[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2062":3},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"view_count":31,"doi":32,"paper":33,"created_at":52},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。",null,"iForest - Biogeosciences and Forestry","2026-09-08T00:00:00Z","论文",10,false,66,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":17,"relevant":21,"comment":22},8,20,17,13,1,"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。",[24],{"name":10,"url":6},[26,27,28,29,30],"机器学习","生态保护","遥感监测","森林防火","植被退化",0,"10.3832\u002Fifor5027-019",{"doi":32,"openalex_id":34,"authors":35,"venue":10,"cited_by_count":31,"oa_url":44,"card":45,"direction":49,"ingested_from":51},"W7211926672",[36,38,40,42],{"name":37,"orcid":9},"F Shahidinejad",{"name":39,"orcid":9},"M Jourgholami",{"name":41,"orcid":9},"MM Pourhanifeh",{"name":43,"orcid":9},"A Esfandyar","https:\u002F\u002Fiforest.sisef.org\u002Fpdf\u002F?id=ifor5027-019",{"tldr":46,"method":47,"finding":48,"direction":49,"opportunity":50},"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。","农业遥感与作物表型","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。","openalex","2026-09-10T23:30:28.899368Z"]