[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2871":3,"related-2871":90},{"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":9,"secondary_topics":32,"classification":33,"search_phrases":59,"slug":62,"view_count":63,"doi":64,"paper":65,"created_at":89},2871,"Spatial and Temporal characteristics and driving force analysis of vegetation cover change in Shanxi Province, China based on kNDVI and XGBoost-SHAP model","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffenvs.2026.1948848","Introduction Systematically clarifying the spatiotemporal evolution of vegetation coverage and elucidating its response mechanisms to climatic fluctuations and human activities carries substantial practical implications for advancing the Dual Carbon Strategy and optimizing the pattern of territorial spatial development and conservation across Shanxi Province, China. Methods Based on kernel Normalized Difference Vegetation Index (kNDVI) datasets, multi-source meteorological, topographic and socioeconomic datasets, this study integrated Theil-Sen slope estimation, Mann-Kendall significance test, Hurst exponent, standard deviational ellipse and gravity center migration model to systematically characterize the spatiotemporal patterns of vegetation coverage for the period 2000 to 2024 and predict the potential persistence of its future evolution. Meanwhile, an interpretable XGBoost-SHAP machine learning framework was constructed to quantify the independent contributions, nonlinear marginal responses, and temporal evolutionary characteristics of seven driving factors: elevation, slope, aspect, annual mean temperature, annual mean precipitation, population density and nighttime light intensity. Results (1) Temporally, the multi-year average kNDVI of the whole province reached approximately 0.1699, presenting an extremely significant fluctuating upward trend with an annual growth rate of 0.0041. Annual kNDVI ranges from 0.1132 recorded in 2001 to a peak value of 0.2227 in 2024. (2) Spatially, vegetation coverage exhibited a remarkable differentiation pattern of “low values in the north and high values in the south”. Higher kNDVI values were predominantly distributed within the forest-covered mountainous regions of the Taihang, Lüliang, Zhongtiao, and Taiyue Mountains, whereas relatively low values were distributed across the sandy-hilly regions of northern Shanxi and urban agglomerations along the Fen River Valley. Vegetation restoration was observed across 98.02% of the study area, among which roughly 92.18% exhibited an extremely significant improvement. (3) Over 2000–2024, the major axis of vegetation spatial distribution maintained a stable northeast-southwest orientation, accompanied by moderate outward expansion of the standard deviational ellipse, and a general northwestward shift of the vegetation gravity centre. (4) The Hurst exponent indicated that the vegetation improvement trend in 98.03% of the region would persist, while scattered patches of industrial, mining and urban land (accounting for 1.97%) faced the potential vegetation degradation risk. (5) The regional vegetation driving system experienced three evolutionary stages: a single precipitation-dominated natural driving stage (2000–2005), a climate-human coupled transitional stage (2005–2010), and a multi-factor synergistic balanced stage (2010–2020). Precipitation and temperature acted as core climatic drivers, and elevation largely determined the vertical differentiation baseline of vegetation distribution. Population density and nighttime light intensity exerted persistent suppressive effects on vegetation growth. Empirically derived tentative thresholds are identified for major predictors: elevation ∼1,200 m, slope ∼8°, annual mean temperature ∼7.5 °C, annual mean precipitation ∼500 mm, population density 500 persons\u002Fkm 2 , and nighttime light intensity ∼5. These values can serve as reference boundaries for differentiating ecological conservation zones from human-disturbed zones. Conclusion This research identified the intertemporal differentiation and nonlinear coupling laws governing vegetation dynamics in Shanxi Province, a temperate transition zone on the Loess Plateau. Differentiated ecological governance strategies targeting climate adaptation, topographic zoning, and anthropogenic-pressure regulation are proposed, which provide observational scientific support for the construction of ecological security barriers on China’s Loess Plateau.","引言 系统厘清植被覆盖的时空演变规律并阐明其对气候波动与人类活动的响应机制，对推进双碳战略、优化山西省国土空间开发保护格局具有重要现实意义。