assessment in tropical coastal regions. The proposed method combines multispectral satellite images, including vegetation indices derived from remote sensing data, with environmental variables such as temperature, precipitation, salinity, and tidal information, which are subsequently processed using a deep learning-based classification model to identify and categorize mangrove health conditions. Experimental evaluation demonstrates that the integration of remote sensing and environmental data significantly enhances model performance compared with approaches relying solely on satellite imagery, achieving high classification accuracy and improving the detection of early signs of ecosystem degradation. The findings further reveal that environmental parameters contribute substantially to distinguishing healthy, moderately degraded, and severely degraded mangrove areas across heterogeneous coastal environments. Consequently, the proposed framework provides an intelligent and reliable decision support tool for environmental monitoring agencies and policymakers while contributing to the development of resilient coastal ecosystem management and sustainable environmental governance in tropical archipelagic regions.","红树林生态系统在海岸防护、碳固存、生物多样性保护及气候变化减缓中发挥着关键作用；然而，日益加剧的人为压力和环境变化加速了红树林退化，亟需高效且可扩展的监测方法。本研究旨在开发一个人工智能驱动的框架，通过整合遥感影像与环境数据集来监测红树林生态系统状况，以提高热带沿海地区生态系统评估的准确性和时效性。所提出的方法将多光谱卫星影像（包括由遥感数据衍生的植被指数）与温度、降水、盐度和潮汐信息等环境变量相结合，随后使用基于深度学习的分类模型进行处理，以识别和分类红树林健康状况。实验评估表明，与仅依赖卫星影像的方法相比，遥感与环境数据的整合显著提升了模型性能，实现了较高的分类精度，并改善了对生态系统退化早期迹象的检测。研究结果进一步揭示，环境参数对于区分异质性沿海环境中健康、中度退化和严重退化的红树林区域具有重要贡献。因此，所提出的框架为环境监测机构和政策制定者提供了一种智能且可靠的决策支持工具，同时有助于热带群岛地区韧性沿海生态系统管理和可持续环境治理的发展。","AI Innovation and Resilience for the Environment (AIR)","2026-09-22T00:00:00Z",76,{"impact":278,"substance":279,"depth":280,"authority":281,"freshness":282,"relevant":83,"comment":283},18,21,17,12,8,"将遥感与环境数据融合的深度学习框架用于红树林健康监测，方法有创新且结论可靠，对沿海生态治理有参考价值，但属细分领域研究，公共影响有限。",[285],{"name":274,"url":271},[287,21,23,288,289],"农业人工智能","生态监测","红树林",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":292},{"candidates":293,"agricultural_evidence":14,"reason":54},[294,301,306,313,320],{"code":33,"score":295,"supported":34,"title":296,"abstract":298,"tags":300},19,[297],"artificial intelligence",[21,36,297,299],"decision support",[287,21],{"code":40,"score":278,"supported":34,"title":302,"abstract":303,"tags":305},[45],[44,45,304],"multispectral",[23],{"code":307,"score":282,"supported":34,"title":308,"abstract":309,"tags":312},"H6",[],[310,311],"生物多样性","biodiversity",[288,289],{"code":314,"score":82,"supported":34,"title":315,"abstract":316,"tags":319},"H7",[],[317,318],"气候变化","climate change",[],{"code":321,"score":49,"supported":34,"title":322,"abstract":323,"tags":325},"H4",[],[324],"carbon sequestration",[],[327,328],"红树林 遥感 人工智能","红树林生态系统 监测","红树林遥感人工智能-3479","10.68012\u002Fair.v1i2.252",{"doi":330,"openalex_id":332,"authors":333,"venue":274,"cited_by_count":15,"oa_url":345,"card":346,"direction":351,"ingested_from":79},"W7213895268",[334,337,340,342],{"name":335,"orcid":336},"Dirvi