方法 基于核归一化植被指数（kNDVI）数据集及多源气象、地形和社会经济数据，本研究综合运用Theil-Sen斜率估计、Mann-Kendall显著性检验、Hurst指数、标准差椭圆和重心迁移模型，系统刻画了2000—2024年植被覆盖的时空格局，并预测其未来演变的潜在持续性。同时，构建了可解释的XGBoost-SHAP机器学习框架，量化了高程、坡度、坡向、年平均气温、年平均降水量、人口密度和夜间灯光强度7个驱动因子的独立贡献、非线性边际响应及时间演变特征。结果 （1）时间上，全省多年平均kNDVI约为0.1699，呈极显著波动上升趋势，年增长率为0.0041。年kNDVI从2001年的0.1132变化至2024年的峰值0.2227。（2）空间上，植被覆盖呈现“北低南高”的显著分异格局。较高kNDVI值主要分布于太行山、吕梁山、中条山和太岳山等森林覆盖山区，而较低值分布于晋北沙丘丘陵区和汾河谷地城市群。研究区98.02%的区域植被呈恢复态势，其中约92.18%表现为极显著改善。（3）2000—2024年间，植被空间分布的主轴保持稳定的东北—西南走向，标准差椭圆呈中度向外扩张，植被重心总体向西北方向迁移。（4）Hurst指数表明，98.03%区域的植被改善趋势将持续，而零星斑块区域的工业",null,"Frontiers in Environmental Science","2026-09-17T00:00:00Z","论文",10,false,82,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,23,19,13,9,1,"基于kNDVI与XGBoost-SHAP的山西植被时空演变与驱动力研究，方法新颖、数据扎实，对黄土高原生态治理有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"机器学习","生态保护","遥感监测","植被覆盖","黄土高原",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":14,"reason":58},[39,47,53],{"code":40,"score":41,"supported":42,"title":43,"abstract":44,"tags":46},"I2",7,true,[],[27,45],"machine learning",[27],{"code":48,"score":49,"supported":14,"title":50,"abstract":51,"tags":52},"I3",2,[],[],[30,29],{"code":54,"score":22,"supported":14,"title":55,"abstract":56,"tags":57},"H6",[],[],[28],"农业相关性需要复核",[60,61],"山西 kNDVI 植被覆盖","XGBoost-SHAP 植被驱动","山西kNDVI植被覆盖-2871",0,"10.3389\u002Ffenvs.2026.1948848",{"doi":64,"openalex_id":66,"authors":67,"venue":10,"cited_by_count":63,"oa_url":81,"card":82,"direction":86,"ingested_from":88},"W7213469060",[68,70,72,74,76,79],{"name":69,"orcid":9},"Jie Chen",{"name":71,"orcid":9},"Yi Hou",{"name":73,"orcid":9},"Jianhua Xue",{"name":75,"orcid":9},"Jianhua Ni",{"name":77,"orcid":78},"Hao Liu","https:\u002F\u002Forcid.org\u002F0000-0001-8903-0983",{"name":80,"orcid":9},"Pengxiang Gao","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fenvironmental-science\u002Farticles\u002F10.3389\u002Ffenvs.2026.1948848\u002Fpdf",{"tldr":83,"method":84,"finding":85,"direction":86,"opportunity":87},"基于kNDVI与XGBoost-SHAP分析山西2000-2024年植被覆盖时空变化及驱动机制。","kNDVI数据结合Theil-Sen、Mann-Kendall、Hurst指数与","山西植被呈显著上升趋势，98.02%区域改善，驱动因子具非线性与时空差异。","农业遥感与作物表型","可引入多源遥感与作物物候数据，将kNDVI驱动分析拓展至农田尺度精准管理与碳汇评估。","openalex","2026-09-18T23:30:29.212735Z",{"total":91,"page":22,"page_size":91,"items":92},6,[93,180,243,303,398,465],{"id":94,"title":95,"url":96,"summary":97,"summary_zh":98,"content":9,"source_name":99,"source_url":96,"published_at":100,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":101,"score_detail":102,"sources":109,"tags":111,"primary_topic":114,"secondary_topics":119,"classification":120,"search_phrases":145,"slug":148,"view_count":49,"doi":149,"paper":150,"created_at":179},2536,"Mapping Native Grass Cover with Random Forest Models: Sentinel-2 Versus Sentinel-2 Combined with Sentinel-1 SAR-Derived GLCM Texture Metrics","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183150","Temperate native grasslands in southeastern Australia have been extensively cleared for agriculture, and the remaining patches are under growing pressure from further land use change, climate variability, and invasive species. Mapping and monitoring their distribution and the cover of native and exotic grasses are critical for their conservation and management. Field-based methods are not always scalable or time-effective, and this study aimed to develop a scalable method to map and monitor the fractional cover-class maps of native C3 and native C4 grass cover as a component of remnant native grasslands on the western outskirts of Melbourne, Victoria, Australia. Field-based reference data for training and validation of random forest machine learning models were collected across multiple sites in 2021. Sentinel-2 optical spectral bands and vegetation indices were used as the primary input data, and Sentinel-1 Synthetic Aperture Radar (SAR)-derived Grey Level Co-occurrence Matrix (GLCM) texture metrics were assessed for their capacity to improve the model. Results show that random forest models trained on Sentinel-2 data without GLCM texture information derived from Sentinel-1 SAR data provided a moderate overall accuracy (C3: 59.1%, C4: 78.1%). Class-specific metrics showed that reliability was highest for better represented lower-cover classes, particularly the 6–25% native C3 class and the 0–5% native C4 class, while higher-cover classes were less reliable because of the limited number of training and validation samples. Grass cover fractions were modelled well for sparse to moderate grass cover, but dense grass cover was not modelled accurately, probably due to limited high-cover samples in the training dataset. Model performance was not improved by the inclusion of Sentinel-1 SAR-derived GLCM texture metrics, indicating that C-band VH-polarised SAR is not sensitive to the fine-scale structural heterogeneity that characterises native grassland ecosystems. Sparse native C3 and C4 grasses could be mapped most reliably in the lower-cover classes as a component of grasslands with optical remote sensing, and the method developed here can now be applied to enable evidence-based management of grasslands, biodiversity conservation and the monitoring of grassland composition in the WGR and elsewhere. Higher-resolution structural datasets and more sophisticated machine learning approaches may be required to accurately predict native C3 and C4 grass cover fractions in denser grasslands.","澳大利亚东南部的温带原生草原已被大面积开垦用于农业，残余斑块正面临土地利用进一步变化、气候变率和入侵物种日益增大的压力。对其分布以及原生和外来草类覆盖度进行制图和监测，对于草原的保护和管理至关重要。基于实地调查的方法并非总是可扩展或省时的，本研究旨在开发一种可扩展的方法，以制图和监测作为残余原生草原组成部分的原生C3和原生C4草类覆盖度的分数覆盖等级图，研究区位于澳大利亚维多利亚州墨尔本西郊。用于训练和验证随机森林机器学习模型的实地参考数据于2021年在多个样点采集。研究以Sentinel-2光学光谱波段和植被指数作为主要输入数据，并评估了Sentinel-1合成孔径雷达（SAR）衍生的灰度共生矩阵（GLCM）纹理指标对提升模型性能的能力。结果表明，仅使用Sentinel-2数据（不含Sentinel-1 SAR衍生的GLCM纹理信息）训练的随机森林模型提供了中等的总体精度（C3：59.1%，C4：78.1%）。分类别指标显示，对于代表性较好的低覆盖度类别，可靠性最高，尤其是6–25%原生C3类别和0–5%原生C4类别，而较高覆盖度类别的可靠性较低，原因是训练和验证样本数量有限。草类覆盖度分数在稀疏至中等草类覆盖条件下建模效果良好，但茂密草类覆盖未能准确建模，可能是由于训练数据集中高覆盖度样本有限。纳入Sentinel-1 SAR衍生的GLCM纹理指标并未改善模型性能，表明C波段VH极化SAR对原生草原生态系统所特有的精细尺度结构异质性不敏感。作为草原的组成部分，稀疏的原生C3和C4草类在低覆盖度类别中利用光学遥感可最可靠地制图，本研究开发的方法现可应用于西维多利亚草原（WGR）及其他地区，以实现基于证据的草原管理、生物多样性保护和草原组成监测。准确预测原生C3和C4草类覆盖度分数可能需要更高分辨率的结构数据集和更先进的机器学习方法。","Remote Sensing","2026-09-13T00:00:00Z",71,{"impact":103,"substance":104,"depth":105,"authority":106,"freshness":107,"relevant":22,"comment":108},12,20,17,14,8,"方法新颖、结论明确（SAR纹理未提升精度），对草地遥感监测有参考价值，但属细分领域研究，影响范围有限。",[110],{"name":99,"url":96},[112,27,29,113,30],"智慧农业","草原生态",{"code":48,"slug":115,"name":116,"path":117,"parent_code":118},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":121,"locked":14,"version":35,"method":36,"evidence":122},"classified",{"candidates":123,"agricultural_evidence":42},[124,130,136,140],{"code":48,"score":107,"supported":42,"title":125,"abstract":126,"tags":129},[],[127,128],"遥感","remote sensing",[30,29],{"code":54,"score":41,"supported":42,"title":131,"abstract":132,"tags":135},[],[133,134],"生物多样性","biodiversity",[113],{"code":40,"score":41,"supported":42,"title":137,"abstract":138,"tags":139},[],[27,45],[27],{"code":141,"score":22,"supported":14,"title":142,"abstract":143,"tags":144},"I1",[],[],[112],[146,147],"智慧农业 机器学习 植被覆盖 草原生态","智慧农业 机器学习","智慧农业机器学习植被覆盖草原生态-2536","10.3390\u002Frs18183150",{"doi":149,"openalex_id":151,"authors":152,"venue":99,"cited_by_count":63,"oa_url":96,"card":174,"direction":86,"ingested_from":88},"W7212561645",[153,156,159,162,164,166,169,171],{"name":154,"orcid":155},"Sabah Sabaghy","https:\u002F\u002Forcid.org\u002F0000-0002-9453-8922",{"name":157,"orcid":158},"M. Abuzar","https:\u002F\u002Forcid.org\u002F0000-0002-6101-1307",{"name":160,"orcid":161},"Steve J. Sinclair","https:\u002F\u002Forcid.org\u002F0000-0002-4282-1021",{"name":163,"orcid":9},"Tony Dugdale",{"name":165,"orcid":9},"Vanessa