Surya Abbas","https:\u002F\u002Forcid.org\u002F0000-0002-7819-2837",{"name":338,"orcid":339},"Asep Sutarman","https:\u002F\u002Forcid.org\u002F0009-0002-1029-7963",{"name":341,"orcid":9},"Ryan Davis",{"name":343,"orcid":344},"Maulana Abbas","https:\u002F\u002Forcid.org\u002F0009-0009-0137-9650","https:\u002F\u002Fjournal.sundarapublishing.com\u002Findex.php\u002Fair\u002Farticle\u002Fdownload\u002F252\u002F142",{"tldr":347,"method":348,"finding":349,"direction":77,"opportunity":350},"融合遥感影像与环境数据，用深度学习构建红树林生态系统健康监测框架。","多光谱卫星影像与植被指数，结合温度、降水、盐度、潮汐等环境变量，训练深度学习分类","融合环境数据显著提升分类精度，能更早识别红树林退化迹象，有效区分不同退化程度。","可探索多源时序遥感与环境数据融合的早期退化预警，并迁移至其他滨海湿地生态系统监测。","智慧农业 \u002F 农业物联网","2026-09-25T23:30:14.373467Z",{"id":354,"title":355,"url":356,"summary":357,"summary_zh":358,"content":9,"source_name":359,"source_url":356,"published_at":360,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":361,"sources":363,"tags":365,"primary_topic":9,"secondary_topics":368,"classification":369,"search_phrases":381,"slug":384,"view_count":59,"doi":385,"paper":386,"created_at":401},3188,"Identification of granitic pegmatites based on GF-5 hyperspectral data and LSTM-Transformer model","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.acags.2026.100406","Lithium is a key strategic mineral to support new energy and advanced technology, mainly enriched in granitic pegmatite. The integration of hyperspectral remote sensing and deep learning frameworks has emerged as a leading approach for quantitative identification of pegmatites. However, deep learning algorithms are often limited by the scarcity of labeled samples and the challenge of extracting features from high-dimensional spectral data. In this study, a data augmentation-driven LSTM-Transformer framework is proposed for pegmatite mapping using GF-5 hyperspectral remote sensing data. In view of limited samples, this study constructed an enhanced training data set by integrating field-measured and infrared scanning spectra, simulating real spectral variability and linear mixing to improve data diversity. The proposed LSTM-Transformer architecture combines LSTM’s advantages in local sequence feature modeling and Transformer’s capacity to capture long-range global relationships, thereby enhancing the detection of weakly diagnostic spectral features. The framework was demonstrated in the Jingerquan lithium deposit, Xinjiang, China. The high-probability areas delineated by the proposed model successfully captured several pegmatite dikes documented in previous geological studies. The prediction results were further validated through field sampling. Geochemical analyses of specimens collected from the predicted high-probability target areas show an average Li 2 O grade of 7.86 wt.%, which meets industrial requirements and confirms the reliability of the proposed method. Overall, these results provide the potential of the proposed framework for pegmatite mapping and subsequent mineral exploration under the conditions of limited labeled samples.","锂是支撑新能源与先进技术的关键战略矿产，主要富集于花岗伟晶岩中。高光谱遥感与深度学习框架的融合已成为伟晶岩定量识别的前沿方法。然而，深度学习算法常受限于标注样本稀缺以及高维光谱数据特征提取的难题。本研究提出了一种数据增强驱动的LSTM-Transformer框架，用于基于GF-5高光谱遥感数据的伟晶岩填图。针对样本有限的问题，本研究通过整合野外实测光谱与红外扫描光谱构建了增强训练数据集，模拟真实光谱变异与线性混合以提升数据多样性。所提出的LSTM-Transformer架构结合了LSTM在局部序列特征建模方面的优势与Transformer捕捉长程全局关系的能力，从而增强了对弱诊断光谱特征的检测。该框架在中国新疆镜儿泉锂矿床进行了验证。所提模型圈定的高概率区域成功捕获了以往地质研究中记录的若干伟晶岩脉。预测结果进一步通过野外采样得到验证。从预测高概率目标区采集的标本地球化学分析显示，Li₂O平均品位为7.86 wt.%，满足工业要求，证实了所提方法的可靠性。总体而言，这些结果展示了所提框架在标注样本有限条件下用于伟晶岩填图及后续矿产勘查的潜力。","Applied Computing and Geosciences","2026-09-19T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":362},"该论文聚焦高光谱遥感与深度学习用于伟晶岩型锂矿识别，属地质矿产勘探领域，与三农、农业信息化、智慧农业主题无关，不建议进入每日精选。",[364],{"name":359,"url":356},[21,23,366,367],"高光谱遥感","锂矿勘探",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":370},{"candidates":371,"agricultural_evidence":14,"reason":54},[372,377],{"code":40,"score":295,"supported":34,"title":373,"abstract":375,"tags":376},[374],"hyperspectral",[44,45,374],[23,366],{"code":33,"score":41,"supported":34,"title":378,"abstract":379,"tags":380},[],[21,36],[21],[382,383],"GF-5 高光谱 伟晶岩","新疆 镜儿泉 锂矿","GF-5高光谱伟晶岩-3188","10.1016\u002Fj.acags.2026.100406",{"doi":385,"openalex_id":387,"authors":388,"venue":359,"cited_by_count":15,"oa_url":395,"card":396,"direction":77,"ingested_from":79},"W7213617576",[389,392],{"name":390,"orcid":391},"Zhong Li","https:\u002F\u002Forcid.org\u002F0000-0002-2312-3746",{"name":393,"orcid":394},"Ziye Wang","https:\u002F\u002Forcid.org\u002F0000-0001-6538-5798","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS259019742600090X\u002Fpdf",{"tldr":397,"method":398,"finding":399,"direction":77,"opportunity":400},"提出数据增强驱动的LSTM-Transformer框架，用GF-5高光谱数据识别花岗伟晶岩。","GF-5高光谱数据，融合实测与红外扫描光谱增强样本，构建LSTM-Transfo","在新疆金儿泉锂矿成功圈定伟晶岩脉，验证区Li2O平均品位7.86 wt.%。","可将该高光谱-深度学习框架迁移至农田土壤属性或作物养分反演，解决标签稀缺问题。","2026-09-22T23:30:25.608490Z",{"id":403,"title":404,"url":405,"summary":406,"summary_zh":407,"content":9,"source_name":408,"source_url":405,"published_at":360,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":409,"sources":411,"tags":413,"primary_topic":416,"secondary_topics":421,"classification":422,"search_phrases":438,"slug":441,"view_count":59,"doi":442,"paper":443,"created_at":454},3015,"Forecasting Urbanization Dynamics On İstanbul’s European Side Using Deep Learning And Extrapolation Techniques","https:\u002F\u002Fdoi.org\u002F10.2478\u002Fjlecol-2026-0037","Abstract Rapid urbanization in metropolitan regions poses significant environmental, social, and infrastructural challenges, necessitating advanced analytical approaches to monitor and predict urban growth. This study investigates the spatio-temporal dynamics of urbanization on the European side of Istanbul from 2013 to 2024 using Landsat 8 imagery and a deep learning (DL)–based Land Cover Classification model integrated within ArcGIS Pro. The U-Net–based pre-trained model generated 15-class Land Use\u002FLand Cover (LULC) maps, which were validated against the Urban Atlas dataset, resulting in high classification accuracies for forest and water classes (PA: 0.84–0.94; UA: 0.87–0.87) and an overall binary urban\u002Fnon-urban accuracy of 87 %, confirming the robustness of the employed DL approach. Spatio-temporal analyses of LULC data were conducted using both Ordinary Least Squares (OLS) and nonlinear regression functions to examine urban growth trends and project future development for 2025, 2026, and 2027. The results indicate a strong linear increase in urbanized areas across most districts, with total developed area on the European side projected to reach approximately 807 km² by 2027, representing a nearly 50% increase compared to 2013. These findings highlight the significant pressure of urban expansion on natural and agricultural lands and emphasize the need for informed planning strategies. By integrating remote sensing, deep learning, and predictive modeling, this study provides actionable insights for sustainable urban development, offering a replicable framework for monitoring rapid urbanization and supporting policy decisions to mitigate environmental and socio-spatial impacts in rapidly growing metropolitan regions.","摘要 大都市区域的快速城市化带来了显著的环境、社会和基础设施挑战，亟需先进的分析方法来监测和预测城市增长。本研究利用Landsat 8影像和集成于ArcGIS Pro中的基于深度学习（DL）的土地覆盖分类模型，研究了2013年至2024年伊斯坦布尔欧洲一侧城市化的时空动态。基于U-Net的预训练模型生成了15类土地利用\u002F土地覆盖（LULC）地图，并依据Urban Atlas数据集进行了验证，森林和水体类别的分类精度较高（生产者精度PA：0.84–0.94；用户精度UA：0.87–0.87），城市\u002F非城市二分类总体精度达87%，证实了所采用深度学习方法稳健可靠。研究采用普通最小二乘法（OLS）和非线性回归函数对LULC数据进行时空分析，以考察城市增长趋势并预测2025年、2026年和2027年的未来发展。结果表明，大多数区域的城市化面积呈显著线性增长，预计到2027年欧洲一侧的总建成区面积将达到约807 km²，较2013年增长近50%。这些发现凸显了城市扩张对自然和农业用地的巨大压力，并强调了科学规划策略的必要性。通过整合遥感、深度学习和预测建模，本研究为可持续城市发展提供了可操作的见解，为监测快速城市化提供了一个可复制的框架，并支持旨在缓解快速增长的都市区域中环境和社会空间影响的政策决策。","Journal of Landscape Ecology",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":410},"研究伊斯坦布尔城市扩张与土地覆盖预测，属城市遥感与景观生态领域，与三农、农业信息化、智慧农业无直接关联，不建议进入每日精选。",[412],{"name":408,"url":405},[21,23,414,415],"土地利用","城市扩张",{"code":33,"slug":417,"name":418,"path":419,"parent_code":420},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":423,"locked":14,"version":28,"method":29,"evidence":424},"classified",{"candidates":425,"agricultural_evidence":34},[426,430,434],{"code":33,"score":170,"supported":34,"title":427,"abstract":428,"tags":429},[36],[21,36],[21],{"code":40,"score":41,"supported":34,"title":431,"abstract":432,"tags":433},[],[44,45],[23],{"code":307,"score":83,"supported":14,"title":435,"abstract":436,"tags":437},[],[],[414],[439,440],"伊斯坦布尔 城市扩张 遥感","U-Net 土地覆盖分类","伊斯坦布尔城市扩张遥感-3015","10.2478\u002Fjlecol-2026-0037",{"doi":442,"openalex_id":444,"authors":445,"venue":408,"cited_by_count":15,"oa_url":405,"card":449,"direction":77,"ingested_from":79},"W7213670913",[446],{"name":447,"orcid":448},"Gizem Dinç","https:\u002F\u002Forcid.org\u002F0000-0003-2406-604X",{"tldr":450,"method":451,"finding":452,"direction":77,"opportunity":453},"用Landsat 8影像和U-Net深度学习模型分析伊斯坦布尔欧洲侧2013-2024年城市化动态并","Landsat 8影像、ArcGIS Pro中U-Net预训练模型生成15类LU","城市面积呈强线性增长，2027年预计达807 km²，较2013年增长近50%，挤压自然与农业用地。","可借鉴该遥感+深度学习+外推框架，研究快速城市化对城郊农业用地与耕地保护的时空影响。","2026-09-20T23:30:21.335156Z"]