Hutchins",{"name":167,"orcid":168},"Yogendra K. Karna","https:\u002F\u002Forcid.org\u002F0000-0002-2120-4710",{"name":170,"orcid":9},"Jonathan Wilson",{"name":172,"orcid":173},"Kathryn Sheffield","https:\u002F\u002Forcid.org\u002F0000-0003-2624-9739",{"tldr":175,"method":176,"finding":177,"direction":86,"opportunity":178},"用随机森林结合Sentinel-2与Sentinel-1纹理特征，绘制澳洲原生草地C3\u002FC4草覆盖度","2021年野外样点训练随机森林，Sentinel-2光谱与植被指数为主，Sent","仅用Sentinel-2精度中等（C3 59.1%、C4 78.1%），加入SAR纹理未提升，高覆盖","高覆盖度草地样本不足且C波段SAR不敏感，可探索高分辨率结构数据与深度模型提升密草覆盖反演。","2026-09-15T23:30:21.287053Z",{"id":181,"title":182,"url":183,"summary":184,"summary_zh":185,"content":9,"source_name":186,"source_url":183,"published_at":187,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":188,"score_detail":189,"sources":192,"tags":194,"primary_topic":9,"secondary_topics":197,"classification":198,"search_phrases":213,"slug":216,"view_count":22,"doi":217,"paper":218,"created_at":242},2430,"Pollution-driven surface water quality improvement and expanding population benefits in karst regions of China","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs43247-026-04006-9","Karst regions in China have high geological permeability, fragmented river networks, and strong surface–groundwater interactions, making water quality management challenging. Despite their ecological and societal importance, long-term patterns of surface water quality remain poorly understood. Here we provide a nationwide, multi-decadal evaluation of surface water quality in karst regions using remote sensing and machine learning. The results show that surface water quality improved markedly, with the proportion of water bodies classified as the highest quality increasing from 22.7% to 35.9%. Attribution analysis indicates that pollution-related factors account for the dominant contribution across basins (> 65%), whereas climate effects are secondary and land-use contributions are generally small (\u003C 5%). The number of people benefiting from high-quality water rose to 4.86 million by 2020, although 1.36 million people remained exposed to polluted water near expanding settlements. Future scenario projections indicate that these improvements may be reversed without sustained pollution control. These findings highlight the importance of protecting surface water in karst regions for ecosystem and human well-being. Surface water quality in China’s karst regions improved substantially, with top-quality waters increasing by up to 36 percent and 4.86 million people benefiting, but gains may reverse without continued controls, according to remote sensing and machine learning.","中国喀斯特地区地质渗透性强、河网破碎、地表水与地下水相互作用强烈，水质管理面临较大挑战。尽管这些区域具有重要的生态和社会意义，但其地表水水质的长期变化规律仍缺乏系统认识。本研究基于遥感和机器学习，对中国喀斯特地区地表水水质开展了全国尺度、跨数十年的评估。结果表明，地表水水质显著改善，水质类别为最高等级的水体比例从22.7%上升至35.9%。归因分析显示，污染相关因素在各流域中占主导贡献（>65%），气候影响次之，土地利用贡献总体较小（\u003C5%）。到2020年，受益于优质水的人口增至486万，但仍有136万人暴露于不断扩张的居民点附近的污染水体中。未来情景预测表明，若缺乏持续的污染控制，上述改善可能发生逆转。这些发现凸显了保护喀斯特地区地表水对生态系统和人类福祉的重要性。基于遥感和机器学习的研究表明，中国喀斯特地区地表水水质大幅改善，最高等级水体比例增加达36%，486万人因此受益，但若缺乏持续管控，这一改善可能逆转。","Communications Earth & Environment","2026-09-11T00:00:00Z",84,{"impact":190,"substance":18,"depth":17,"authority":106,"freshness":41,"relevant":22,"comment":191},22,"基于遥感与机器学习的全国性喀斯特地区地表水质多年代评估，数据规模大、结论有新意，对农业用水与乡村生态保护有参考价值，但主题偏生态环境而非农业信息化核心，故未达每日精选顶级门槛。",[193],{"name":186,"url":183},[27,28,29,195,196],"水质评价","喀斯特地区",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":199},{"candidates":200,"agricultural_evidence":14,"reason":58},[201,205,209],{"code":40,"score":41,"supported":42,"title":202,"abstract":203,"tags":204},[],[27,45],[27],{"code":48,"score":41,"supported":42,"title":206,"abstract":207,"tags":208},[],[127,128],[29],{"code":54,"score":22,"supported":14,"title":210,"abstract":211,"tags":212},[],[],[28],[214,215],"喀斯特地区 机器学习 水质评价 生态保护","喀斯特地区 机器学习","喀斯特地区机器学习水质评价生态保护-2430","10.1038\u002Fs43247-026-04006-9",{"doi":217,"openalex_id":219,"authors":220,"venue":186,"cited_by_count":63,"oa_url":235,"card":236,"direction":86,"ingested_from":88},"W7212291140",[221,223,225,228,230,232],{"name":222,"orcid":9},"Mingxia He",{"name":224,"orcid":9},"Jie Niu",{"name":226,"orcid":227},"Chuanhao Wu","https:\u002F\u002Forcid.org\u002F0000-0003-4855-7716",{"name":229,"orcid":9},"Dongdong Liu",{"name":231,"orcid":9},"Pan Wu",{"name":233,"orcid":234},"Bill X. Hu","https:\u002F\u002Forcid.org\u002F0000-0003-4490-5250","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs43247-026-04006-9_reference.pdf",{"tldr":237,"method":238,"finding":239,"direction":240,"opportunity":241},"用遥感与机器学习评估中国喀斯特地区地表水水质长期变化及受益人口。","遥感与机器学习，多年代全国尺度水质分类与归因分析。","水质显著改善，污染治理主导，486万人受益，但控制放松可能逆转。","农业绿色发展与碳","可探究农业面源污染在喀斯特水质改善中的具体贡献及持续控制策略。","2026-09-14T23:30:27.091671Z",{"id":244,"title":245,"url":246,"summary":247,"summary_zh":248,"content":9,"source_name":249,"source_url":246,"published_at":250,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":251,"score_detail":252,"sources":254,"tags":256,"primary_topic":9,"secondary_topics":259,"classification":260,"search_phrases":280,"slug":283,"view_count":22,"doi":284,"paper":285,"created_at":302},2062,"Multi-scale drivers of wildfire burn severity in Central Zagros: insights from remote sensing and machine learning","https:\u002F\u002Fdoi.org\u002F10.3832\u002Fifor5027-019","Over the past few decades, wildfire activity has increased globally. In the Central Zagros Mountains of Iran, widespread oak decline has significantly altered fuel structures and raised ecological concerns. However, the specific contribution of long-term vegetation degradation to wildfire burn severity remains under-quantified. This study addresses this gap by investigating whether decadal declines in the Normalized Difference Vegetation Index (NDVI) are associated with higher burn severity, while assessing their relative importance against short-term pre-fire environmental conditions, fuel types, topography, and human access gradients. Focusing on a major wildfire in June 2024 in the Kashkan Watershed, we mapped burn severity using the differenced Normalized Burn Ratio (dNBR) derived from Sentinel-2 imagery. A comprehensive suite of predictors was evaluated, including the long-term NDVI trend (May- September 2014-2023), pre-fire Normalized Difference Moisture Index (NDMI), Land Surface Temperature (LST), fuel categories based on ESA WorldCover, slope, aspect, spatial texture contrast, and distance to roads and settlements. A stratified sampling design supported statistical inference using ordinary least squares regression and predictive modeling via Random Forest and XGBoost algorithms with five-fold cross-validation. XGBoost demonstrated the highest predictive performance (cross-validated R2 = 0.70; RMSE = 0.11), outperforming Random Forest (R2 = 0.64) and linear regression (R2 = 0.34). Fuel moisture (NDMI) and thermal stress (LST) emerged as the primary drivers of severity, followed by land cover, topography, and spatial texture. While the long-term NDVI decline showed a small but consistent positive association with dNBR at the landscape scale, the results highlight a distinct multi-scale mechanism. In this dynamic, pre-fire moisture and temperature establish the broad watershed-scale environmental susceptibility, whereas specific fuel types and their spatial configurations drive the local-level amplification or damping of burn severity. These findings provide a framework for proactive vulnerability mapping in Zagros oak woodlands, suggesting that integrating dynamic fire-weather data and field-based fuel measurements could further refine future predictability.","过去几十年间，全球野火活动日益加剧。在伊朗中扎格罗斯山脉，大范围的橡树衰退显著改变了可燃物结构，并引发了生态担忧。然而，长期植被退化对野火烧毁严重程度的具体贡献仍缺乏充分的量化研究。本研究通过探讨归一化植被指数（NDVI）的十年尺度下降是否与更高的烧毁严重程度相关，填补了这一空白，同时评估了其相对于短期火前环境条件、可燃物类型、地形和人类可达性梯度的相对重要性。以2024年6月卡什坎流域的一场重大野火为研究对象，我们利用Sentinel-2影像衍生的差分归一化燃烧比（dNBR）绘制了烧毁严重程度图。研究评估了一套综合预测因子，包括长期NDVI趋势（2014—2023年5—9月）、火前归一化差异水分指数（NDMI）、地表温度（LST）、基于ESA WorldCover的可燃物类别、坡度、坡向、空间纹理对比度以及与道路和居民点的距离。分层抽样设计支持了普通最小二乘回归的统计推断，并通过随机森林和XGBoost算法结合五折交叉验证进行预测建模。XGBoost表现出最高的预测性能（交叉验证R² = 0.70；RMSE = 0.11），优于随机森林（R² = 0.64）和线性回归（R² = 0.34）。可燃物湿度（NDMI）和热胁迫（LST）是烧毁严重程度的主要驱动因素，其次是土地覆盖、地形和空间纹理。尽管长期NDVI下降在景观尺度上与dNBR呈现出微小但一致的正相关关系，结果仍揭示了一种独特的多尺度机制。在这一机制中，火前湿度和温度奠定了流域尺度的广泛环境脆弱性，而特定可燃物类型及其空间配置则驱动了局部尺度烧毁严重程度的放大或抑制。这些发现为扎格罗斯橡树林地的主动脆弱性制图提供了框架，并表明整合动态火险天气数据和实地可燃物测量可进一步提升未来的可预测性。","iForest - Biogeosciences and Forestry","2026-09-08T00:00:00Z",66,{"impact":107,"substance":104,"depth":105,"authority":20,"freshness":107,"relevant":22,"comment":253},"伊朗扎格罗斯山区野火烧伤严重度多尺度驱动研究，方法扎实但属境外区域案例，对国内农业信息化仅有方法借鉴价值。",[255],{"name":249,"url":246},[27,28,29,257,258],"森林防火","植被退化",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":261},{"candidates":262,"agricultural_evidence":14,"reason":58},[263,267,271,275],{"code":48,"score":13,"supported":42,"title":264,"abstract":265,"tags":266},[128],[],[258,29],{"code":40,"score":21,"supported":42,"title":268,"abstract":269,"tags":270},[45],[],[27],{"code":54,"score":22,"supported":14,"title":272,"abstract":273,"tags":274},[],[],[28],{"code":276,"score":22,"supported":14,"title":277,"abstract":278,"tags":279},"H7",[],[],[257],[281,282],"机器学习 森林防火 植被退化 生态保护","机器学习 森林防火","机器学习森林防火植被退化生态保护-2062","10.3832\u002Fifor5027-019",{"doi":284,"openalex_id":286,"authors":287,"venue":249,"cited_by_count":63,"oa_url":296,"card":297,"direction":86,"ingested_from":88},"W7211926672",[288,290,292,294],{"name":289,"orcid":9},"F Shahidinejad",{"name":291,"orcid":9},"M Jourgholami",{"name":293,"orcid":9},"MM Pourhanifeh",{"name":295,"orcid":9},"A Esfandyar","https:\u002F\u002Fiforest.sisef.org\u002Fpdf\u002F?id=ifor5027-019",{"tldr":298,"method":299,"finding":300,"direction":86,"opportunity":301},"结合遥感与机器学习，量化伊朗扎格罗斯中部野火烧毁严重度的多尺度驱动因素。","Sentinel-2 dNBR、长期NDVI趋势、随机森林与XGBoost建模。","燃料湿度和热胁迫主导烧毁严重度，长期NDVI下降有微弱正相关，呈现多尺度机制。","可引入动态火险天气与地面燃料实测，提升多尺度火险制图与预测精度。","2026-09-10T23:30:28.899368Z",{"id":304,"title":305,"url":306,"summary":307,"summary_zh":308,"content":9,"source_name":309,"source_url":306,"published_at":310,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":311,"score_detail":312,"sources":316,"tags":318,"primary_topic":321,"secondary_topics":327,"classification":338,"search_phrases":374,"slug":377,"view_count":63,"doi":378,"paper":379,"created_at":397},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":313,"substance":314,"depth":105,"authority":20,"freshness":13,"relevant":22,"comment":315},16,21,"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。",[317],{"name":309,"url":306},[112,27,29,319,320],"土壤墒情","冬小麦",{"code":322,"slug":323,"name":324,"path":325,"parent_code":326},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[328,334],{"code":329,"slug":330,"name":331,"path":332,"parent_code":333},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":40,"slug":335,"name":336,"path":337,"parent_code":118},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":121,"locked":14,"version":35,"method":36,"evidence":339},{"candidates":340,"agricultural_evidence":42},[341,347,353,357,362,369],{"code":322,"score":342,"supported":42,"title":343,"abstract":345,"tags":346},26,[344,323],"winter wheat",[324,344,323],[320],{"code":329,"score":348,"supported":42,"title":349,"abstract":350,"tags":352},15,[330],[351,330],"土壤",[319],{"code":40,"score":348,"supported":42,"title":354,"abstract":355,"tags":356},[45],[27,45],[27],{"code":48,"score":13,"supported":42,"title":358,"abstract":359,"tags":361},[],[127,128,360],"multispectral",[29],{"code":363,"score":91,"supported":42,"title":364,"abstract":365,"tags":368},"H3",[],[366,367],"灌溉","irrigation",[],{"code":141,"score":370,"supported":42,"title":371,"abstract":372,"tags":373},4,[],[112],[112],[375,376],"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":378,"openalex_id":380,"authors":381,"venue":309,"cited_by_count":63,"oa_url":306,"card":391,"direction":396,"ingested_from":88},"W7223156204",[382,385,387,389],{"name":383,"orcid":384},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":386,"orcid":9},"Yi Zhang",{"name":388,"orcid":9},"WEI Lei",{"name":390,"orcid":9},"Chengcai Zhang",{"tldr":392,"method":393,"finding":394,"direction":86,"opportunity":395},"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。","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":399,"title":400,"url":401,"summary":402,"summary_zh":403,"content":9,"source_name":404,"source_url":401,"published_at":405,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":63,"score_detail":406,"sources":408,"tags":410,"primary_topic":413,"secondary_topics":414,"classification":420,"search_phrases":442,"slug":445,"view_count":63,"doi":446,"paper":447,"created_at":464},5485,"Integrating machine learning and geospatial technologies for spatio-temporal analysis of urban expansion and land use transformation in Gambella Town, Ethiopia","https:\u002F\u002Fdoi.org\u002F10.1371\u002Fjournal.pone.0360419","Rapid urbanization and the associated expansion of built-up areas are transforming land resources, ecosystem functions, and the spatial structure of cities. Distinguishing urban growth, urban expansion, and urban sprawl is essential for understanding the processes and patterns of urban transformation and supporting sustainable urban planning. This study integrates machine learning and geospatial technologies to analyze spatio-temporal land use and land cover (LULC) dynamics and urban expansion in Gambella Town, Ethiopia. Multi-temporal Landsat satellite images from 2005, 2015, and 2025 were processed using remote sensing techniques and a supervised machine learning approach based on the Random Forest (RF) classifier. Six major LULC classes were identified: Agricultural Land, Bush with Grass, Built-Up Area, Bare Land, Forest Land, and Water Bodies. The classification achieved overall accuracies of 90%, 90%, and 89% for 2005, 2015, and 2025, respectively. The results revealed substantial land transformation and rapid physical urban expansion, with the built-up area increasing from 93 ha (2.0%) in 2005–1,956 ha (41.3%) in 2025. This expansion was accompanied by major transformations of surrounding land resources, particularly the conversion of Bush with Grass and other open areas to built-up land. Agricultural land increased from 634 ha (13.4%) to 1,750 ha (36.9%), whereas Bush with Grass declined from 3,375 ha (71.1%) to 652 ha (13.7%). Socio-economic information collected from 277 respondents indicated that population growth, rural–urban migration, housing demand, employment opportunities, and infrastructure development were major drivers of urban expansion. The study distinguishes urban expansion, represented by the increase in built-up land, from urban sprawl, which refers to the spatial pattern and form of outward urban development. The integration of Random Forest classification and GIS-based spatial analysis provides valuable evidence of land transformation, vegetation loss, and increasing pressure on urban services, supporting more sustainable urban planning and land management in Gambella Town.","快速城市化及与之相关的建成区扩张正在改变土地资源、生态系统功能和城市空间结构。区分城市增长（urban growth）、城市扩张（urban expansion）和城市蔓延（urban sprawl），对于理解城市转型的过程与格局、支撑可持续城市规划至关重要。本研究融合机器学习与地理空间技术，分析埃塞俄比亚甘贝拉镇（Gambella Town）土地利用与土地覆盖（LULC）的时空动态及城市扩张。采用遥感技术和基于随机森林（RF）分类器的监督机器学习方法，处理了2005年、2015年和2025年的多时相Landsat卫星影像。研究识别出六类主要LULC类型：农业用地、灌草地、建成区、裸地、林地和水体。2005年、2015年和2025年的分类总体精度分别为90%、90%和89%。结果表明，土地发生了显著转变，城市实体空间快速扩张，建成区面积从2005年的93公顷（2.0%）增至2025年的1,956公顷（41.3%）。这一扩张伴随着周边土地资源的重大转变，尤其是灌草地及其他开阔地被转化为建成用地。农业用地从634公顷（13.4%）增至1,750公顷（36.9%），而灌草地则从3,375公顷（71.1%）降至652公顷（13.7%）。从277名受访者收集的社会经济信息表明，人口增长、城乡迁移、住房需求、就业机会和基础设施建设是城市扩张的主要驱动因素。本研究将城市扩张（以建成用地增加为表征）与城市蔓延（指城市向外发展的空间格局与形态）加以区分。随机森林分类与基于GIS的空间分析的融合，为土地转变、植被丧失及城市服务压力加剧提供了有价值的证据，有助于甘贝拉镇实现更可持续的城市规划与土地管理。","PLoS ONE","2026-10-20T00:00:00Z",{"impact":63,"substance":63,"depth":63,"authority":63,"freshness":63,"relevant":63,"comment":407},"研究聚焦埃塞俄比亚城市扩张与土地利用变化，属城市地理与遥感应用，与三农、农业信息化主题无直接关联，不建议进入每日精选。",[409],{"name":404,"url":401},[27,29,411,412],"土地利用","城市扩张",{"code":40,"slug":335,"name":336,"path":337,"parent_code":118},[415],{"code":416,"slug":417,"name":418,"path":419,"parent_code":118},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",{"status":121,"locked":14,"version":35,"method":36,"evidence":421},{"candidates":422,"agricultural_evidence":42},[423,427,434,438],{"code":40,"score":348,"supported":42,"title":424,"abstract":425,"tags":426},[45],[27,45],[27],{"code":416,"score":21,"supported":42,"title":428,"abstract":429,"tags":433},[],[430,431,432],"空间分析","GIS","spatial analysis",[],{"code":48,"score":41,"supported":42,"title":435,"abstract":436,"tags":437},[],[127,128],[29],{"code":54,"score":22,"supported":14,"title":439,"abstract":440,"tags":441},[],[],[411],[443,444],"Gambella Town 城市扩张","Random Forest 土地利用分类","GambellaTown城市扩张-5485","10.1371\u002Fjournal.pone.0360419",{"doi":446,"openalex_id":448,"authors":449,"venue":404,"cited_by_count":63,"oa_url":401,"card":459,"direction":86,"ingested_from":88},"W7223022155",[450,453,455,457],{"name":451,"orcid":452},"Kanenus Fufa Dararo","https:\u002F\u002Forcid.org\u002F0009-0007-5747-1558",{"name":454,"orcid":9},"Goanar Jal Dup",{"name":456,"orcid":9},"Weyesa Merga Chemeda",{"name":458,"orcid":9},"Shankar Karuppannan",{"tldr":460,"method":461,"finding":462,"direction":86,"opportunity":463},"用机器学习与遥感分析埃塞俄比亚甘贝拉镇2005-2025年城市扩张与土地利用变化。","Landsat多时相影像、随机森林分类与GIS空间分析，结合277份问卷。","建成区从93公顷增至1956公顷，灌草地大幅转为建成区和农地。","可将随机森林时序分类与驱动力调查结合，扩展到更多非洲小城镇并耦合城市增长模拟。","2026-10-21T23:30:23.271293Z",{"id":466,"title":467,"url":468,"summary":469,"summary_zh":470,"content":9,"source_name":471,"source_url":468,"published_at":472,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":473,"score_detail":474,"sources":476,"tags":478,"primary_topic":480,"secondary_topics":481,"classification":482,"search_phrases":499,"slug":502,"view_count":63,"doi":503,"paper":504,"created_at":522},5323,"Impact of Land Use and Land Cover Change on Vegetation Cover Loss in Rwanda: Evidence from Muhoza Sector, Musanze District (2015–2025)","https:\u002F\u002Fdoi.org\u002F10.38124\u002Fijisrt\u002F26oct696","This study analyzed the impact of land use and land cover (LULC) change on vegetation cover loss in Muhoza Sector, Musanze District, Rwanda, between 2015 and 2025. A quantitative geospatial research design was adopted using multi-temporal Landsat and Sentinel-2 satellite imagery, field-based GPS validation, Geographic Information Systems, and Normalized Difference Vegetation Index (NDVI) analysis. Six land-cover classes—forestland, grassland, cropland, urbanized land, wetland, and water bodies—were mapped using supervised classification and post-classification change detection.","本研究分析了2015年至2025年间卢旺达穆桑泽区穆霍扎地区土地利用与土地覆盖（LULC）变化对植被覆盖丧失的影响。研究采用定量地理空间研究设计，运用多时相Landsat和Sentinel-2卫星影像、基于实地GPS验证、地理信息系统以及归一化植被指数（NDVI）分析。通过监督分类和分类后变化检测，对林地、草地、耕地、城市化用地、湿地和水体六类土地覆盖类型进行了制图。","International Journal of Innovative Science and Research Technology (IJISRT)","2026-10-17T00:00:00Z",55,{"impact":107,"substance":17,"depth":106,"authority":91,"freshness":21,"relevant":22,"comment":475},"基于Landsat与Sentinel-2多时相影像的卢旺达局部土地利用变化与植被损失实证研究，方法规范但属区域案例，国际参考价值有限。",[477],{"name":471,"url":468},[29,411,30,479],"卢旺达农业",{"code":416,"slug":417,"name":418,"path":419,"parent_code":118},[],{"status":121,"locked":14,"version":35,"method":36,"evidence":483},{"candidates":484,"agricultural_evidence":42},[485,491,495],{"code":416,"score":91,"supported":42,"title":486,"abstract":487,"tags":490},[],[488,489],"地理信息","geographic information",[],{"code":48,"score":49,"supported":14,"title":492,"abstract":493,"tags":494},[],[],[30,29],{"code":54,"score":22,"supported":14,"title":496,"abstract":497,"tags":498},[],[],[411],[500,501],"Muhoza Sector 土地利用","卢旺达 NDVI 植被覆盖","MuhozaSector土地利用-5323","10.38124\u002Fijisrt\u002F26oct696",{"doi":503,"openalex_id":505,"authors":506,"venue":471,"cited_by_count":63,"oa_url":516,"card":517,"direction":86,"ingested_from":88},"W7222817253",[507,509,511,513],{"name":508,"orcid":9},"Vincent Hategekimana",{"name":510,"orcid":9},"Richard Mind J. E.",{"name":512,"orcid":9},"Aboubakar Gasirabo",{"name":514,"orcid":515},"Didier Ntwali","https:\u002F\u002Forcid.org\u002F0000-0002-6914-6652","https:\u002F\u002Fwww.ijisrt.com\u002Fassets\u002Fupload\u002Ffiles\u002FIJISRT26OCT696.pdf",{"tldr":518,"method":519,"finding":520,"direction":86,"opportunity":521},"分析卢旺达Muhoza地区2015–2025年土地利用变化对植被覆盖丧失的影响。","多时相Landsat与Sentinel-2影像、GPS实地验证、GIS与NDVI","六类地物制图揭示建设用地扩张等LULC变化是植被覆盖减少的主要驱动。","可结合高分辨率时序遥感与驱动因子模型，量化小农户尺度城镇化对耕地与植被的胁迫。","2026-10-19T23:30:23.040351Z"]